See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/360168315

A Review of Digital Transformation on Supply Chain Process Management

Using Text Mining

Article in Processes · April 2022

DOI: 10.3390/pr10050842

CITATIONS READS

51 1,638

4 authors:

Madjid Tavana Akram Shaabani

La Salle University Allameh Tabataba'i University
433 PUBLICATIONS 14,317 CITATIONS 12 PUBLICATIONS 309 CITATIONS

SEE PROFILE SEE PROFILE

Iman Raeesi Vanani Rajan Kumar

Allameh Tabataba'i University NITIE-National Institute of Industrial Engineering
92 PUBLICATIONS 813 CITATIONS 14 PUBLICATIONS 164 CITATIONS

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Iman Raeesi Vanani on 25 April 2022.

The user has requested enhancement of the downloaded file.

 processes
Review
A Review of Digital Transformation on Supply Chain Process
Management Using Text Mining
Madjid Tavana 1,2, * , Akram Shaabani 3 , Iman Raeesi Vanani 3 and Rajan Kumar Gangadhari 4

1 Business Systems and Analytics Department, Distinguished Chair of Business Analytics, La Salle University,
Philadelphia, PA 19141, USA
2 Business Information Systems Department, Faculty of Business Administration and Economics, University of
Paderborn, 33100 Paderborn, Germany
3 Department of Industrial Management, Faculty of Management and Accounting, Allameh Tabataba’i
University, Tehran 14896-84511, Iran; shaabani_akram@atu.ac.ir (A.S.); imanraeesi@atu.ac.ir (I.R.V.)
4 Industrial Engineering and Manufacturing Systems, National Institute of Industrial Engineering,
Mumbai 400087, India; rajan.gangadhari.2018@nitie.ac.in
* Correspondence: tavana@lasalle.edu

Abstract: Industry 4.0 technologies are causing a paradigm shift in supply chain process management.
The digital transformation of the supply chains provides enormous benefits to organizations by
empowering collaboration among multiple internal and external organizations and systems. This
study presents a narrative review explaining the existing knowledge on digital transformation in
supply chain process management using text mining. It summarizes the existing literature to explain
the current state of the art in supply chain digitalization. This comprehensive review identifies the
most important topics and technologies and determines the future trends in this emerging field.
We investigate the articles published in Web of Science and Scopus databases and use text mining
techniques (clustering and topic modeling) on the article contents. Using VOS viewer, a bibliometric
analysis of 395 articles with 12,700 references is analyzed. The contents of the articles are explored
Citation: Tavana, M.; Shaabani, A.;
using text mining approaches. The synthesized results reveal that the most important topics in digital
Raeesi Vanani, I.; Kumar Gangadhari, transformation are “sustainable supply chain management” and “circular economy and industry 4.0
R. A Review of Digital technologies”. The study further discovers big data, data analytics, blockchain, artificial intelligence,
Transformation on Supply Chain machine learning, and the Internet of Things as the most critical technologies for facilitating supply
Process Management Using Text chain digital transformation. Finally, an overlay heatmap analysis of the research articles found that
Mining. Processes 2022, 10, 842. digital transformation, supply chain management, industry 4.0, decision-making, and sustainability
https://doi.org/10.3390/pr10050842 are emerging trends in supply chain digitalization.
Academic Editor: Tsai Chi Kuo
Keywords: digital transformation; supply chain management; industry 4.0; text mining; big data; analytics
Received: 20 March 2022
Accepted: 20 April 2022
Published: 24 April 2022

Publisher’s Note: MDPI stays neutral 1. Introduction

with regard to jurisdictional claims in Digital transformation uses digital technologies to create new business processes and
published maps and institutional affil- opportunities to meet the ever-increasing changes in the business environment [1]. Many
iations. organizations use digital transformation technologies (Industry 4.0) to enhance systems
integrations [2]. Supply chain (SC) managers are trying to cut costs and develop more agile,
flexible, connected systems to gain market value to meet the rapidly changing consumer
behaviors and market volatility [3]. Digital transformation helps organizations shorten
Copyright: © 2022 by the authors.
product development, increase flexibility, and generate innovation [4]. It helps people re-
Licensee MDPI, Basel, Switzerland.
This article is an open access article
main competitive in the Internet age [5,6]. The digital transformation uses newly integrated
distributed under the terms and
technologies in the industry to create the industry 4.0 realm and smarter manufacturers [7].
conditions of the Creative Commons It leads to synchronizing production, preventing information distortion, and decreasing
Attribution (CC BY) license (https:// delivery times [8]. Industry 4.0 is an adaptable system that automatically adjusts flexible
creativecommons.org/licenses/by/ production lines for different types of products according to changing conditions. It can
4.0/).

Processes 2022, 10, 842. https://doi.org/10.3390/pr10050842 https://www.mdpi.com/journal/processes

Processes 2022, 10, 842 2 of 19

enhance quality, flexibility, and productivity, leading to customized goods with better
resource consumption [8].
A digital supply chain (DSC) electronically delivers products from origin to desti-
nation [9]. DSC helps increase responsiveness, flexibility, and agility [10]. It uses new
technologies to create a transparent, secure, and reliable supply chain management (SCM)
system [11]. These technologies enable the firms to achieve the customer’s dynamic needs
on time. DSC benefits include cost-effective services and value-added operations, which
can be used by many ecosystem actors [12]. The technologies under digital transformation,
such as the Industrial Internet of Things (IoT) and cyber-physical systems (CPS), help
improve SC performance by bridging the gap between the digital and physical worlds.
Industry 4.0 significantly changes SC behavior towards achieving smarter and more flexible
processes, driving automation and optimization measures, resources efficiency, and overall
welfare of the staff and the society [13]. These emerging new technologies and emerging
digitalization trends have had a tremendous positive impact on SC processes [14].
Different studies in the SC literature investigate the role of digital transformation in
SCM. Tjahjono et al. (2017) [15] investigated the impact of Industry 4.0 on SC. Dolgui et al.
(2018) [16] used control theory to dissolve engineering issues in SCM and Industry 4.0 to
SC optimization. Ramirez-Peña et al. (2020) [17] offered a model under the perspective
of Industry 4.0 to improve and sustainability of SC by considering lean, agile, resilience,
and green dimensions in SC. Zimmermann et al. (2019) [18] investigated the impact of
Industry 4.0 technologies on SC risks. Dallasega et al. (2018) [19] presented a framework
for illustrating Industry 4.0 concepts in construction SCs. Müller and Voigt (2018) [20]
examined the subject of SCM in the field of Industry 4.0 and provided challenges, potentials,
and recommendations for their integration. Ghadimi et al. (2019b) [21] investigated
the stable supplier evaluation and selection process for SCs in Industry 4.0. Manavalan
and Jayakrishna (2019) [22] proposed a conceptual model for SC and considered trade,
technology, sustainable expansion, cooperation, and dimensions of management strategy
to answer the revolution provisions of Industry 4.0. De Giovanni and Cariola (2020) [23]
examined the impact of innovation strategy through the technologies of Industry 4.0 in
lean and green SC.
Büyüközkan and Göçer (2018) [14] proposed a framework for the implementation of
DSC and provided advantages, weaknesses, and limitations. Seyedghorban et al. (2020) [24]
examined the literature on SC digitalization using bibliometric analysis and meta-analysis.
Queiroz et al. (2019) [25] proposed a model for DSC capabilities in Industry 4.0 that include
six main enabler technologies. Nasiri et al. (2020) [26] examined the impact of digital
transformation and smart technologies in improving DSC performance. Kittipanya-Ngam
and Tan (2020) [27] proposed a framework for the digitalization of the food SC.
The following section describes some essential digital transformation technologies that
have improved SC performance. The Internet of Things (IoT) is concerned with connecting
objects to the Internet in the physical world for data sharing [28,29]. Moreover, IoT enables
objects to hear, speak, act, and behave intelligently [30]. As a global network infrastructure,
autonomous machines and devices can interact and collaborate [31]. IoT aims to connect
different electronic devices at any time and place [32] and create commercial activities
inside and outside the companies, i.e., the markets [28]. The IoT technologies support
the integrations of SCs and networks [33] and create commercial activities inside and
outside the companies, i.e., the markets [28]. IoT allows connection, communication, and
interaction between SC drivers, thus allowing dynamic management of global network
operations [32,34]. IoT has a crucial role in the SC process and leads to the automation of
product flows from suppliers to customers [30]. The IoT helps real-time location tracking
of goods/services and vehicles. Using the various sensors attached to the vehicles, the
SC managers can track storage conditions of shipments, including temperature, pressure,
humidity, and other measures linked with product quality and condition. IoT also provides
a robust and secure way to exchange information in the SC, increasing operational processes,
Processes 2022, 10, 842 3 of 19

