Sentiment Analysis in Social Media for Depression Identification Using BiLSTM


  • M. Subathra Research Scholar, Department of Computer Science, Erode Arts and Science College (Autonomous), Tamil Nadu, India
  • K. Meenakshisundaram Associate Professor and Head, Department of Computer Science, Erode Arts and Science College (Autonomous), Tamil Nadu, India



Depression, Machine Learning, Mental Health, Sentiment Analysis, Social Media


Social networks have evolved into an excellent platform for users to engage with their interested friends and share their thoughts, photographs, and videos that show their emotions, feelings, and sentiments. This opens up the possibility of analyzing social network data for user feelings and sentiments in order to examine their moods and attitudes when talking through these online platforms. Although the diagnosis of depression using social network data has gained popularity around the world, there are other dimensions that have yet to be discovered. In this study, aim to perform a depression analysis on social media data collected from an online public source. The proposed is to explore the impact of Rule based Vader Analyzer and a BiLSTM . The results are calculated and shown using the performance metrics such as recall, precision and accuracy.


S. Almouzinia, M. Khemakhema, and A. Alageel, “Detecting Arabic Depressed Users from Twitter Data,” 16th International Learning and Technology Conference, Procedia Computer Science, Vol. 163, pp. 9, 2019.

P. Arora, and P. Arora, “Mining Twitter Data for Depression Detection,” International Conference on Signal Processing and Communication (ICSC), Noida, pp. 186-189, 2019.

N. Asad, M. Mahmud Pranto, S. Afreen, and I. M. M., “Depression Detection by Analyzing Social Media Posts of User,” IEEE International Conference on Signal Processing, Information, Communication and Systems (SPICSCON), Dhaka, Bangladesh, pp. 13-17, 2019.

M. De Choudhury, M. Gamon, S. Counts, and E. Horvitz, “Predicting Depression via Social Media”, ICWSM, Vol. 7, No. 1, pp. 128-137, Aug. 2021.

M. Deshpande, and V. Rao, “Depression detection using emotion artificial intelligence,” Proceedings of the International Conference on Intelligent Sustainable Systems (ICISS), IEEE, pp. 5, 2017.

C. Hutto, and E. Gilbert, “VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text,” Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media, AAAI, Vol. 216, pp. 10, 2014.

M. R. Islam, A. Kamal, N. Sultana, R. Islam, M. Moni, and A. Ulhaq, “Detecting Depression Using K-Nearest Neighbors (KNN) Classification Technique,” International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2), pp. 4, 2018.

J. Jacobson, “Detecting Language from Depressed Users with Korean Twitter Data,” Seoul National University, August 2018, [Online]. Available:

M. Hemnathkumar., and A. Latha, “Depression Detection with Sentiment Analysis of Tweets,” International Research Journal of Engineering and Technology (IRJET), Vol. 5, 2019.

T. Mikolov, I. Sutskever, K. Chen, G. Corrado, and J. Dean, “Distributed Representations of Words and Phrases and their Compositionality,” Advances in Neural Information Processing Systems, Vol. 26, No. 9, 2013.

Z. Peng, Q. Hu, and J. Dang, “Multi-kernel SVM based depression recognition using social media data,” International Journal of Machine Learning and Cybernetics, Vol. 15, 2017.

C. Seri, M. Zulkarnain, S. H. Ab Hamid, N. Anuar, M. Jali, and H. Meon, “Tweep: A System Development to Detect Depression in Twitter Posts,” 2020. DOI: 10.1007/978-981-15-0058-9_52.

P. M. Sosa, Twitter Sentiment Analysis using combined LSTM-CNN Models, Eprint Arxiv, pp. 1-9, 2017.

J. J. Stephen, and P. P. “Detecting the magnitude of depression in Twitter users using sentiment analysis,” International Journal of Electrical and Computer Engineering, Vol. 9, 2019.

TWINT tool. (n.d.). [Online]. Available:

T. Xiaohui, Ji Xujuan, Zhang, and Yong. “Sentiment analysis for depression detection on social networks,” 12th International Conference on Advanced Data Mining and Applications (ADMA 2016), Australia, 2016.

WHO, 2011, [Online]. Available: pdf_files/EB130/B130_9-en.pdf 18. Google News Vectors. (n.d.). GitHub - mmihaltz/word2vec-Google News-vectors: word2vec Google News model.

M. Subathra, “A Survey on Sentimental Analysis and Techniques,” The International Journal of Analytical and Experiment Al Model Analysis, Vol. 13, No. 4.

M. Subathra, “Comparison of Sentiment Analysis Using Efficient Feature Selection Techniques,” Vol. 11, No. 6.

P. M. Sosa, Twitter Sentiment Analysis using combined LSTM-CNN Models, Eprint Arxiv, pp. 1-9, 2017.




How to Cite

Subathra, M., & Meenakshisundaram, K. (2022). Sentiment Analysis in Social Media for Depression Identification Using BiLSTM. Asian Journal of Computer Science and Technology, 11(1), 17–20.