A Depression Diagnostic System using Lexicon-based Text Sentiment Analysis
Keywords:
Extraction, Lexicon-based sentiment analysis, Depression classification, Social media analytics, Text miningAbstract
Clinical psychologists typically diagnose depression via a face-to-face session, applying depression diagnostic criteria. However, past literature revealed that most patients would not seek help from doctors at the early stage of depression, resulting in a declination of their mental health condition. Many people feel more comfortable sharing their thoughts online through social media platforms in today's modern digital era. Since then, many researchers have studied using social media to predict mental health conditions. To the extent of our knowledge, there is no study related to the experimentation of online depression diagnostic systems using text from social media platforms available for individuals. Our study presented in this paper has two-fold: i) enhancing existing lexicon-based methods by formulating a more accurate classification function for detecting depressive text from a social media platform, and ii) developing a depression diagnostic system embedded with our improved lexicon method for individuals to visualize their depression state instantly via an online interface. The depression lexicon developed in this study was validated by psychologists who have relevant domain knowledge in depression. Our experimented lexicon-based method achieved a precision of 77% and an F1-score of 74% in classifying depression state. In addition, we also found that depressed person uses more offensive words and are more aggressive when they communicate.
References
J. Dine, Companies, international trade, and human rights, Cambridge University Press, 2005.
X. Wang, C. Zhang, Y. Ji, L. Sun, L. Wu, and Z. Bao, A depression detection model based on sentiment analysis in micro-blog social network. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 201-213. Berlin, Germany: Springer, 2013. https://doi.org/10.1007/978-3-642-40319-4_18
S. Gilbody, T. Sheldon, and A. House, Screening and case-finding instruments for depression: a meta-analysis. Cmaj. 178(8), 997-1003, 2008. https://doi.org/10.1503/cmaj.070281
A. J. Mitcehk and J. C.Coyne, Screening for Depression in Clinical Practice: An Evidence?Based Guide. OUP USA, 2009.
C. Aggarwal, An introduction to social network data analytics. In Social network data analytics, pp. 1-15. Boston, MA: Springer, 2011. https://doi.org/10.1007/978-1-4419-8462-3_1
P. A. Cavazos-Rehg, M. J. Krauss, S. Sowles, S. Connolly, C. Rosas, M. Bharadwaj, and L. J. Bierut, A content analysis of depression-related tweets. Computers in Human Behavior, 54, 351–357, 2016. https://doi.org/10.1016/j.chb.2015.08.023.
A. Basantani, Y. Kesarwani, S. Bhatia, and S. Jain, EmoCure: Utilising Social Media Data and Smartphones to Predict and Cure depression. IOP Conference Series. Materials Science and Engineering, 1110(1), 12010, 2021. https://doi.org/10.1088/1757-899X/1110/1/012010
D. E. Losada and P. Gamallo, Evaluating and improving lexical resources for detecting signs of depression in text. Language Resources and Evaluation, 54(1), 1–24, 2020. https://doi.org/10.1007/s10579-018-9423-1.
Y. Neuman, Y. Cohen, D. Assaf, and G. Kedma, Proactive screening for depression through metaphorical and automatic text analysis. Artificial Intelligence in Medicine, 56(1), 19–25, 2012. https://doi.org/10.1016/j.artmed.2012.06.001
B. Y. Ziwei, and H. N. Chua, An Application for Classifying Depression in Tweets. In Proceedings of the 2nd International Conference on Computing and Big Data, pp. 37–41, 2019.
R. L. Spitzer, K. Kroenke, and J. B. Williams, Validation and utility of a self-report version of PRIME-MD: the PHQ primary care study. Primary Care Evaluation of Mental Disorders. Patient Health Questionnaire. JAMA?: the Journal of the American Medical Association, 282(18), 1737–1744, 1999.
R. L. Spitzer, J. B. Williams, K. Kroenke, R. Hornyak, and J. McMurray, Validity and utility of the PRIME-MD Patient Health Questionnaire in assessment of 3000 obstetric-gynecologic patients: The PRIME-MD Patient Health Questionnaire Obstetrics-Gynecology Study. American Journal of Obstetrics and Gynecology, 183(3), 759–769, 2000. https://doi.org/10.1067/mob.2000.106580
L. S. Radloff, The CES-D Scale: A Self-Report Depression Scale for Research in the General Population. Applied Psychological Measurement. 1(3), 385–401, 1977.
“Diagnostic and statistical manual of mental disorders,” DSM-5, Fifth edition. American Psychiatric Publishing, 2013.
B. Pang and L. Lee, Opinion mining and sentiment analysis. Comput. Linguist. 35.2, 311-312, 2009.
A. Saxena, A Semantically Enhanced Approach to Identify Depression-Indicative Symptoms Using Twitter Data, 2018.
S. Stieglitz and L. Dang-Xuan, Emotions and Information Diffusion in Social Media-Sentiment of Microblogs and Sharing Behavior. Journal of Management Information Systems, 29(4), 217–248, 2013. https://doi.org/10.2753/MIS0742-1222290408
A. Go, R. Bhayani, and L. Huang, Twitter sentiment classification using distant supervision. CS224N project report, Stanford 1.12, 2009.
A. Bermingham and A.Smeaton, Classifying sentiment in microblogs: is brevity an advantage?. Proceedings of the 19th ACM International Conference on Information and Knowledge Management. ACM, pp. 1833–36, 2010. https://doi.org/10.1145/1871437.1871741
S. Rude, E. M. Gortner, and J. Pennebaker, Language use of depressed and depression-vulnerable college students. Cognition and Emotion, pp. 1121–33. Taylor & Francis Group, 2004. https://doi.org/10.1080/02699930441000030.