reducing risk and cost, and improving segmentation, visibility, transparency, adaptability,
flexibility, and virtualization [35].
Blockchain is a digital distributed ledger [36] and a database system that records
transaction data or other information, is securely encrypted, and operates through a con-
sensus mechanism [37,38]. Blockchain cannot be tampered with concerning the use of
cryptographic methods [39] and has many applications that can be used for various types
of transactions, agreements and contracts, tracking, and payment [40]. As the name implies,
it is made up of various blocks, each of which has specific information. In addition, each
block has a unique identity with unique information. It is impossible to change, delete,
or update blockchain information. If any information changes, it is necessary to create
a new block to add information. This unique feature has led to the ability to track and
audit anywhere in the SC, which leads to the SC’s effectiveness and efficiency [41]. Chang
and Chen (2020) [42] have reviewed the blockchain literature in digital SC from the year
2016 to 2021, and this study concludes that the use of blockchain in SCs will improve
the performance, but organizations should focus on addressing the operations issues in
implementing blockchain technologies.
Big data analytics (BDA) is “the process of collecting, organizing, and analyzing
large amounts of data to discover patterns and useful information” [43,44]. Data analytics
and information analysis lead to achieving goals, increasing revenue, reducing the cost
of production or services, reducing fraud, and increasing accountability [45]. BDA has
transformed SCs through various technologies such as sensors, barcodes, RFID, and IoT
for integration and coordination. BDA enables companies to reduce operating costs,
improve SC agility, and increase customer satisfaction as the market changes rapidly, and
ultimately make these companies excel [46]. Using BDA, companies can better understand
patterns, trends, and issues in SC [47]. Due to environmental uncertainties and complexities,
managers must base their decision on data rather than intuition. BDA is very effective
in changing and improving SC performance and helping managers make efficient and
effective decisions [48].
Cloud computing (CC) is a set of distributed computers such as data centers and
servers that provide the requested services and resources over the Internet [49]. CC has
become one of the most critical technologies and ubiquitous to the increasing use of the
Internet, broadband, mobile devices, superior transportation valence, and portable prereq-
uisites for end-users [50]. CC consists of five basic features: self-service, extensive network
access, resource collection, fast traction, and measured service. CC can help integrate the
SC by using geographically dispersed resources and can be prepared rapidly [51].
This research examines the most critical topics in digital transformation and SCM. In
addition, we identify which technologies are used in the SC to digitize and which have
received more attention, and then what the trends have been in recent years. This research
aims to examine the disparate pieces of knowledge published in multiple journals over the
last six years to identify the key technologies that promote the integration and digitalization
of SCs. This analysis aids in understanding the evolution of emerging technologies’ role in
improving SC performance using a literature review. The study by [25] has highlighted the
need for DSCs and that many companies are searching for improving their capabilities by
implementing DSCs. However, understanding of DSCs is still in its early stages. This study
aims to shed light on the role of emerging technologies in improving the performance of
SCs, as well as introducing some core technologies for upgrading conventional SCs. This
research uses text mining techniques on the articles downloaded from Web of Science and
Scopus databases to achieve the study’s objectives. First, we used a VOS viewer to analyze
the downloaded research articles to find the research trends. In the second stage, clustering,
keywords extraction, and topic modeling approaches are used with the help of text mining
approaches. Combining these methods provides a complete understanding of the current
state of digital transformation and SCM research and finds the direction of research in this
field. Generally, the main questions we try to answer through the present paper are:
RQ1. What are the most critical topics in digital transformation and SCM?
 2. Research Framework
The research framework includes two major phases: data collection and data analyt-
ics by VOS viewer and text mining.

Processes 2022, 10, 842 2.1. Data Collection 4 of 19

In this research, a systematic review is adopted to extract information from different
research articles and summarize the findings using various analysis methods. The re-
search process
RQ2. Whichin this research is
technologies areshown
used inin the
Figure 1. of digital transformation and SCM?
fields
Step
RQ3. 1What
involves
are thedetermining
trends in thethe field
field of
of digital
research, keywords, and
transformation andsearch
SCM?terms to ex-
ploreThe
on remainder
online databases. keywords
of this research is asA:follows.
“SupplySection
chain”, “supply the
2 presents chain management”,
proposed research
framework,
“digital supplydata collection,
chain”, “smart and the tools
supply used
chain”, for analysis.
“supply Section
chain 4.0”; 3 presents4.0”,
B: “Industry the results
“tech-
and conclusions,
nologies”, and
“digital Section 4 concludes
transformation”, and the study.
“digitalization”; and C: “Big data analytics”,
“blockchain”, “internet of things”, “3D printing”, “additive manufacturing”, “cloud com-
2. Research
puting”, Framework
“machine learning”, and “artificial intelligence”.
The research
Step 2 involvesframework
searchingincludes
keywords twoinmajor
online phases: data(Web
databases collection and data
of Science andanalytics
Scopus)
bythe
in VOS viewer
journal and text
articles’ mining.
titles, keywords, and abstracts.
Step 3 involves text mining and the co-word, network visualization-analysis on the
2.1. Data Collection
journal articles. This step applies clustering, topic modeling, and labeling techniques to
In this articles.
the journal research, a systematic review is adopted to extract information from different
research
Steparticles and analyzing
4 involves summarizethe theinterpretation
findings usingofvarious
results analysis methods.
and writing The research
conclusions based
process
on in this research is shown in Figure 1.
the findings.

Phase 1 Phase 2 Phase 3 Phase 4

Determine the field of Search the keywords on Text mining and co-word,
Analysis of the findings
research and keywords the online databases network visualization

(A: Supply chain supply chain

management digital supply Finding the most important
chain smart supply chain Text mining approaches: topics
supply chain B: Industry Databases:
Clustering and topic modelling
technologies digital Web Of Science and Scopus
by python 3.8.3 software Identifying the most important
transformation and
technologies in digital
digitalization C: Big data Journal articles
analytics blockchain internet co-word occurrence, keywords transformation of SCM
of things D printing additive network, density visualization
Timeline: 2015-2021
manufacturing cloud using VOS viewer Exploring the recent research
computing machine learning trends in SCM
and artificial intelligence )

Figure
Figure 1.
1. Research
Research process.
process.

Step 1 involves determining the field of research, keywords, and search terms to
explore on online databases. keywords A: “Supply chain”, “supply chain management”,
“digital supply chain”, “smart supply chain”, “supply chain 4.0”; B: “Industry 4.0”, “tech-
nologies”, “digital transformation”, and “digitalization”; and C: “Big data analytics”,
“blockchain”, “internet of things”, “3D printing”, “additive manufacturing”, “cloud com-
puting”, “machine learning”, and “artificial intelligence”.
Step 2 involves searching keywords in online databases (Web of Science and Scopus)
in the journal articles’ titles, keywords, and abstracts.
Step 3 involves text mining and the co-word, network visualization-analysis on the
journal articles. This step applies clustering, topic modeling, and labeling techniques to the
journal articles.
Step 4 involves analyzing the interpretation of results and writing conclusions based
on the findings.
To begin the analysis, we used the web of science and Scopus databases to collect
the articles’ information. First, we considered the timeline of 2000–2021 for searching the
articles, but the search results showed that the number of articles published before 2015 was
very few. Since digitalization and industry 4.0 technologies have been getting researchers’
attention for the past few years, we restricted our search to the timeline 2015–2021. After
Processes 2022, 10, 842 5 of 19

the initial examination, 1340 articles were found using keywords A–C in 2015–2021. The
1340 articles were manually checked to remove irrelevant ones by reading the details in
the title, abstract, and keywords. A total of 395 journal articles were found to be related
to the study’s objectives after the initial screening. Table 1 shows the summary of articles
considered for further analysis.

Table 1. Number of articles collected.

Journal Name Number H-Index Impact Factor

1 Journal of Cleaner Production 28 173 7.246
2 International Journal of Production Economics 26 93 3.954
3 Computers in Industry 24 172 5.134
4 Technological Forecasting and Social Change 23 70 3.605
5 Production Planning and Control 21 103 5.846
6 Computers in Industry 19 100 3.954
7 International Journal of Production Research 18 125 4.577
8 Sustainability 18 85 2.798
9 Computers and Industrial Engineering 18 121 4.135
10 Resources, Conservation, and Recycling 17 119 8.086
11 International Journal of Information Management 14 99 8.210
12 Industrial Marketing Management 8 125 4.695
13 Transportation Research Part E: Logistics and Transportation Review 8 110 4.690
14 Journal of Manufacturing Technology Management 5 70 3.385
15 Supply Chain Management: An International Journal 5 115 4.725
16 Journal of Purchasing and Supply Management 4 80 4.640
17 Business Horizons 4 87 3.444
18 European Journal of Operational Research 3 243 3.806
19 Future Generation Computer Systems 3 119 5.387
20 Applied Soft Computing Journal 3 143 5.472
21 Computers and Chemical Engineering 2 139 4.000
22 Expert Systems with Applications 2 184 4.292
23 other 124
Total 395

Figure 2 presents the articles published each year; it is observed that SC and digital
Processes 2022, 10, x FOR PEER REVIEW
transformation 6 of 20
articles have significantly increased from 2019. It indicates that research
studies in SCM focus on using the latest technologies.

