Scribd
Upload
43 views3 pages

AAA Intro Maria Hanif

The document discusses semantic analysis of text data using machine learning techniques. It introduces the topic of semantic analysis and discusses how both supervised and unsupervised learning algorithms can be used for predictive and descriptive text mining respectively. The document proposes a hybrid deep learning technique for semantic analysis that improves accuracy and performance over existing methods. It also provides motivations and outlines the research contributions on developing techniques to help computers better understand human language.

Uploaded by

Sinan Ahmed
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
43 views3 pages

AAA Intro Maria Hanif

The document discusses semantic analysis of text data using machine learning techniques. It introduces the topic of semantic analysis and discusses how both supervised and unsupervised learning algorithms can be used for predictive and descriptive text mining respectively. The document proposes a hybrid deep learning technique for semantic analysis that improves accuracy and performance over existing methods. It also provides motivations and outlines the research contributions on developing techniques to help computers better understand human language.

Uploaded by

Sinan Ahmed
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Course Title Advance Analysis of Algorithm

Assignment No: 2

Programme MSCS Fall 2020

Student’s Name Maria Hanif

Roll No. 1078

Submitted to Dr. Farhan Hassan

Submission Date 03-11-2020


Semantic Analysis of text data using Machine Learning Techniques

1. Introduction

In the modern times of technology, the world is all about the data and computers. Data is the basic unit of
our lives. We produce and consume data simultaneously [1]. This data is present in the form of text and
graphics in large databases. These databases contains only 20% structured text data and rest of 80% data
is semi-structured or unstructured text data [2]. For such continuously increasing huge amount of text
data, we need efficient techniques to extract useful information from this text data. In web based search
engines, search engine gives result of our searches on the basis of keywords which produce poor results
and irrelevant web pages while semantic analysis work on theme of our searches which produce good
results [3]. In E-commerce applications, companies need data analysis of customer purchases and
transactions which help them in making decisions using business strategies [4].

Natural Language Processing is the processing of information contained in natural language text. The
purpose of NLP is making machines able to analyze, understand and generate human language just like
humans do [5]. In third phase of NLP, Semantic analysis (SA) of text is performed. SA concerns with the
literal meaning of words, phrases and sentences [6].

Semantic analysis of text is done through text mining which is sub category of data mining. Data mining
deals with the discovery of patterns of interest from large amount of data. Text mining is further classified
into predictive text mining and descriptive text mining. Predictive text mining uses supervised learning
algorithms and deep learning techniques. These algorithms are trained on labeled examples as inputs
where desired output is known. K-nearest neighbor (KNN), Naïve Bayes, Decision Tree and Support
Vector Machine (SVM) are supervised learning classifiers used for SA [7]. Deep learning uses
Convolutional Neural Network for text analysis which further classified as Dynamic CNN and Recurrent
CNN [8]. Descriptive text mining uses unsupervised learning algorithms. These algorithms operate on
unlabeled examples as inputs where desired output is unknown. Clustering, Word2Vec and Doc2Vec are
unsupervised techniques used for Semantic Analysis of text [9]. Word2Vec and Doc2Vec are the word
embedding methods that are used to represent the vector representation of text [10].

1.1. Motivation

In last few decades, data in human language is continuously increasing in very large amount with high
speed. So it is highly needed to develop computer programs to make computers able to understand and
analyze human language as humans do. There are several methods and techniques that used for semantic
analysis of text data which gives accurate results as humans and even surpass humans.

1.2. Research Contributions

 A hybrid technique of deep learning is proposed for semantic analysis of text data.
 Results are improved in terms of accuracy and performance.
 Performance is improved in terms of response time and large datasets.
 Provides the comparative analysis of state-of-Art supervised machine learning techniques for
Semantic Analysis.
 Deep learning techniques are compared.
Figure 1. Block diagram of Techniques of Semantic Analysis

References

[1] Adhikar, S. (2020, March). NLP based Machine Learning Approaches for Text Summarization.
In 2020 Fourth International Conference on Computing Methodologies and Communication
(ICCMC) (pp. 535-538). IEEE.
[2] Zhou, S., Xu, X., Liu, Y., Chang, R., & Xiao, Y. (2019). Text similarity measurement of semantic
cognition based on word vector distance decentralization with clustering analysis. IEEE Access, 7,
107247-107258.
[3] Bayrakdar, S., Yucedag, I., Simsek, M., & Dogru, I. A. (2020). Semantic analysis on social
networks: A survey. International Journal of Communication Systems, e4424.
[4] Trappey, C. V., Trappey, A. J., & Liu, B. H. (2020). Identify trademark legal case precedents-Using
machine learning to enable semantic analysis of judgments. World Patent Information, 62, 101980.
[5] Lee, R. S. (2020). Natural language processing. In Artificial Intelligence in Daily Life (pp. 157-192).
Springer, Singapore.
[6] Salloum, S. A., Khan, R., & Shaalan, K. (2020, April). A survey of semantic analysis approaches.
In Joint European-US Workshop on Applications of Invariance in Computer Vision (pp. 61-70).
Springer, Cham.
[7] Alhawarat, M., & Aseeri, A. O. (2020). A Superior Arabic Text Categorization Deep Model
(SATCDM). IEEE Access, 8, 24653-24661.
[8] Chen, Y., Lv, Y., Wang, X., Li, L., & Wang, F. Y. (2018). Detecting traffic information from social
media texts with deep learning approaches. IEEE Transactions on Intelligent Transportation
Systems, 20(8), 3049-3058.
[9] Fang, Y., Huang, C., Su, Y., & Qiu, Y. (2020). Detecting malicious JavaScript code based on
semantic analysis. Computers & Security, 93, 101764.
[10] Ren, J., Li, T., Gen, S., Liu, Q., He, Y., Wang, Z., & Zhou, D. (2020). An Automatic Mapping
Method of Intelligent Recorder Configuration Datasets Based on Chinese Semantic Deep
Learning. IEEE Access, 8, 168186-168195.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy