A Deep Learning Framework with a Hybrid Model for Automatic Depression Detection in Social Media Posts
Keywords:
Depression Detection, Machine Learning, Deep Learning, Artificial Intelligence, Natural Language ProcessingAbstract
In the contemporary era, there have been increasing incidents of mental health issues due to various reasons, including lifestyle changes. Social media's widespread use has allowed people to openly express their emotions, giving researchers access to much data. In this context, it is possible to mine social media conversations and detect the probability of depression based on the expressions in the underlying text. There are many heuristic approaches for depression detection. With the development of artificial intelligence (AI), learning-based techniques may fare better in identifying depression. However, since there isn't a single solution that works for everyone, deep learning models must be enhanced to perform better in the diagnosis of depression. This study introduced a hybrid deep learning framework that seamlessly integrates bi-directional long short-term memory (biLSTM) and convolutional neural network (CNN) models to extract features and temporal connections from data. Social media posts may be automatically analyzed using the deep learning framework developed to identify depression. Our method, called Learning Based Depression Detection (LBDD), is designed to classify tweets based on their likelihood of containing depression. It works by taking in input from Twitter users. We evaluated our methodology with a benchmark dataset and found that the proposed deep learning model could outperform many existing models with the highest accuracy of 96.32%. Therefore, our deep learning model can be integrated with a clinical decision support system for assessing mental well-being.
Downloads
References
Paffenbarger RS Jr, Lee IM, Leung R (1994) Physical activity and personal characteristics associated with depression and suicide in American college men. Acta Psychiatrica Scandinavica 89:16–22. https://doi.org/ 10.1111/j.1600-0447.1994.tb05796.x.
Zafar A, Chitnis S (2020) Survey of depression detection using social networking sites via datamining.In:202010thInternationalConferenceonCloudComputing,DataScience&Engineering(Confluenc).IEEE, pp 88–93. https://doi.org/10.1109/Confluence47617.2020.9058189.
Kohrt BA, Speckman RA, Kunz RD, Baldwin JL, Upadhaya N, Acharya NR, … Worthman CM (2009) Culture in psychiatric epidemiology: using ethnography and multiple mediator models to assess the relationship of caste with depression and anxiety in Nepal. Annals of Human Biology 36(3):261–280. https://doi.org/10.1080/03014460902839194 .
Oquendo MA, Ellis SP, Greenwald S, Malone KM, Weissman MM, Mann JJ (2001) Ethnic and sex differences in suiciderates relativeto major depression in the UnitedStates. American Journal of Psychiatry 158(10):1652–1658. https://doi.org/10.1176/appi.ajp.158.10.1652
Beard C, Millner AJ, Forgeard MJ, Fried EI, Hsu KJ, Treadway MT, … Björgvinsson T (2016) Network analysis of depression and anxiety symptom relationships in a psychiatric sample. Psychological Medicine 46(16):3359–3369. https://doi.org/10.1017/S0033291716002300.
Biradar A, Totad SG (2018) Detecting Depression in Social Media Posts Using Machine Learning. In: International Conference on Recent Trends in Image Processing and Pattern Recognition. Springer, Singapore, pp 716–725. https://doi.org/10.1007/978-981-13-9187-3_64
Arora P, Arora P (2019) Mining twitter data for depression detection. In: 2019 International Conference on Signal Processing and Communication (ICSC). IEEE, pp 186–189. https://doi.org/10.1109/ICSC45622. 2019.8938353
Shreya Ghosh and Tarique Anwar; (2021). Depression Intensity Estimation via Social Media: A Deep Learning Approach . IEEE Transactions on Computational Social Systems. http://doi:10.1109/TCSS.2021.3084154
Keshu Malviya; Bholanath Roy and SK Saritha; (2021). A Transformers Approach to Detect Depression in Social Media . 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS). http://doi:10.1109/icais50930.2021.9395943
Chenhao Lin; Pengwei Hu; Hui Su; Shaochun Li; Jing Mei; Jie Zhou and Henry Leung; (2020). SenseMood: Depression Detection on Social Media . Proceedings of the 2020 International Conference on Multimedia Retrieval. http://doi:10.1145/3372278.3391932
Giuntini, Felipe T.; Cazzolato, Mirela T.; dos Reis, Maria de Jesus Dutra; Campbell, Andrew T.; Traina, Agma J. M. and Ueyama, Jó (2020). A review on recognizing depression in social networks: challenges and opportunities. Journal of Ambient Intelligence and Humanized Computing. http://doi:10.1007/s12652-020-01726-4
Shini Renjith, Annie Abraham, Surya B. Jyothi, Lekshmi Chandran and Jincy Thomson. (2022). An ensemble deep learning technique for detecting suicidal ideation from posts in social media platforms. Elsevier. 34(10), pp.9564-9575. https://doi.org/10.1016/j.jksuci.2021.11.010
Yang, Xingwei; McEwen, Rhonda; Ong, Liza Robee and Zihayat, Morteza (2020). A big data analytics framework for detecting user-level depression from social networks. International Journal of Information Management, 54, 102141–. http://doi:10.1016/j.ijinfomgt.2020.102141
Kailai Yang, Tianlin Zhang and Sophia Ananiadou. (2022). A mental state Knowledge–aware and Contrastive Network for early stress and depression detection on social media. Elsevier. 59(4), pp.1-16. https://doi.org/10.1016/j.ipm.2022.102961
Tapotosh Ghosh, Md. Hasan Al Banna, Md. Jaber Al Nahian, Mohammed Nasir Uddin, M. Shamim Kaiser and Mufti Mahmud. (2023). An attention-based hybrid architecture with explainability for depressive social media text detection in Bangla. Elsevier. 213(C), pp.1-17. https://doi.org/10.1016/j.eswa.2022.119007
Esteban A. Ríssola; David E. Losada and Fabio Crestani; (2021). A Survey of Computational Methods for Online Mental State Assessment on Social Media . ACM Transactions on Computing for Healthcare. http://doi:10.1145/3437259
Ziwei, Bernice Yeow and Chua, Hui Na (2019). Proceedings of the 2nd International Conference on Computing and Big Data - ICCBD 2019 - An Application for Classifying Depression in Tweets. 37–41. http://doi:10.1145/3366650.3366653
Tariq, Subhan; Akhtar, Nadeem; Afzal, Humaira; Khalid, Shahzad; Mufti, Muhammad Rafiq; Hussain, Shahid; Habib, Asad and Ahmad, Ghufran (2019). A novel Co-training based approach for the classification of mental illnesses using Social media posts. IEEE Access, 1–1. http://doi:10.1109/ACCESS.2019.2953087
Sancheng Peng, Lihong Cao, Yongmei Zhou, Zhouhao Ouyang, Aimin Yang, Xinguang Li, Weijia Jia and Shui Yu. (2022). A survey on deep learning for textual emotion analysis in social networks. Elsevier. 8(5), pp.745-762. https://doi.org/10.1016/j.dcan.2021.10.003
Ruba Skaik and Diana Inkpen; (2021). Using Social Media for Mental Health Surveillance . ACM Computing Surveys. http://doi:10.1145/3422824
Adikari, Achini; Gamage, Gihan; de Silva, Daswin; Mills, Nishan; Wong, Sze-Meng Jojo and Alahakoon, Damminda (2020). A self structuring artificial intelligence framework for deep emotions modelling and analysis on the social web. Future Generation Computer Systems, S0167739X20330053–. http://doi:10.1016/j.future.2020.10.028