Figure 2.
Figure 2. Number
Number of
of articles
articles published
published per
per year.
year.

Keyword
Keywordanalysis
analysisofofthe
theselected
selected papers
papersononthethe
digital transformation
digital transformation indicates thatthat
indicates big
data, blockchain,
big data, blockchain,DSC,DSC,
machine learning,
machine cyber-physical
learning, systems,
cyber-physical etc., have
systems, etc.,been
havefrequently
been fre-
cited andcited
quently usedand in the academic
used literatureliterature
in the academic in recentinyears (see
recent Figure
years (see3). The limitation
Figure of
3). The limi-
VoS viewer
tation of VoSis itviewer
only works on the
is it only keywords,
works on theand it cannotand
keywords, readitarticle
cannot titles,
readabstracts, and
article titles,
other sections
abstracts, andexcept citationsexcept
other sections co-network analysis.
citations The keywords
co-network analysis.analysis of the academic
The keywords analysis
articles
of the academic articles might reveal some helpful information. Still, the findingsbecause
might reveal some helpful information. Still, the findings are not complete are not
keywords only carry
complete because commononly
keywords words, andcommon
carry much of words,
the information
and much available in the other
of the information
sections
availableofinthe
thearticle
otherissections
unutilized.
of theToarticle
overcome the limitation,
is unutilized. we havethe
To overcome used text mining
limitation, we
have used text mining approaches to analyze the content available in the title, keywords,
and abstract to find valuable insights regarding the digital transformation of SCM.
 quently cited and used in the academic literature in recent years (see Figure 3). The li
tation of VoS viewer is it only works on the keywords, and it cannot read article tit
abstracts, and other sections except citations co-network analysis. The keywords analy
of the academic articles might reveal some helpful information. Still, the findings are
complete because keywords only carry common words, and much of the informat
Processes 2022, 10, 842 6 of 19
available in the other sections of the article is unutilized. To overcome the limitation,
have used text mining approaches to analyze the content available in the title, keywor
and abstract to find valuable insights regarding the digital transformation of SCM.
approaches to analyze the content available in the title, keywords, and abstract to find
valuable insights regarding the digital transformation of SCM.

Figure 3. Keyword
Figureoccurrence
3. Keywordinoccurrence
the selectedinpapers.
the selected papers.

2.2. Text Mining

Text mining is a process to extract meaningful information from massive datasets. The
efficiency of the text mining approaches depends on the quality size of the data and model
training [52–54] and includes a set of linguistic, statistical, and machine learning (ML) that
models and structure textual content information techniques for business intelligence and
research or review [55,56]. In recent years, text mining has offered solutions to analyzing
huge content of academic literature; it can save the time and effort required for analyzing
the documents [57]. Some of the works that used text mining approaches in analyzing the
literature of SCM are [52,58,59].

2.2.1. Clustering and Topic Modeling Techniques

Text clustering is an ML technique for unstructured learning that groups articles
based on their similarity. Depending on the purpose of the study size of the documents,
researchers can use suitable algorithms for finding from the document [60]. Some standard
clustering algorithms include hierarchical clustering, grid-based clustering, partitioning,
density-based clustering, etc. Out of the different clustering approaches, we have used the
T-SNE algorithm to analyze the articles due to its advantages of handling high dimensional
data and reducing it to two to three dimensions for easy visualization [61]. Clustering
techniques are used to distribute the papers according to the class (content) of the papers.
T-SNE clustering was applied to articles’ titles, keywords, and abstract sections. After the
clustering technique, we performed the topic modeling technique to reveal the hidden
patterns in the generated clusters. Topic modeling is a text mining approach that is fre-
quently used to extract patterns and useful information from unstructured data [57]. A
topic includes a set of words that are often put together, and various types of approaches
are available in topic modeling [54]. The Latent Dirichlet Allocation (LDA) algorithm is
Processes 2022, 10, 842 7 of 19

the most wieldy applied technique for topic modeling [62] that was introduced by [63].
LDA techniques discover a set of common frequently occurring patterns based on their
co-occurrence and semantic information. In this study, we have also used text clustering
Processes 2022, 10, x FOR PEER REVIEW 8 of 20
techniques to present the clustered keywords in groups. The text mining process used in
this research (Phases 3,4 in Figure 1) is shown in Figure 4.

Step 1 Step 2 Step 3 Step 4

Text pre-processing Word frequency Clustering Topic modeling

Remove of punctuation, To identify the most Text clustering on the

Topic modelling:
numbers and stop words frequent words/ Word results of topic modelling:
LDA Model
cloud T-SNE technique
Tokenization
(Titles, abstracts and
(Titles, abstracts and (Titles, abstracts and
keywords of the articles)
Lemmatization keywords of the articles) keywords of the articles)

Figure 4. The
Figure 4. The process
process of
of text
text mining.
mining.

3. Results
Step 1: This step includes text pre-processing (removing punctuation, numbers and
stop In
words, tokenization).
this section, Tokenization
we analyzed the resultsis breaking downarticles
of 395 journal sentences intomining
by text a set ofand
words
VOSr
called tokens Punctuations such as (, . ;:’ ‘ “) are removed as they do
viewer software. We used different bibliographic information such as titles, keywords,not carry in useful
information.
and abstracts Stop-words
to extract theare removedfrom
keywords as theythe occur
list of frequently andwe
articles. First, doused
not carry any
the word
useful information.
cloud technique using Python 3.8.3 software, and the results are shown in Figures 5–7. In
2: Thisofstep
Step phase
the initial worduses the modeling,
cloud word cloud technique
some common to words
presentrelated
the frequently
to SCM wereoccurring
over-
words in the documents. The size of a word represents its frequency
fitted over other words. To reveal the hidden words from the text, we have added some of occurrence in
the documents.
standard SCM words such as “supply chain”, “industry”, and “system” to the standard
This
Step 3:list
stop-words step applies
of NLTK text
to avoid clustering
their presencetointhe thetitles,
word abstracts,
cloud. As and
shown keywords to
in Figures
create clusters of articles discussing a similar topic. Additionally, after
5–7, the research article in the SC digitalization has highly used words such as “empiricalclustering and
dimensionality reduction with the T-SNE technique, we use VOS viewer software to
study”, “blockchain”, “emerging technologies”, “information”, “forecast”, big data”,
visualize the words. Then, we analyze the results of the text mining technique and VOS
“manufacturing”, “barrier”, “digitalization”, “analytics”, “perspective”, “internet”,
viewer software.
“things”, “sustainable”, “circular economy”, “smart manufacturing”, “digital transfor-
Step 4: This step applies LDA topic modeling on the titles, abstracts, and keywords of
mation”, “digital”, “artificial intelligence”, “machine learning”, “cloud computing”, and
the articles to get an overall understanding of the text.
“IOT”. These frequent words give us some important information about the emerging
trends and recent developments in the subject domain [64].
3. Results
In this section, we analyzed the results of 395 journal articles by text mining and VOS
viewer software. We used different bibliographic information such as titles, keywords, and
abstracts to extract the keywords from the list of articles. First, we used the word cloud tech-
nique using Python 3.8.3 software, and the results are shown in Figures 5–7. In the initial
phase of word cloud modeling, some common words related to SCM were overfitted over
other words. To reveal the hidden words from the text, we have added some standard SCM
words such as “supply chain”, “industry”, and “system” to the standard stop-words list of
NLTK to avoid their presence in the word cloud. As shown in Figures 5–7, the research arti-
cle in the SC digitalization has highly used words such as “empirical study”, “blockchain”,
“emerging technologies”, “information”, “forecast”, big data”, “manufacturing”, “barrier”,
 and abstracts to extract the keywords from the list of articles. First, we used the word
cloud technique using Python 3.8.3 software, and the results are shown in Figures 5–7. In
the initial phase of word cloud modeling, some common words related to SCM were over-
fitted over other words. To reveal the hidden words from the text, we have added some
standard SCM words such as “supply chain”, “industry”, and “system” to the standard
Processes 2022, 10, 842 8 of 19
stop-words list of NLTK to avoid their presence in the word cloud. As shown in Figures
5–7, the research article in the SC digitalization has highly used words such as “empirical
study”, “blockchain”, “emerging technologies”, “information”, “forecast”, big data”,
“digitalization”,
“manufacturing”, “analytics”,
“barrier”,“perspective”, “internet”,
“digitalization”, “things”,
“analytics”, “sustainable”,“internet”,
“perspective”, “circular
economy”, “smart manufacturing”,
“things”, “sustainable”, “digital transformation”,
“circular economy”, “digital”, “digital
“smart manufacturing”, “artificial intelli-
transfor-
gence”, “machine learning”, “cloud computing”, and “IOT”. These frequent words
mation”, “digital”, “artificial intelligence”, “machine learning”, “cloud computing”, andgive us
some important information about the emerging trends and recent developments
“IOT”. These frequent words give us some important information about the emerging in the
subject
trends domain [64].
and recent developments in the subject domain [64].

