Title page:

Automated depression detection and personalized support: A multifaceted

approach by using CNN compared to Bi-LSTM

G.Moni Samhitha Reddy, S.Tamilselvan

G.Moni Samhitha Reddy

Research Scholar,
Department of Cyber Security,
Saveetha School of Engineering,
Saveetha Institute of Medical and Technical Sciences,
Saveetha University, Chennai, Tamil Nadu. India. Pincode: 602105.
gottigundalasamhitha1170.sse@saveetha.com
S.Tamilselvan
Project Guide, Corresponding Author,
Department of Electronics And Communication Engineering,
Saveetha School of Engineering,
Saveetha Institute of Medical and Technical Sciences,
Saveetha University, Chennai, Tamil Nadu. India. Pincode: 602105.
tamilselvans.sse@saveetha.com

Keywords: Convolution neural networks, Bi- Long short-term memory, Depression, Mental
health, Chatbot, Natural Language.

ABSTRACT:

Aim: In an era where mental health has garnered increasing attention, the development of
innovative and automated solutions to detect and address depression has become paramount.
This project, titled " Automated depression detection and personalized support: A multifaceted
approach by using CNN compared to Bi-LSTM," embarks on a comprehensive journey to
employ state-of-the-art deep learning architectures, namely Convolutional Neural Networks
(CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks, in a multifaceted
approach to enhance mental health support. The primary objective is to tackle the multifaceted
nature of depression detection and support by harnessing the strengths of CNNs and Bi-LSTMs.
Materials and Methods: While CNNs excel in feature extraction and pattern recognition, Bi-
LSTMs are specialized for capturing contextual and sequential information. By integrating these
two architectures, our project aims to create a robust system capable of not only accurately
detecting signs of depression within text data but also offering personalized support that adapts
to an individual's unique emotional needs. This multifaceted approach is rooted in the
understanding that depression is a complex and nuanced condition, often requiring a multifaceted
solution. Results: By employing CNNs and Bi-LSTMs in tandem, we strive to provide an
integrated platform that can compassionately and effectively assist individuals in their mental
health journey, while also pushing the boundaries of AI's role in mental health care. This
research marks a significant step towards the development of a holistic mental health support
system, aligning with the evolving landscape of AI-driven emotional well-being.

Keywords: Convolution neural networks, Bi- Long short-term memory, Depression, Mental
Health, Natural language, Depression.

INTRODUCTION:

Mental health, once a silent and often stigmatized concern, has risen to the forefront of global
public health discussions. The recognition of the profound impact of mental well-being on
overall health and quality of life has ignited a quest for innovative solutions that can detect and
address mental health(Kulkarni 2018) challenges effectively and compassionately. Within this
transformative landscape, our project emerges as a beacon of hope, titled "Automated
Depression Detection(Alfadhli 2022) and Personalized Support: A Multifaceted
Approach(United States. Depression Guideline Panel 1993)." We embark on a multifaceted
journey that harnesses cutting-edge deep learning architectures, Convolutional Neural Networks
(CNN), and Bidirectional Long Short-Term Memory (Bi-LSTM) networks, to revolutionize
mental health support through a holistic and automated approach. The imperative for effective
mental health support cannot be overstated. Depression, a leading cause of disability worldwide,
often remains underdiagnosed and undertreated due to various barriers, including stigma, limited
access to professional care, and the subtlety of emotional struggles(DIANE Publishing Company
1994). This pressing concern necessitates innovative, empathetic, and accessible solutions that
can transcend these barriers.