M. Park, C. Cha, and M. Cha, Depressive moods of users portrayed in Twitter. In Proceedings of the ACM SIGKDD Workshop on Healthcare Informatics (HI-KDD’12), pp. 1–8, 2012.
M. De Choudhury, S. Counts, and E. Horvitz, Social media as a measurement tool of depression in populations. Proceedings of the 5th Annual ACM Web Science Conference, ACM. pp. 47–56, 2013. https://doi.org/10.1145/2464464.2464480.
S. Malmasi, M. Zampieri, and M. Dras, Predicting post severity in mental health forums. In Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology, pp. 133-137, 2016.
B. Ay, O. Yildirim, M. Talo, U. B. Baloglu, G. Aydin, S. D. Puthankattil, and U. R. Acharya, Automated Depression Detection Using Deep Representation and Sequence Learning with EEG Signals. Journal of Medical Systems, 43(7), 1–12, 2019. https://doi.org/10.1007/s10916-019-1345-y
C. Zucco, B. Calabrese, and M. Cannataro, Sentiment analysis and affective computing for depression monitoring. 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, pp. 1988–95 (2017). https://doi.org/10.1109/BIBM.2017.8217966.
N. Ramirez-Esparza, C. K. Chung, E. Kacewicz, and J. W. Pennebaker, The Psychology of Word Use in Depression Forums in English and in Spanish: Texting Two Text Analytic Approaches. In ICWSM, 2008.
P. G. F. Cheng, R. M. Ramos, J. Á. Bitsch, S. M. Jonas, T. Ix, P. L. Q. See, and K. Wehrle, Psychologist in a pocket: Lexicon development and content validation of a mobile-based app for depression screening. JMIR mHealth and uHealth, pp. e88–e88. JMIR Publications, 2016. https://doi.org/10.2196/mhealth.5284
S. Almatarneh and P. Gamallo, A lexicon based method to search for extreme opinions. PloS One, pp. e0197816–e0197816. PUBLIC Library Science, 2018. https://doi.org/10.1371/journal.pone.0197816.
M. Taboada, J. Brooke, M. Tofiloski, K. Voll, and M. Stede, Lexicon-based methods for sentiment analysis. Computational Linguistics - Association for Computational Linguistics, 37(2), 267–307, 2011. https://doi.org/10.1162/COLI_a_00049.
X. Wang, C. Zhang, Y. Ji, L. Sun, L. Wu, and Z. Bao, A Depression Detection Model Based on Sentiment Analysis in Micro-blog Social Network. Trends and Applications in Knowledge Discovery and Data Mining, 7867, 201–213, 2013. https://doi.org/10.1007/978-3-642-40319-4_18
Z. Dong, and Q. Dong, HowNet - a hybrid language and knowledge resource. In: Proceedings of International Conference on Natural Language Processing and Knowledge Engineering, pp. 820–824, 2003.
M. De Choudhury, S. Counts, and E. Horvitz, Predicting postpartum changes in emotion and behavior via social media. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 3267–3276, 2013.
D. E. Losada and F. Crestani, A Test Collection for Research on Depression and Language Use. In International Conference of the Cross-Language Evaluation Forum for European Languages, pp. 28–39. Cham: Springer, 2016.
J. Schler, M. Koppel, S. Argamon, and J. W. Pennebaker, Effects of age and gender on blogging. In AAAI 2006 spring symposium on computational approaches to analysing weblogs, pp. 1-7, 2006.
T. Davidson, D. Warmsley, M. Macy, and I. Weber, Automated hate speech detection and the problem of offensive language. In Proceedings of the International AAAI Conference on Web and Social Media, 2017.
M. Stankevich, I. Smirnov, N. Kiselnikova, and A. Ushakova, Depression Detection from Social Media Profiles. In Data Analytics and Management in Data Intensive Domains, pp. 181–194. Springer International Publishing, 2020. https://doi.org/10.1007/978-3-030-51913-1_12.
L. Ma, Z. Wang, and Y. Zhang, Extracting Depression Symptoms from Social Networks and Web Blogs via Text Mining. Bioinformatics Research and Applications, 10330, 325–330, 2017. https://doi.org/10.1007/978-3-319-59575-7_29.
S. K. Bharti and K. S. Babu, Automatic keyword extraction for text summarization: A survey. arXiv preprint arXiv:1704.03242, 2017.
A. Dunne, M. Etropolski, A. Vermeulen, and P.Nandy, On Average: Data Exploration Based on Means Can Be Misleading. The AAPS Journal, pp. 60–67, us: Springer, 2012.
C. Goutte, and E. Gaussier, A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation. In European conference on information retrieval, pp. 345–359. Heidelberg, Berlin: Springer, 2005.
M. Taboada, J. Brooke, M. Tofiloski, K. Voll, and M. Stede, Lexicon-based methods for sentiment analysis. Computational linguistics, 37(2), pp.267-307, 2011.
M. Taboada, Computational analysis of text sentiment, 2021. http://www.sfu.ca/~mtaboada/nserc-project.html.
L. Zhang, R. Ghosh, M. Dekhil, M. Hsu, and B. Liu, Combining lexicon-based and learning-based methods for Twitter sentiment analysis. HP Laboratories, Technical Report HPL-2011, 89, 2011.
P. Palanisamy, V. Yadav, and H. Elchuri, Serendio: Simple and Practical lexicon based approach to Sentiment Analysis. In Second Joint Conference on Lexical and Computational Semantics (* SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013) (pp. 543-548), 2013, June.
H. Christina, On Classification to and from Various Orders of Magnitude, 2008. https://serendipstudio.org/exchange/christina-harview/classification-and-various-orders-magnitude.