Processes 2022, 10, x FOR PEER REVIEW 9 of 20

Figure5.5.Word
Figure WordCloud
Cloudon
on“Title”.
“Title”.

Figure6.6. Word
Figure WordCloud
Cloudon
on“Abstracts”.
“Abstracts”.

Each keyword may give us some significant information about the emerging trends,
but sometimes we cannot draw useful insights using one word’s occurrence. For example,
the phrase “blockchain” example has occurred 462 times, “barrier” 327 times, “sustainabil-
ity” 179 times in 395 articles, which means recent studies have been discussing the use
of blockchain, adaption-related barrier issues, and sustainability-related issues in SCM.
An inference can be made using the word cloud in Figures 5–7—that empirical studies
about the usage of emerging technologies such as blockchain, big data, and information
management have been increasing in recent years. However, without further analysis, it is
difficult to know the context, and the purpose of using these words is unclear. To overcome
this ambiguity and find the areas or the purpose of using the above keywords mentioned
in the word clouds, we have used clustering and topic modeling techniques available in
text mining approaches. Clustering divides the data or information such that data points
in the same groups are more similar to other data points. The topic modeling techniques

Figure 7. Word Cloud on “Keywords”.

Processes 2022, 10, 842 9 of 19

are probabilistic models that analyze the word occurrence and the association between the
words
Figure using the
6. Word probabilities.
Cloud on “Abstracts”.

Figure 7. Word
Figure7. WordCloud
Cloudon
on“Keywords”.
“Keywords”.

Due to the vast content and diversity of subjects discussed by academic articles, it is
Each keyword may give us some significant information about the emerging trends,
difficult for researchers to keep up with new information about the digital transformation
but sometimes we cannot draw useful insights using one word’s occurrence. For example,
of SC. The collection of literature can be represented by a scatter plot using clustering
the phrase “blockchain” example has occurred 462 times, “barrier” 327 times, “sustaina-
for labeling and dimensionality reduction for visualization. On this plot, publications of
bility” 179 times in 395 articles, which means recent studies have been discussing the use
highly similar topics will share a label and will be plotted near each other. Topic modeling
of blockchain, adaption-related barrier issues, and sustainability-related issues in SCM.
was performed to find the keywords of each cluster to find meaning in the clusters. As
An inference can be made using the word cloud in Figures 5–7—that empirical studies
discussed in Section 2.2.1 of this study, clustering was applied, and an automatic label
about the usage of emerging technologies such as blockchain, big data, and information
extraction algorithm for labeling the generated results using Gensim. We used the T-SNE
management have been increasing in recent years. However, without further analysis, it
clustering technique to similar group articles. It groups the articles based on features and
is difficultsimilarity,
semantic to know the context,inand
as shown the purpose
Figures 8–10. The of using theseof
clustering words is unclear.
the articles To over-
divided the
come this ambiguity
information from titlesand
intofind the areas
3 clusters, or the purpose
abstracts of using
into 5 clusters, andthe above keywords
keywords men-
into 4 clusters.
tioned in
Finally, the
the word clouds,
Gensim supportedwe have used clustering
automated and topic modeling
labeling algorithm techniques
has been used avail-
to label the
clusters. The Gensim supported auto-labeling feature (see Table 2) has labeled KC4data
able in text mining approaches. Clustering divides the data or information such that as
points ineconomy
“Circular the same groups
and are more
sustainable similar to
development other data
in supply points.
chains”. We The
havetopic
usedmodeling tech-
the keywords
niques
in topicsare
andprobabilistic models
labels generated bythat analyzetothe
the genism word
label theoccurrence and the
generated topics association
manually. be-
Based
tween
on the words label
the automatic usinggeneration
the probabilities.
result and manual interpretation of words in the topics,
Due to the vast content and diversity
the final topic is labeled “Systematic reviews of subjects discussed
in sustainable by academic
supply articles, it is
chain management”.
difficult for researchers to keep up with new information about the digital
The other two topics for titles are labeled “Big data, blockchain research in supply chaintransformation
of SC. The collection
management” of literature
and “Digital can be represented
manufacturing and supply by chain
a scatter plot using clustering
management”. for
The results
labeling and dimensionality reduction for visualization. On this plot,
are shown in Table 2. We named the clusters based on topic modeling results and analyzed publications of
the clusters according to these names.
Out of many topic modeling techniques, the Latent Dirichlet Allocation (LDA) is
proven to give better results than other techniques [65]. To extract the topics (patterns of
text) from research articles, we have applied LDA on the titles, keywords, and abstract
of the final 395 articles individually. For this process, we have converted the required
bibliometric information into a CSV file and used python programming language for the
analysis. The LDA model performance depends on the tuning parameters. To identify
the optimal number of topics for topic modeling, we have used coherence perplexity
measures [66].
 in topics and labels generated by the genism to label the generated topics manually. Based
on the automatic label generation result and manual interpretation of words in the topics,
the final topic is labeled “Systematic reviews in sustainable supply chain management”.
The other two topics for titles are labeled “Big data, blockchain research in supply chain
management” and “Digital manufacturing and supply chain management”. The results
Processes 2022, 10, 842 10 of 19
are shown in Table 2. We named the clusters based on topic modeling results and ana-
lyzed the clusters according to these names.

Figure 8.
Figure 8. Clustering
Clustering on
on “Title”.
“Title”.

Processes 2022, 10, x FOR PEER REVIEW 11 of 20

Figure 9. Clustering
Figure 9. Clustering on
on “Abstract”.
“Abstract”.

Figure 10. Clustering on “Keywords”.

Figure 10. Clustering on “Keywords”.

Out of many topic modeling techniques, the Latent Dirichlet Allocation (LDA) is
proven to give better results than other techniques [65]. To extract the topics (patterns of
text) from research articles, we have applied LDA on the titles, keywords, and abstract of
Processes 2022, 10, 842 11 of 19

Table 2. Topic modeling and cluster analyzing using topic modeling technique (LDA), word embed-
ding word2vec.

Automatic Cluster
Component Cluster Number Label Extraction Using Manual Interpretation LDA Output on Each Cluster
Word Embedding Technique
[‘0.568 * “Literature” + 0.415 * “review” + “0.027 *
Supply chain management Systematic reviews in the area “sustainable” + 0.014 * “management” + ”0.016*
TC1 integration using systematic of sustainable supply chain “supply” + 0.012 * “chain” + “0.009 * “application”,
literature reviews management “0.007 * “systematic” + “0.007* “circular” + “0.003 *
“research”’]
[“0.412 * Big data”, “0.267 * manufacturing”, “0.051 *
Title Big supply chain management
Big data, blockchain research in blockchain”, “0.046*model”, “0.026 * adoption”, “0.021 *
TC2 service industry using
supply chain management performance”, “0.019 * industry”, “0.007 * supply”,
blockchain big data analytics
“0.004 * chain”, “0.004 * management”]”
[“0.018 * digital”, “0.018 * food”, “0.016 * industry”,
Impact digital manufacturing
Digital manufacturing and “0.012 * technology”, “0.009 * management”, “0.008 *
TC3 supply chain
supply chain management framework”, “0.007 * impact”, “0.006 * smart”, “0.004 *
framework research
model”, “0.004 * analytics”]
[‘0.023 * “provide” + 0.215 * “develop” + “0.119 *
Practical approaches to “technology” + 0.014 * “sustainability” + ”0.009 *
Estimate challenges
AC1 sustainable supply “practice” + 0.007 * “model” + “0.006 * “company”,
supply chain
chain management “0.006 * “study” + “0.004 * “industry” + “0.003 *
“approach”’]
[‘0.016 * “application” + 0.011 * “digital” + “0.011 *
Information systems and digital “supply_chain” + 0.009 * “information” + ”0.009 *
AC2 Forecast serve basic planning
transformation models “system” + 0.008 * “trust” + “0.008 * “cost”, “0.008 *
“firm” + “0.006 * “measurement” + “0.003 * “model”’]
[‘0.030 * “block_chain” + 0.219 * “traceability” + “0.018 *
Abstract Blockchain, strategy
“use” + 0.016 * “system” + ”0.014 * “product” + 0.012 *
AC3 Identify blockchain literature applications in supply
“purpose” + “0.008 * “application”, “0.007 *
chain management
“stratergy”+ “0.006 * “provide” + “0.005 * “market”’]
[‘0.028 * “technology” + 0.020 * “supply_chain” + “0.018
Big data research in supply * “big_data” + 0.012 * “impact” + ”0.012 * “research” +
AC4 Firm access big data analysis
chain 0.011 * “identify” + “0.009 * “paper”, “0.009 * “industry”
+ “0.008 * “issue” + “0.006 * “metric”’]
[‘0.568 * “review” + 0.415 * “field” + “0.027 * “paper” +
Purpose paper aim identify
Literature reviews in 0.014 * “article” + ”0.016 * “research” + 0.012 *
AC5 literature blockchain
supply chain “challenge” + “0.009 * “supply_chain”, “0.007 *
supply chain.
“systematic” + “0.007 * “process” + “0.003 * “concept”’]
[‘0.294 * “block” + 0.272 * “chain” + “0.117 * “emerge” +
Blockchain, 0.109 * “sustainability” + ”0.071 * “supply” + 0.012 *
KC1 Emerging blockchain research
sustainability-related research “chain” + “0.008 * “research”, “0.007 * “important” +
“0.005 * “article” + “0.002 * “focus”’]
[‘0.030 * “decision” + 0.013 * “time” + “0.011 * “read” +
Decision support techniques in 0.011 * “support” + ”0.009* “engineer” + 0.009 *
KC2 Analytic infrastructure
global emerging markets “system” + “0.007 * “global”, “0.007 * “study” + “0.004 *
Keywords “various” + “0.002 * “market”’]
[‘0.036 * “data” + 0.024 * “big” + “0.020* “manage” +
Big service application in Big data-based smart 0.017 * “field” + ”0.016 * “application” + 0.010 *
KC3
supply chain management manufacturing “industry” + “0.009 * “manufacturing”, “0.008 *
“outer”+ “0.007 * “analysis” + “0.007 * “role”’]
[‘0.082 * “evidence” + 0.061 * “supply” + “0.006 *
Circular economy and
“circular” + 0.006 * “economy” + ”0.006 * “value” +
KC4 Supply chain management sustainable development in
0.006 * “challenge” + “0.004 * “manage”, “0.004 * “role”
supply chains
+ “0.004 * “progress” + “0.003 * “chain”’]