As the World Health Organization projects depression(Wang et al. 2024) to be the leading cause
of disease burden by 2030, the need for multifaceted and personalized support systems becomes
all the more evident(Ou et al. 2024). Central to our project's multifaceted approach are two
remarkable deep learning architectures: CNN and Bi-LSTM. The CNN model, renowned for its
prowess in feature extraction and pattern recognition(Barker et al. 2024), promises to uncover
the subtlest emotional cues within text data. In contrast, the Bi-LSTM model, as a variant of the
Long Short-Term Memory (LSTM) network, excels in capturing contextual and sequential
information, offering a nuanced understanding of emotional well-being. The integration of these
two architectures underscores our commitment to addressing the multifaceted nature of
depression detection and personalized support(Crestani, Losada, and Parapar 2022). By
leveraging the strengths of CNNs and Bi-LSTMs, we aim to create a comprehensive platform
capable of accurately identifying signs of depression and delivering personalized assistance that
adapts to an individual's unique emotional needs.

This multifaceted approach, rooted in the understanding that depression is a multifaceted

condition, not only showcases the potential of AI in mental health(Tumurbaatar et al. 2023) care
but also underscores the urgency of providing holistic support to individuals in their mental
health journey. It represents a significant stride towards a future where AI-driven systems play a
pivotal role(Forman-Hoffman et al. 2024) in enhancing emotional well-being and alleviating the
burden of mental health challenges.

MATERIALS AND METHODS:

This study was carried out in the Machine Learning Lab at Saveetha School of Engineering
located in Chennai. The success of any machine learning project hinges on the quality and
quantity of the data used for training and testing the model. In this study, data was collected from
diverse sources, including online forums, social media platforms, and anonymized electronic
health records (EHRs). This dataset was carefully curated to include a wide range of text-based
content that reflects the linguistic diversity of individuals expressing their emotions, thoughts,
and feelings, particularly those related to depression. Before implementing machine learning
models, it is crucial to preprocess the data to ensure it is in a suitable format. Data preprocessing
involved tasks such as tokenization, stop word removal, and lemmatization to standardize text
inputs. Additionally, the data underwent sentiment analysis to categorize expressions into
positive, negative, or neutral sentiments. Textual data were labeled based on whether they
indicated signs of depression, creating the ground truth for model training and evaluation.

The proposed work is designed and implemented with the help of Python OpenCV software. The
platform to assess deep learning was Windows 10 OS. The hardware configuration was an Intel
core i7 processor with a RAM size of 4GB. The system sort used was 64-bit. For the
implementation of code, the python programming language was used. As for code execution, the
dataset is worked behind to perform an output process for accuracy. For the research project on
detecting and addressing depression(Augustus, Bold, and Williams 2019) through chatbot
insights, a dataset was sourced from Kaggle, a prominent platform for datasets and machine
learning resources. The dataset, structured in JSON format, was curated to facilitate the
comparison of Convolutional Neural Network (CNN) and Bi-LSTM models. This dataset
contains a diverse array of user interactions, capturing textual(Fernando 2014) and emotional
nuances relevant to depression detection. Attributes include text messages, sentiment labels, and
contextual information crucial for training and evaluating the chatbot's performance. To execute
the machine learning models seamlessly, the research was conducted in Google Colab, a cloud-
based platform that allows for collaborative coding and execution of Python scripts. This
integration with Google Colab not only facilitated the efficient processing of the dataset but also
streamlined the implementation and comparison of the CNN and Bi-LSTM models, contributing
to the research's computational efficiency and reproducibility.

Convolutional Neural Network (CNN):

Description:
The Convolutional Neural Network (CNN)(Ma and Li 2023) is a deep learning architecture
primarily designed for image processing tasks. In the context of text analysis, it can be adapted
for feature extraction by treating the text as an image, with one dimension representing word
position and the other representing word embeddings or vectors. The embedding layer converts
words into dense vectors, which serve as the input for the CNN model. Max-pooling or average-
pooling layers follow the convolutional layers, reducing the dimensionality of the extracted
features while retaining important information. After pooling, fully connected layers are used for
classification, making predictions based on the learned features.