Chatterjee, Ankush; Gupta, Umang; Chinnakotla, Manoj Kumar; Srikanth, Radhakrishnan; Galley, Michel and Agrawal, Puneet (2018). Understanding emotions in text using deep learning and big data. Computers in Human Behavior, S0747563218306150–. http://doi:10.1016/j.chb.2018.12.029
Yang, T., Li, F., Ji, D., Liang, X., Xie, T., Tian, S., and Liang, P. (2021). Fine-grained depression analysis based on Chinese micro-blog reviews. Information Processing & Management, 58(6), 102681. http://doi:10.1016/j.ipm.2021.102681
Xiaoxu Yao; Guang Yu; Jingyun Tang and Jialing Zhang; (2021). Extracting depressive symptoms and their associations from an online depression community . Computers in Human Behavior. http://doi:10.1016/j.chb.2021.106734
Lei Cao; Huijun Zhang and Ling Feng; (2022). Building and Using Personal Knowledge Graph to Improve Suicidal Ideation Detection on Social Media . IEEE Transactions on Multimedia. http://doi:10.1109/tmm.2020.3046867
Sanja Scepanovic; Enrique Martin-Lopez; Daniele Quercia and Khan Baykaner; (2020). Extracting medical entities from social media . Proceedings of the ACM Conference on Health, Inference, and Learning. http://doi:10.1145/3368555.3384467
Pran, Md. Sabbir Alam; Bhuiyan, Md. Rafiuzzaman; Hossain, Syed Akhter and Abujar, Sheikh (2020). 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT) - Analysis Of Bangladeshi People's Emotion During Covid-19 In Social Media Using Deep Learning. 1–6. http://doi:10.1109/ICCCNT49239.2020.9225500
Guillermo Blanco and Analia ´ Lourenço. (2022). Optimism and pessimism analysis using deep learning on COVID-19 related twitter conversations. Elsevier. 59(3), pp.1-15. https://doi.org/10.1016/j.ipm.2022.102918
Subramani, Sudha; Michalska, Sandra; Wang, Hua; Du, Jiahua; Zhang, Yanchun and Shakeel, Haroon (2019). Deep Learning for Multi-Class Identification From Domestic Violence Online Posts. IEEE Access, 7, 46210–46224. http://doi:10.1109/ACCESS.2019.2908827
Nawshad Farruque, Randy Goebel, Sudhakar Sivapalan and Osmar Zaïane. (2024). Deep temporal modelling of clinical depression through social media text. Elsevier. 6, pp.1-14. https://doi.org/10.1016/j.nlp.2023.100052
ABHINAV KUMAR, JYOTI KUMARI and JIESTH PRADHAN. (2023). Explainable Deep Learning for Mental Health Detection from English and Arabic Social Media Posts. ACM, pp.1-18. https://doi.org/10.1145/3632949
USMAN AHMED, JERRY CHUN-WEI LIN and GAUTAM SRIVASTAVA. (2023). Graph Attention Network for Text Classification and Detection of Mental Disorder. ACM. 17(3), pp.1-31. https://doi.org/10.1145/3572406
Jesia Quader Yuki; Md. Mahfil Quader Sakib; Zaisha Zamal; Sabiha Haque Feel and Mohammad Ashrafuzzaman Khan; (2020). Detecting Depression from Human Conversations . Proceedings of the 8th International Conference on Computer and Communications Management. http://doi:10.1145/3411174.3411187
Esteban A. Ríssola; Seyed Ali Bahrainian and Fabio Crestani; (2020). A Dataset for Research on Depression in Social Media . Proceedings of the 28th ACM Conference on User Modeling, Adaptation and Personalization. http://doi:10.1145/3340631.3394879
Felipe Taliar Giuntini; Kaue L. de Moraes; Mirela T. Cazzolato; Luziane de Fatima Kirchner; Maria de Jesus D. Dos Reis; Agma J. M. Traina; Andrew T. Campbell and Jo Ueyama; (2021). Modeling and Assessing the Temporal Behavior of Emotional and Depressive User Interactions on Social Networks . IEEE Access. http://doi:10.1109/access.2021.3091801
Sanjana Mendu; Anna Baglione; Sonia Baee; Congyu Wu; Brandon Ng; Adi Shaked; Gerald Clore; Mehdi Boukhechba and Laura Barnes; (2020). A Framework for Understanding the Relationship between Social Media Discourse and Mental Health . Proceedings of the ACM on Human-Computer Interaction. http://doi:10.1145/3415215
Kuhaneswaran AL Govindasamy and Naveen Palanichamy; (2021). Depression Detection Using Machine Learning Techniques on Twitter Data . 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS). http://doi:10.1109/ICICCS51141.2021.9432203
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