The perplexity coherence score gave optimal values for the topic modeling of research arti-
cle titles for n = 3 topics. We have used multiple iterations and observed the generated results. At
50 no of passes, n = 3 topics, the generated three topics were converging meaningful results. The
generated results are reported in Table 2. To interpret the output of topic modeling, we explain
Topic 1 generated using titles. In Topic 1, the frequent keywords with co-occurrence of [0.568 *
“Literature” + 0.415 * “review” + “0.027 * “sustainable” + 0.014 * “management” + ”0.016* “sup-
ply” + 0.012 * “chain” + “0.009 * “application”, “0.007 * “systematic” + “0.007 * “circular” + “0.003
* “research”’] (see Table 2), which implies that the above words in the braces occur frequently
together in the titles of research articles. The “literature” has a high coefficient of 0.568, which
indicates that this word has a high contribution to the topic. Therefore, the top 10 words which
make up the topic are extracted.
Processes 2022, 10, 842 12 of 19

Additionally, we have shown the results of clustering in Figures 8–10. These clusters
are based on the topic modeling results shown in Table 2.
We have identified the important clusters based on the clustering and topic modeling
results. In summary, the important topic and clusters include “Sustainable supply chain
management”, “big data, blockchain in supply chain management and smart manufacturing”,
“Digital manufacturing and supply chain management”, “practical approaches to sustainable
supply chain management”, and “circular economy and sustainable development in supply chains”.
Due to increasing competition among the organizations at the global level, adopting
sustainability in SCM is more important for production organizations [67]. Additionally, the
industries are rapidly moving towards digitization. Therefore, these developments cannot
be ignored and are traditionally managed by the SC [68]. Sustainability affects the whole
production process, from raw materials, managing inventory, production processes, sales,
and marketing to using and recycling the product or service. Therefore, manufacturers
need to use novel methods to track their acts in the SC. For example, one of the dimensions
of sustainability is paying attention to the environment and then reducing waste, recyclable
packaging, and eco-friendly materials in the manufacturing processes. It leads to reduced
cost, improved product quality, customer loyalty, and strengthening of the brand and
SC sustainability.
Another trend is the circular economy in SCs. The circular economy concept is to
eliminate waste by adopting appropriate resource-efficient methods from a sustainability
viewpoint [69]. A circular economy as a sustainable strategy aims to maximize the use
of resources. The circular flows lead to the high utilization of resources based on waste
minimization approaches such as reducing, redesigning, reusing, repairing, recycling, and
remanufacturing [70]. A circular economy supports SCs by the material recovery process
in closed-loop and open-loop flow and increases the product life cycle, components, and
useful waste outputs [71].
According to clustering results from Figure 8, it can be inferred that the blockchain
and big data research in SCM is a widespread cluster. Research in this domain is constantly
evolving; the topic modeling results can help us understand the emerging areas in the
cluster. From keywords in Topic TC2, we found the topics of blockchain models, adoption,
performance, and big data applications in manufacturing industries are the important
topics in SCM in recent years.
Additionally, the text mining approaches have helped identify the emerging areas
and knowledge groups that the timeline of the evolution of the new developments did
not capture. The VOS viewer software plots the timeline of emerging digitalization trends
in SCM. Figure 11 shows the trend of the keywords that were cited year-wise. From
Figure 11, it can be observed that big data, blockchain, cloud computing, digital twin,
food supply chain, and IoT have been the emerging areas since 2019. Health care, service
sector, agriculture, agriculture, digital technologies, etc., are the key areas emerging in
2021. The topic modeling and VoS viewer results conclude that digital technologies such as
blockchain, IoT, artificial intelligence, machine learning, cyber-physical systems, big data
analytics, digital storage, and cloud computing are the main technologies considered in
2018 2021 for digital transformation and SCM.
Additionally, to show the SC and digital transformation trend, we used the articles
published from 2017 to 2021. The results are shown in Figure 12. The heatmap anal-
ysis of the research articles has confirmed that digital transformation, big data, digital
manufacturing, IoT, industry 4.0, decision-making, and sustainability are trending topics.
Processes 2022, 10, x FOR PEER REVIEW 14 of 20

Processes 2022, 10, 842 13 of 19

Figure 11. Keyword overlay visualization by VOS viewer software.

Additionally, to show the SC and digital transformation trend, we used the articles
published from 2017 to 2021. The results are shown in Figure 12. The heatmap analysis of
the research articles has confirmed that digital transformation, big data, digital manufac-
turing, IoT,
Figure 11. industry
Keyword 4.0, decision-making,
overlay and
visualization by VOS sustainability
viewer software. are trending topics.

Additionally, to show the SC and digital transformation trend, we used the articles
published from 2017 to 2021. The results are shown in Figure 12. The heatmap analysis of
the research articles has confirmed that digital transformation, big data, digital manufac-
turing, IoT, industry 4.0, decision-making, and sustainability are trending topics.

Figure
Figure 12.
12. Cluster
Cluster density
density visualization
visualization of
of trends
trends (digital
(digital transformation and SCM).
transformation and SCM).

Additionally, big data and blockchain in SCM are essential issues that have been
considered in recent years. One significant feature of blockchain is that it operates on
a decentralized network. That means there is nothing to control or manage the system,
Figure
and 12.need
the Cluster
fordensity visualization
a third of trendsthe
party to control (digital transformation
process disappearsand[72].
SCM).Advocators in
implementing blockchain in SC have expressed that increasing efficiency and transparency
through blockchain can positively affect SC activities. Inventory management, material
Processes 2022, 10, 842 14 of 19

flow, product and service design, and delivery and payment are only some SC activities
affected [73].
The impacts of BD on SC include BD acquisition sources in SC: acquisitions of BD in
SCM are from various sources in SC. The sources are suppliers, manufacturers, logistics,
distribution, and/or retail [74]. Reducing Delivery Time: BD analysis connected the systems
with customers’ systems, allowing moving the data ahead of packages [75]. One way to
find out about customer needs is BD. Using BD can provide services tailored to customers’
needs that attract customers and increase sales [75,76]. Reducing Inventory Costs: using BD,
inventory can be kept at a low level because data relating to the past can be used to predict
the future [75]. Other impacts include improving efficiency, risk assessment, and reaction
time [76], and improvements in the economy and competitiveness and performance [77].