Algorithm:

1. Input JSON dataset for a chatbot with depression labels.

2. Let ‘f’ be the feature 3D matrix.

3. Vectorize the data in the ‘f’ dataset.

4. Split the feature set and labels.

5. Apply Convolutional Neural Networks algorithm.

6. Train the model using the training set.

7. Evaluate the model using the training set.

8. Return the accuracy and loss.

Bidirectional Long Short-Term Memory (Bi-LSTM):

Description:

The Bidirectional Long Short-Term Memory (Bi-LSTM)(Zeberga et al. 2022) network

represents an advanced variant of the traditional Long Short-Term Memory (LSTM) architecture.
Bi-LSTMs are specifically designed to capture intricate dependencies and contextual information
within sequential data, making them well-suited for natural language processing tasks, including
the analysis of textual content for signs of depression. Similar to the previously discussed
models, the Bi-LSTM model commences with an embedding layer. This layer transforms
individual words into continuous vectors, thereby enabling the network to work with a numerical
representation of text data.

Algorithm:

1. Input JSON dataset for a chatbot with depression labels.

2. Let ‘f’ be the feature 3D matrix.

3. Vectorize the data in the ‘f’ dataset.

4. Split the feature set and labels.

5. Apply Bidirectional Long Short-Term Memory algorithm.

6. Train the model using the training set.

7. Evaluate the model using the training set.

8. Return the accuracy and loss.

Statistical Analysis:

Statistical analysis is a vital aspect of the " Automated depression detection and personalized
support: A multifaceted approach by using CNN compared to Bi-LSTM " project, as it serves to
evaluate the performance and effectiveness of the employed machine learning models—
Convolutional Neural Network (CNN) and Bi-LSTM. The first step in the statistical analysis is
assessing the performance of the CNN and Bi-LSTM models. Data serves as the independent
variable, while accuracy is the dependent variable. The analysis includes conducting an
Independent T-test to calculate the accuracy of both methods. Statistical analysis is a vital aspect.

RESULTS:

The results of our study, which examined the performance of the Convolutional Neural Network
(CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) models in the context of
depression detection, provide valuable insights into the capabilities of these two deep learning
architectures. The CNN model demonstrated an impressive accuracy rate of 95.28%, while the
Bi-LSTM model achieved an accuracy rate of 86.22%. These findings reveal a clear distinction
in the performance of these models, shedding light on their potential utility in automated mental
health support systems. Table 1 presents a comprehensive overview of the performance metrics
for both the CNN and Bi-LSTM models. The discrepancy in accuracy is evident, with the CNN
model significantly outperforming the Bi-LSTM model. Moreover, the CNN model maintains a
robust balance of precision, recall, and F1-score, while the Bi-LSTM model also exhibits
respectable metrics, albeit slightly lower than the CNN model. The bar chart prominently
illustrates the substantial difference in accuracy, with the CNN model emerging as the more
accurate model. This visual representation underscores the critical role of model selection in the
task of depression detection and highlights the potential of Convolutional Neural Networks in
this context.
DISCUSSION:

The results of our comparative analysis between the Convolutional Neural Network (CNN) and
Bidirectional Long Short-Term Memory (Bi-LSTM) models in depression detection provide an
opportunity for nuanced discussion regarding the implications and underlying factors
contributing to the disparity in performance.

The notable contrast in accuracy rates between the CNN and Bi-LSTM models underscores the
significance of model architecture in natural language processing tasks. CNN celebrated for its
feature extraction capabilities, excelled in capturing nuanced emotional(Crestani, Losada, and
Parapar 2022) cues within text data. In contrast, the Bi-LSTM, designed for contextual analysis,
exhibited a commendable but somewhat lower accuracy. This discrepancy emphasizes the
necessity of understanding the strengths and limitations of each model architecture.
Depression(Kerz et al. 2023) detection is inherently challenging, as it demands the interpretation
of both the sequential nature and the nuanced context of emotional expression(Jain et al. 2022) in
text data. While the Bi-LSTM model was expected to excel in contextual analysis due to its
bidirectional processing, CNN showcased remarkable abilities in feature extraction. The results
suggest that CNN's proficiency in identifying key textual patterns is a significant advantage in
depression detection. Mental health assessment through textual data presents unique challenges
due to the subtle and contextual nature of emotional expression. The project underscores the
importance of selecting model architectures that can effectively capture both emotional
nuances(Sa-Nguannarm, Elbasani, and Kim 2023) and sequential dependencies. Furthermore, it
raises the question of whether a hybrid approach that combines the strengths of CNNs and Bi-
LSTMs could provide a more holistic solution for text-based depression detection and
personalized support.