4. Discussion
This study aimed to provide an overview of existing supply chain digitalization
knowledge using text mining techniques. Systematic literature reviews are valuable and
popular, but they are a complex task that requires a lot of time and is prone to human
error [78,79]. This study uses text mining approaches to discover the latest trends in Digital
Transformation in Supply Chain Process Management rather than traditional literature
review analysis techniques. Our approach was to analyze 395 journal articles published
from 2015 to 2021 using the text mining approach to achieve our objectives: (i) identifying
the most critical topics, (ii) determining the main technologies used in SCM and how to
improve SC performance, and (iii) a complete understanding of the current state of digital
transformation and SCM researches and future research directions and trends.
To achieve our first objective, first, we retrieved research articles from Web of Science
and Scopus databases. All the required information was downloaded in CSV format, and
clustering and topic modeling analysis were performed using Python. The clustering and
topic modeling results showed that literature reviews in the areas of sustainable supply
chains, circular economy, big data analytics, and decision support systems are increasing,
and these studies are receiving the attention of scholars in the SCM domain. This is because
modern SCs are experiencing a compulsion to adopt green practices, reduce emissions,
and design eco-friendly packaging and logistics operations. In a study conducted by [80],
consumers are becoming cautious about the environmental impact of the product/service
they are utilizing, which affects SC to improve their socio-environmental performance.
These situational factors are driving the organization to adopt green practices. To aid
in the decision-making process, these complex operating conditions can be achieved by
deploying big data analytics and IoT technologies. Indeed, several papers in our literature
review connect the adoption of those technologies and firms’ sustainability performance
and circular economy. A network analysis of keywords associated with circular economy
revealed highly co-occurring with “big data, digital storage, automation, industry 4.0,
life cycle, data analytics”. The organization should focus on these areas to achieve the
targets of sustainability and circular economy. A close investigation of the articles citing
these keywords will give us detailed insights that can help sustain economic growth in the
coming post-COVID-19 pandemic years
Our second objective was to determine the critical technologies that are used to
digitalize modern SCs. A detailed analysis of keywords and abstracts sections of the
research papers has revealed that big data analytics, Blockchain, IoT, AI, and ML have been
considered important technologies used in modern SCM. Results also emphasized that
these technologies positively impact SCM and improve SC performance and integrate SC.
In general, AI analytics aid in predicting customer behaviors, target market orientation,
supplier activity, delivery time, inventory requirements, and inventory costs using data.
Manufacturers can use the customer’s vision to predict the state of their products and make
changes accordingly. Additionally, manufacturers can predict the supplier activity and
the quality of their products and investigate the effect of the activities of their suppliers in
the SC and the delivery time of the suppliers. In modern SCs, IoT provides flexibility and
Processes 2022, 10, 842 15 of 19

connectivity in information sharing and processing. DSCs require integrated supply chain
information models, and IoT technologies can help with information integration and service
automation [12]. ML is another critical technology that plays an essential role in optimizing
the modern complex, agile SCs. [81] reviewed the ten years (2009–2019) of literature
published, having the keywords “machine learning” and “supply chain”. This study
has identified some critical areas where ML can increase the SC performance, including
selecting the supply chain partner using various parameters, demand forecasting, resources
optimization, detecting false RFID signals, selection of manufacturing and warehousing
location, etc. In addition, with the use of ML techniques, manufacturers can determine the
inventory level more precisely and decrease its cost by using data obtained in the SC from
the suppliers, the retailers, the distributors, and the customers [81]. Blockchain offers safety
and security to all stakeholders in the SC network by offering a distributed or decentralized
digital system for recording transactions in a verifiable, tamperproof way. Büyüközkan
et al. (2021) [82] highlight the use of Blockchain technology in the digitalization of SC
networks because this technology allows for the secure transfer of data and assets across
large networks of users without the use of intermediaries.
Our final objective was to identify the latest trends in the DSC using the literature. A
time-series analysis of the keywords in published articles was used to draw conclusions
on the topic. It can be observed that blockchain, the health industry, digitalization, digital
transformation, digital technologies, and big data analytics are some future research topics
in the domain. A careful examination of the literature reveals that the majority of the
papers we have analyzed are conceptual papers proposing to deploy the above-mentioned
technologies in optimizing the performance of existing SCs. Based on the literature, it can
be concluded that data science has a predominant role in improving SC performance. Some
studies have stressed the use of these digital technologies in the health care industry. Future
studies might look into areas of digital manufacturing, vaccine, and medicinal distribution
networks by offering simple and efficient solutions to save costs. Agriculture and value
chains are also trending buzzwords revealed from the analysis. The study by [39] is guided
to achieve sustainable performance in agricultural SC using data-driven decision-making.
These studies help practitioners and researchers leverage the benefits of these emerging
technologies in modern SCs.

5. Conclusions and Limitations of the Study

The digitalization of SCs has been an important issue for more than two decades. This
study aims to identify the role of emerging technologies in transitioning traditional SCs to
DSCs. Analyzing the past six years of the literature revealed that SCs are gradually adopting
emerging technologies in their day-to-day operations. One important finding is that a gap
exists between the current readiness of the SCs and the new business environment. COVID-
19 has brought many obstacles, such as labor, material shortages, and fall in demand
and supply.
On the other hand, it helped firms adopt digital technologies and remote working
quickly to meet the global demands. Blockchain, ML, and IoT are believed to be future
trends in the DSCs, but the absence of case studies guiding the firms on adopting these
technologies is significantly less. DSC will enable any organization to grasp the untapped
potential of their existing capacity and achieve higher performance. People must be trained
with the right skills and tools to create more excellent value from DSCs. Based on gaps
identified in the literature, we keep the following questions open for future studies. For
instance, how do different national environments impact the adoption of those technolo-
gies? Or, what industrial sectors are better prepared to take advantage of Industry 4.0
technologies (readiness level)? How can Industry 4.0 technologies contribute to improved
integration and performance under new operating paradigms such as circular economy?
The following are some of the study’s limitations. For our analysis, we looked at
articles published between 2015 and 2021; however, there is a chance that we missed
some published studies before 2015 or after our article was submitted (2021). We only
Processes 2022, 10, 842 16 of 19

looked at academic articles published in English, and we only used the Scopus and Web
of Science databases to do so. Our study may be biased toward articles indexed in these
databases while ignoring articles indexed in other databases. Topic modeling output gives
the frequency of top keywords under each topic. The analysis and synthesis of topic
modeling output are based on the authors’ interpretation of the selected articles, which
might be subjected to bias and human errors. We have not conducted co-citation or network
analysis, which can help us understand how knowledge is shared between journals and
how topics are linked together.
Managerial implications
DSCs have been a buzzword, and it is embedded with many technologies to optimize
performance. This study helps managers identify the key technologies used in transforming
traditional SCs into DSCs. Recent studies have indicated that the firm investing in digital
transformation are gaining revenues as well as a reputation in the global markets [14]. DSCs
offer agility, flexibility, security, and openness, which helps achieve higher performance
in these highly competitive, complex global markets. With the help of digitalization and
blockchain, managers can track the feedback of all stakeholders and consumers in real-
time, which helps them to re-shape their business operations to achieve higher consumer
satisfaction by reducing the communication and construction gap. Investment in digital
technologies should be more focused on the internal integration process of the SCs once
they are ready; these DSCs help reduce risks. It aids in better forecasting in terms of costs,
market conditions, etc.
Scope for future research
Future studies can extend the timeframe to capture knowledge from comprehensive
papers. We considered studies published in a limited timeframe (2015–2021). Researchers
can also retrieve papers from other databases, such as Scopus and Web of Science, to
capture important literature from other sources. This study used text mining approaches
for the analysis; in future studies, researchers can compare text mining approaches to
literature analysis tools such as cite space, Knime, and others to determine which tool is
best for quick and efficient literature reviews. We limited our analysis to clustering, topic
modeling, and keyword analysis; however, future researchers can use visual text mining
and text summarization techniques to summarize research articles without reading them
quickly. We strongly advise future researchers to identify a successful journey of industry
or company in harnessing the benefits of digital technologies and present the findings as
a roadmap that will guide industry practitioners and academic researchers through the
various stages of making their organization take advantage of these emerging technologies.

Author Contributions: M.T.: Conceptualization, Methodology, Writing–review & editing. A.S.:

Formal analysis, Investigation, Methodology, Writing–review & editing. I.R.V.: Formal analysis,
Validation, Investigation. R.K.G.: Investigation, Validation, Writing–review & editing. All authors
have read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Informed Consent Statement: Not applicable.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Abedi, M.; Fathi, M.S.; Rawai, N.M. The impact of cloud computing technology to precast supply chain management. Int. J.
Constr. Eng. Manag. 2013, 2, 13–16.
2. Abeyratne, S.A.; Monfared, R.P. Blockchain ready manufacturing supply chain using distributed ledger. Int. J. Res. Eng. Technol.
2016, 5, 1–10. [CrossRef]
3. Addo-Tenkorang, R.; Helo, P.T. Big data applications in operations/supply-chain management: A literature review. Comput. Ind.
Eng. 2016, 101, 528–543. [CrossRef]
4. Agrawal, P.; Narain, R.; Ullah, I. Analysis of barriers in implementation of digital transformation of supply chain using interpretive
structural modelling approach. J. Model. Manag. 2019, 15, 297–317. [CrossRef]
Processes 2022, 10, 842 17 of 19