Our findings have broad implications for the development of AI-driven mental health support
systems. Accurate and sensitive depression detection is a critical aspect of these systems, and the
choice of the model architecture plays a pivotal role. The results emphasize that the CNN model,
with its higher accuracy, is better suited for this specific task. However, the project does not
discount the utility of Bi-LSTMs in other aspects of mental health support and related natural
language processing tasks. The research presented here serves as a stepping stone for further
exploration of advanced deep learning architectures and hybrid models that can provide
comprehensive and multifaceted solutions for mental health applications. The quest to automate
depression detection and provide personalized support remains an evolving and dynamic field,
guided by the continuous advancements in AI technologies and informed by studies such as this
one.

CONCLUSION:

In summary, our findings suggest that the CNN model excels in the task of depression detection,
attaining an impressive accuracy rate of 95.28%. In contrast, the Bi-LSTM model, while still
showing promise, achieves an accuracy rate of 86.22%. These results emphasize the pivotal
significance of model architecture in the accuracy and efficacy of automated mental health
support systems. While both models offer potential, CNN's superior accuracy makes it a
compelling choice for applications in the multifaceted approach to mental health support.

DECLARATIONS

Conflicts of Interests

No conflicts of interest in this manuscript.

Authors Contribution

Author BV was involved in data collection, data analysis, and manuscript writing. Author PJ was
involved in the conceptualization, data validation, and critical reviews of manuscripts.

Acknowledgment

The authors would like to express their gratitude towards Saveetha School of Engineering,
Saveetha Institute of Medical and Technical Sciences (formerly known as Saveetha University)
for providing the necessary infrastructure to carry out this work successfully.

Funding

Thanks to the following organizations for providing financial support that enabled us to complete
the study.

1. Infysec Solution, Chennai

2. Saveetha University

3. Saveetha Institute of Medical and Technical Sciences.

4. Saveetha School of Engineering.

REFERENCES:

Alfadhli, Norah. 2022. Depression Detection in Social Media Via Differential Text
Embedding.
Augustus, Jo, Justine Bold, and Briony Williams. 2019. An Introduction to Mental Health.
SAGE.

Barker, Tamsin Greene, Aoife O’Higgins, Peter Fonagy, and Frances Gardner. 2024. “A
Systematic Review and Meta-Analysis of the Effectiveness of Co-Designed, in-person,
Mental Health Interventions for Reducing Anxiety and Depression Symptoms.” Journal of
Affective Disorders, January. https://doi.org/10.1016/j.jad.2023.12.080.

Crestani, Fabio, David E. Losada, and Javier Parapar. 2022. Early Detection of Mental
Health Disorders by Social Media Monitoring: The First Five Years of the eRisk Project.
Springer Nature.

DIANE Publishing Company. 1994. Depression in Primary Care: Detection and Diagnosis.
DIANE Publishing.

Fernando, S. 2014. Mental Health Worldwide: Culture, Globalization and Development.

Springer.

Forman-Hoffman, Valerie L., Samuel Sihvonen, Joseph Wielgosz, Eric Kuhn, Benjamin W.
Nelson, Nicholas C. Peiper, and Christine E. Gould. 2024. “Therapist-Supported Digital
Mental Health Intervention for Depressive Symptoms: A Randomized Clinical Trial.”
Journal of Affective Disorders, January. https://doi.org/10.1016/j.jad.2024.01.057.