5. Akinade, O.O.; Oyedele, L.O. Integrating construction supply chains within a circular economy: An ANFIS-based waste analytics
system (A-WAS). J. Clean. Prod. 2019, 229, 863–873. [CrossRef]
6. Alqahtani, A.Y.; Gupta, S.M.; Nakashima, K. Warranty and maintenance analysis of sensor embedded products using internet of
things in industry 4.0. Int. J. Prod. Econ. 2019, 208, 483–499. [CrossRef]
7. Arunachalam, D.; Kumar, N.; Kawalek, J.P. Understanding big data analytics capabilities in supply chain management: Un-
ravelling the issues, challenges and implications for practice. Transp. Res. Part E Logist. Transp. Rev. 2018, 114, 416–436.
[CrossRef]
8. Awwad, M.; Kulkarni, P.; Bapna, R.; Marathe, A. Big data analytics in supply chain: A literature review. In Proceedings of
the International Conference on Industrial Engineering and Operations Management, Paris, France, 27–29 September 2018;
pp. 418–425.
9. Barnes, S.; Rutter, R.N.; La Paz, A.I.; Scornavacca, E. Empirical identification of skills gaps between chief information officer
supply and demand: A resource-based view using machine learning. Ind. Manag. Data Syst. 2021, 121, 1749–1766. [CrossRef]
10. Batista, L.; Bourlakis, M.; Smart, P.; Maull, R. In search of a circular supply chain archetype—a content-analysis-based literature
review. Prod. Plan. Control 2018, 29, 438–451. [CrossRef]
11. Batista, L.; Dora, M.; Garza-Reyes, J.A.; Kumar, V. Improving the sustainability of food supply chains through circular economy
practices—A qualitative mapping approach. Manag. Environ. Qual. Int. J. 2021, 32, 752–767. [CrossRef]
12. Bechtsis, D.; Tsolakis, N.; Vlachos, D.; Srai, J.S. Intelligent Autonomous Vehicles in digital supply chains: A framework for
integrating innovations towards sustainable value networks. J. Clean. Prod. 2018, 181, 60–71. [CrossRef]
13. Blei, D.M.; Ng, A.Y.; Jordan, M.I. Latent dirichlet allocation. J. Mach. Learn. Res. 2003, 3, 993–1022.
14. Bose, R. Advanced analytics: Opportunities and challenges. Ind. Manag. Data Syst. 2009, 109, 155–172. [CrossRef]
15. Brereton, P.; Kitchenham, B.; Budgen, D.; Turner, M.; Khalil, M. Lessons from applying the systematic literature review process
within the software engineering domain. J. Syst. Softw. 2006, 80, 571–583. [CrossRef]
16. Brinch, M. Understanding the value of big data in supply chain management and its business processes: Towards a conceptual
framework. Int. J. Oper. Prod. Manag. 2018, 38, 1589–1614. [CrossRef]
17. Büyüközkan, G.; Göçer, F. Digital Supply Chain: Literature review and a proposed framework for future research. Comput. Ind.
2018, 97, 157–177. [CrossRef]
18. Büyüközkan, G.; Tüfekçi, G.; Uztürk, D. Evaluating Blockchain requirements for effective digital supply chain management. Int.
J. Prod. Econ. 2021, 242, 108309. [CrossRef]
19. Chang, S.E.; Chen, Y. When Blockchain Meets Supply Chain: A Systematic Literature Review on Current Development and
Potential Applications. IEEE Access 2020, 8, 62478–62494. [CrossRef]
20. Chiarello, F.; Belingheri, P.; Bonaccorsi, A.; Fantoni, G.; Martini, A. Value creation in emerging technologies through text mining:
The case of blockchain. Technol. Anal. Strat. Manag. 2021, 33, 1404–1420. [CrossRef]
21. Chu, C.-Y.; Park, K.; Kremer, G.E. A global supply chain risk management framework: An application of text-mining to identify
region-specific supply chain risks. Adv. Eng. Inform. 2020, 45, 101053. [CrossRef]
22. Cole, R.; Stevenson, M.; Aitken, J. Blockchain technology: Implications for operations and supply chain management. Supply
Chain Manag. Int. J. 2019, 24, 469–483. [CrossRef]
23. Dallasega, P.; Rauch, E.; Linder, C. Industry 4.0 as an enabler of proximity for construction supply chains: A systematic literature
review. Comput. Ind. 2018, 99, 205–225. [CrossRef]
24. Gölcük, I. An interval type-2 fuzzy reasoning model for digital transformation project risk assessment. Expert Syst. Appl. 2020,
159, 113579. [CrossRef]
25. De Giovanni, P.; Cariola, A. Process innovation through industry 4.0 technologies, lean practices and green supply chains. Res.
Transp. Econ. 2020, 90, 100869. [CrossRef]
26. Dev, N.K.; Shankar, R.; Qaiser, F.H. Industry 4.0 and circular economy: Operational excellence for sustainable reverse supply
chain performance. Resour. Conserv. Recycl. 2020, 153, 104583. [CrossRef]
27. Ding, R.; Nallapati, R.; Xiang, B. Coherence-Aware Neural Topic Modeling. In Proceedings of the 2018 Conference on Empirical
Methods in Natural Language Processing, Brussels, Belgium, 2–4 November 2018; pp. 830–836. [CrossRef]
28. Dolgui, A.; Ivanov, D.; Sethi, S.; Sokolov, B. Control theory applications to operations systems, supply chain management and
Industry 4.0 networks. IFAC-PapersOnLine 2018, 51, 1536–1541. [CrossRef]
29. Eltsov, T.; Yutkin, M.; Patzek, T.W. Text Analysis Reveals Major Trends in Exploration Geophysics. Energies 2020, 13, 4550.
[CrossRef]
30. Frank, A.G.; Dalenogare, L.S.; Ayala, N.F. Industry 4.0 technologies: Implementation patterns in manufacturing companies. Int. J.
Prod. Econ. 2019, 210, 15–26. [CrossRef]
31. Gezdur, A.; Bhattacharjya, J. Digitization in the Oil and Gas Industry: Challenges and Opportunities for Supply Chain Partners.
In IFIP Advances in Information and Communication Technology; Springer: Zurich, Switzerland, 2017; Volume 506, pp. 97–103.
[CrossRef]
32. Ghadimi, P.; Wang, C.; Lim, M.K.; Heavey, C. Intelligent sustainable supplier selection using multi-agent technology: Theory and
application for Industry 4.0 supply chains. Comput. Ind. Eng. 2018, 127, 588–600. [CrossRef]
33. Gupta, H.; Kusi-Sarpong, S.; Rezaei, J. Barriers and overcoming strategies to supply chain sustainability innovation. Resour.
Conserv. Recycl. 2020, 161, 104819. [CrossRef]
Processes 2022, 10, 842 18 of 19

34. Hackius, N.; Petersen, M. Blockchain in logistics and supply chain: Trick or treat? In Proceedings of the Hamburg International
Conference of Logistics (HICL), Hamburg, Germant, 12–13 October 2017; pp. 3–18. [CrossRef]
35. HaddadPajouh, H.; Dehghantanha, A.; Parizi, R.M.; Aledhari, M.; Karimipour, H. A survey on internet of things security:
Requirements, challenges, and solutions. Internet Things 2021, 14, 100129. [CrossRef]
36. Hald, K.S.; Kinra, A. How the blockchain enables and constrains supply chain performance. Int. J. Phys. Distrib. Logist. Manag.
2019, 49, 376–397. [CrossRef]
37. Kamble, S.S.; Gunasekaran, A.; Parekh, H.; Joshi, S. Modeling the internet of things adoption barriers in food retail supply chains.
J. Retail. Consum. Serv. 2019, 48, 154–168. [CrossRef]
38. Kamble, S.S.; Gunasekaran, A.; Sharma, R. Analysis of the driving and dependence power of barriers to adopt industry 4.0 in
Indian manufacturing industry. Comput. Ind. 2018, 101, 107–119. [CrossRef]
39. Kamble, S.S.; Gunasekaran, A.; Gawankar, S.A. Achieving sustainable performance in a data-driven agriculture supply chain: A
review for research and applications. Int. J. Prod. Econ. 2019, 219, 179–194. [CrossRef]
40. Kannan, D.; Khodaverdi, R.; Olfat, L.; Jafarian, A.; Diabat, A. Integrated fuzzy multi criteria decision making method and
multi-objective programming approach for supplier selection and order allocation in a green supply chain. J. Clean. Prod. 2013,
47, 355–367. [CrossRef]
41. Karami, A.; Lundy, M.; Webb, F.; Dwivedi, Y.K. Twitter and Research: A Systematic Literature Review through Text Mining. IEEE
Access 2020, 8, 67698–67717. [CrossRef]
42. Keshavarz-Ghorabaee, M.; Amiri, M.; Hashemi-Tabatabaei, M.; Ghahremanloo, M. Prioritizing the Barriers and Challenges of
Big Data Analytics in Logistics and Supply Chain Management Using MCDM Method. In Big Data Analytics in Supply Chain
Management: Theory and Applications; CRC Press: Boca Raton, FL, USA, 2020; pp. 29–43. [CrossRef]
43. Kittipanya-Ngam, P.; Tan, K.H. A framework for food supply chain digitalization: Lessons from Thailand. Prod. Plan. Control
2019, 31, 158–172. [CrossRef]
44. Korpela, K.; Hallikas, J.; Dahlberg, T. Digital supply chain transformation toward blockchain integration. In Proceedings of the
50th Hawaii International Conference on System Sciences, Waikoloa, Hawaii, 4–7 January 2017.
45. Leminen, S.; Rajahonka, M.; Wendelin, R.; Westerlund, M. Industrial internet of things business models in the machine-to-machine
context. Ind. Mark. Manag. 2019, 84, 298–311. [CrossRef]
46. Luthra, S.; Mangla, S.K. Evaluating challenges to Industry 4.0 initiatives for supply chain sustainability in emerging economies.
Process Saf. Environ. Prot. 2018, 117, 168–179. [CrossRef]
47. Ly, P.T.M.; Lai, W.-H.; Hsu, C.-W.; Shih, F.-Y. Fuzzy AHP analysis of Internet of Things (IoT) in enterprises. Technol. Forecast. Soc.
Chang. 2018, 136, 1–13. [CrossRef]
48. Lyu, J.C.; Luli, G.K. Understanding the Public Discussion about the Centers for Disease Control and Prevention During the
COVID-19 Pandemic Using Twitter Data: Text Mining Analysis Study. J. Med. Internet Res. 2021, 23, e25108. [CrossRef] [PubMed]
49. Majeed, M.A.A.; Rupasinghe, T.D. Internet of things (IoT) embedded future supply chains for industry 4.0: An assessment from
an ERP-based fashion apparel and footwear industry. Int. J. Supply Chain. Manag. 2017, 6, 25–40.
50. Manavalan, E.; Jayakrishna, K. A review of Internet of Things (IoT) embedded sustainable supply chain for industry 4.0
requirements. Comput. Ind. Eng. 2018, 127, 925–953. [CrossRef]
51. Matt, C.; Hess, T.; Benlian, A. Digital Transformation Strategies. Bus. Inf. Syst. Eng. 2015, 57, 339–343. [CrossRef]
52. Mergel, I.; Edelmann, N.; Haug, N. Defining digital transformation: Results from expert interviews. Gov. Inf. Q. 2019, 36, 101385.
[CrossRef]
53. Müller, J.M.; Voigt, K.-I. The Impact of Industry 4.0 on Supply Chains in Engineer-to-Order Industries—An Exploratory Case
Study. IFAC-PapersOnLine 2018, 51, 122–127. [CrossRef]
54. Nagar, D.; Raghav, S.; Bhardwaj, A.; Kumar, R.; Singh, P.L.; Sindhwani, R. Machine learning: Best way to sustain the supply chain
in the era of industry 4.0. Mater. Today Proc. 2021, 47, 3676–3682. [CrossRef]
55. Nasiri, M.; Ukko, J.; Saunila, M.; Rantala, T. Managing the digital supply chain: The role of smart technologies. Technovation 2020,
96–97, 102121. [CrossRef]
56. Van Nguyen, T.; Zhou, L.; Spiegler, V.; Ieromonachou, P.; Lin, Y. Big data analytics in supply chain management: A state-of-the-art
literature review. Comput. Oper. Res. 2018, 98, 254–264. [CrossRef]
57. Novais, L.; Maqueira, J.M.; Ortiz-Bas, A. A systematic literature review of cloud computing use in supply chain integration.
Comput. Ind. Eng. 2019, 129, 296–314. [CrossRef]
58. O’Mara-Eves, A.; Thomas, J.; McNaught, J.; Miwa, M.; Ananiadou, S. Using text mining for study identification in systematic
reviews: A systematic review of current approaches. Syst. Rev. 2015, 4, 1–22.
59. Park, C.; Kim, Y.; Jeong, M. Influencing factors on risk perception of IoT-based home energy management services. Telemat.
Inform. 2018, 35, 2355–2365. [CrossRef]
60. Pflaum, A.; Prockl, G.; Bodendorf, F.; Chen, H. Introduction to the Minitrack on The Digital Supply Chain of the Future:
Technologies, Applications and Business Models. In Proceedings of the 51st Hawaii International Conference on System Sciences,
Waikoloa, Hawaii, 3–6 January 2018; pp. 4179–4181. [CrossRef]
61. Queiroz, M.M.; Pereira, S.C.F.; Telles, R.; Machado, M.C. Industry 4.0 and digital supply chain capabilities. Benchmark. Int. J. 2019,
28, 1761–1782. [CrossRef]
Processes 2022, 10, 842 19 of 19

62. Ramirez-Peña, M.; Sotano, A.J.S.; Pérez-Fernandez, V.; Abad, F.J.; Batista, M. Achieving a sustainable shipbuilding supply chain
under I4.0 perspective. J. Clean. Prod. 2019, 244, 118789. [CrossRef]
63. da Silva, E.H.D.R.; Shinohara, A.C.; de Lima, E.P.; Angelis, J.; Machado, C. Reviewing Digital Manufacturing concept in the
Industry 4.0 paradigm. Procedia CIRP 2019, 81, 240–245. [CrossRef]
64. Saberi, S.; Kouhizadeh, M.; Sarkis, J. Blockchains and the Supply Chain: Findings from a Broad Study of Practitioners. IEEE Eng.
Manag. Rev. 2019, 47, 95–103. [CrossRef]
65. Seyedghorban, Z.; Tahernejad, H.; Meriton, R.; Graham, G. Supply chain digitalization: Past, present and future. Prod. Plan.
Control 2019, 31, 96–114. [CrossRef]
66. Jain, A.D.S.; Mehta, I.; Mitra, J.; Agrawal, S. Application of Big Data in Supply Chain Management. Mater. Today Proc. 2017, 4,
1106–1115. [CrossRef]
67. Sohrabi, B.; Vanani, I.R.; Gooyavar, A.; Naderi, N. Predicting the Readmission of Heart Failure Patients through Data Analytics. J.
Inf. Knowl. Manag. 2019, 18. [CrossRef]
68. Tao, D.; Yang, P.; Feng, H. Utilization of text mining as a big data analysis tool for food science and nutrition. Compr. Rev. Food Sci.
Food Saf. 2020, 19, 875–894. [CrossRef] [PubMed]
69. Taghikhah, F.; Voinov, A.; Shukla, N. Extending the supply chain to address sustainability. J. Clean. Prod. 2019, 229, 652–666.
[CrossRef]
70. Tavana, M.; Shaabani, A.; Santos-Arteaga, F.J.; Vanani, I.R. A Review of Uncertain Decision-Making Methods in Energy
Management Using Text Mining and Data Analytics. Energies 2020, 13, 3947. [CrossRef]
71. Tjahjono, B.; Esplugues, C.; Ares, E.; Pelaez, G. What does Industry 4.0 mean to Supply Chain? Procedia Manuf. 2017, 13, 1175–1182.
[CrossRef]
72. Tsao, Y.-C. Managing default risk under trade credit: Who should implement Big-Data analytics in supply chains? Transp. Res.
Part E Logist. Transp. Rev. 2017, 106, 276–293. [CrossRef]
73. van der Maaten, L.; Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 2008, 9, 2579–2605.
74. Vemula, R.; Zsifkovits, H. Cloud Computing im Supply Chain Management. BHM Berg-Und Hüttenmännische Mon. 2016, 161,
229–232. [CrossRef]
75. Wang, Y.; Han, J.H.; Beynon-Davies, P. Understanding blockchain technology for future supply chains: A systematic literature
review and research agenda. Supply Chain Manag. 2019, 24, 62–84. [CrossRef]
76. Wang, Z.; Zhong, Y. What were residents’ petitions in Beijing- based on text mining. J. Urban Manag. 2019, 9, 228–237. [CrossRef]
77. Hannah, W.; Daniel, S.; Saskia, S. A literature review on machine learning in supply chain management. In Proceedings of
the Hamburg International Conference of Logistics (HICL), Hamburg, Germany, 26–27 September 2019; epubli GmbH: Berlin,
Germany, 2019; Volume 27, pp. 413–441, ISBN 978-3-7502-4947-9. [CrossRef]
78. Yadav, G.; Luthra, S.; Jakhar, S.K.; Mangla, S.K.; Rai, D.P. A framework to overcome sustainable supply chain challenges through
solution measures of industry 4.0 and circular economy: An automotive case. J. Clean. Prod. 2020, 254, 120112. [CrossRef]
79. Yadav, S.; Singh, S.P. Blockchain critical success factors for sustainable supply chain. Resour. Conserv. Recycl. 2020, 152, 104505.
[CrossRef]
80. Zhan, Y.; Tan, K.H. An analytic infrastructure for harvesting big data to enhance supply chain performance. Eur. J. Oper. Res.
2018, 281, 559–574. [CrossRef]
81. Zhu, Y.; Kim, M.C.; Chen, C. An investigation of the intellectual structure of opinion mining research. Inf. Res. Int. Electron. J.
2017, 22, n1.
82. Zimmermann, M.; Rosca, E.; Antons, O.; Bendul, J.C. Supply chain risks in times of Industry 4.0: Insights from German cases.
IFAC-PapersOnLine 2019, 52, 1755–1760. [CrossRef]

View publication stats