Jain, Shikha, Kavita Pandey, Princi Jain, and Kah Phooi Seng. 2022. Artificial Intelligence,
Machine Learning, and Mental Health in Pandemics: A Computational Approach.
Academic Press.

Kerz, Elma, Sourabh Zanwar, Yu Qiao, and Daniel Wiechmann. 2023. “Toward
Explainable AI (XAI) for Mental Health Detection Based on Language Behavior.” Frontiers
in Psychiatry / Frontiers Research Foundation 14 (December): 1219479.

Kulkarni, Akshay Bhavani Kumar. 2018. Early Detection of Depression.

Ma, Fake, and Huwei Li. 2023. “Online Painting Image Clustering for the Mental Health of
College Art Students Based on Improved CNN and SMOTE.” PeerJ. Computer Science 9
(July): e1462.

Ou, Wenwen, Chuman Xiao, Qiangli Dong, Yafei Chen, Chunxi Ke, Bangshan Liu, Jin Liu,
Yumeng Ju, and Yan Zhang. 2024. “Risk Factors Associated with Depression and Anxiety
among the Chinese General Population after Retracting the Dynamic Zero-COVID Policy:
A Network Analysis.” Journal of Affective Disorders 349 (January): 77–85.

Sa-Nguannarm, Phataratah, Ermal Elbasani, and Jeong-Dong Kim. 2023. “Human Activity
Recognition for Analyzing Stress Behavior Based on Bi-LSTM.” Technology and Health
Care: Official Journal of the European Society for Engineering and Medicine 31 (5): 1997–
 2007.

Tumurbaatar, Enkhnaran, Enkhjin Bat-Erdene, Tsolmontuya Amartuvshin, Myagmartseren

Dashtseren, Gantsetseg Tumur-Ochir, Damdindorj Boldbaatar, Tsolmon Jadamba, Tetsuya
Hiramoto, Takakazu Oka, and Battuvshin Lkhagvasuren. 2023. “Heart Rate Variability and
Tension-Type Headache: A Population-Based Cross-Sectional Study.” IBRO Neuroscience
Reports 15 (December): 194–202.

United States. Depression Guideline Panel. 1993. Depression in Primary Care: Detection
and Diagnosis.

Wang, Wenjing, Ye Li, Liyan Wang, Xiao Chen, Tian Lan, Changmin Wang, Shihong
Chen, and Shuyan Yu. 2024. “FBXL20 Promotes Synaptic Impairment in Depression
Disorder via Degrading Vesicle-Associated Proteins.” Journal of Affective Disorders,
January. https://doi.org/10.1016/j.jad.2024.01.055.

Zeberga, Kamil, Muhammad Attique, Babar Shah, Farman Ali, Yalew Zelalem Jembre, and
Tae-Sun Chung. 2022. “A Novel Text Mining Approach for Mental Health Prediction
Using Bi-LSTM and BERT Model.” Computational Intelligence and Neuroscience 2022
(March): 7893775.

TABLES AND FIGURES:

Table – 1: Comparative performance analysis of accuracy and loss of two models CNN and Bi-
LSTM.

ITERATION ACCURACY (%) LOSS

(LAST 5)

CNN Bi-LSTM CNN Bi-LSTM

90 96.8 88.7 0.005 0.38

 89 95.6 88.2 0.008 0.40

88 95.2 86.5 0.013 0.45

87 95.0 84.2 0.014 0.47

86 93.8 83.5 0.019 0.49

Table 2: Comparison of CNN and Bi-LSTM

Neural Network Model Accuracy (%)

CNN 95.28

Bi-LSTM 86.22

Table 3: Comparison of Mean, Standard deviation, and Standard Error Mean of Convolutional
Neural Networks and Bi-LSTM.
Table 4: Comparison of Independent Sample test of Convolutional Neural Networks and Bi-
LSTM.