Social Media Depression Monitoring Model Using Sentiment Analysis  
  Authors : Ebunoluwa Okediran; Jonah Joshua; Afolashade Kuyoro; Abolaji Akanbi

 

The proliferation of mobile technology, with the privacy and ubiquity that it offers often presents social media pseudo-confidant for lonely and depressed individuals. Social media continues to play an active part in contemporary human life, according to statistics about 40% of the global population are currently active on social media. According to the World Health Organization, at least one in every twenty-five people living as at October 2019 are depressed. Several authors and researchers have developed and proposed methods to predict depression through sentiments in social media posts. Twitter have been widely investigated although other social networks have also been discoursed such as Sina (a Chinese micro blog) and Myspace. It is in light of this that this research seeks to gather social media dataset that is applicable for non-clinical early prediction of the mental health status of users towards strengthening business intelligence. Hence, this work is focusing on mining comments from twitter as a mitigation technique for depression.

 

Published In : IJCAT Journal Volume 7, Issue 4

Date of Publication : April 2020

Pages : 47-51

Figures :02

Tables :--

 

 

 

Ebunoluwa Okediran : Computer Science Department, School of Computing and Engineering Sciences, Babcock University, Ilishan-Remo, Ogun State, Nigeria.

Jonah Joshua : Computer Science Department, School of Computing and Engineering Sciences, Babcock University, Ilishan-Remo, Ogun State, Nigeria.

Afolashade Kuyoro : Computer Science Department, School of Computing and Engineering Sciences, Babcock University, Ilishan-Remo, Ogun State, Nigeria.

Abolaji Akanbi : Computer Science Department, School of Computing and Engineering Sciences, Babcock University, Ilishan-Remo, Ogun State, Nigeria.

 

 

 

 

 

 

 

Classification Algorithms, Depression, Machine Learning (ML), Sentiment Analysis (SA), Social Media

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Sentiment Analysis can help to monitor people's mood. People with symptoms of depression have similar behavior that can be expressed in the phrases posted on social media. Thus, this useful information helps to determine users who have potential psychological disturbs such as depression. Also, authorized persons, relatives and medical personnel can have access to this information.In conclusion, this research proffers a web-based DMS that provides a solution to the problem of identifying depression, analyzing and recommending therapy to such individuals. With these solutions the aftermath of depression which is death will drastically reduce.

 

 

 

 

 

 

 

 

 

[1] H. Ritchie, and M. Roser, "Mental Health," 2018. [Online]. Available: https://ourworldindata.org/mental-health. . [2] WHO, "Depression," 2018. [Online]. Available: World Health Organization: https://www.who.int/news-room/fact-sheets/detail/depression.. [3] WHO, "Mental Health: Suicide Data," 2018. [Online]. Available: World Health Organization: https://www.who.int/mental_health/prevention/suicide/suicideprevent/en/. [4] R. Feintzeig, "With Workplace Suicides Rising, Companies Plan for the Unthinkable," 2018. [Online]. Available: https://www.wsj.com/articles/with-workplace-suicides-rising-companies-plan-for-the-unthinkable-1516205932. [5] S. Advanced, "expertsystem," 2017. [Online]. Available: https://expertsystem.com/social-media-data-mining/. [6] J.R, Brubaker, F. Kivran-Swaine, L. Taber, and G.R. Hayes, "Grief-stricken in a crowd: the language of bereavement and distress in social media," in Proceedings of ICWSM, 2012, pp. 42-49. [7] 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 Li, J., Cao, L., Wang, C., Tan, K.C., Liu, B., Pei, J., Tseng, V.S. (eds.) PAKDD LNCS, 2013, Vol. 7867, pp. 201-213. [8] M. De Choudhury, S. Counts, and, E. Horvitz, "Social Media as a measurement tool of depression in populations," in Proceedings of the 5th Annual ACM Web Science Conference, 2013, pp. 47-56. [9] S. Tsugawa, Y. Kikuchi, F. Kishino, K. Nakajima, Y. Itoh, and H. Ohsaki, "Recognizing depression from twitter activity," in CHI'15 Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, 2015, pp. 3187-3196. [10] M. Nadeem, "Identifying depression on Twitter," arXiv preprint:1607.07384, 2016. [11] X. Tao, X. Zhou, J. Zhang, and J. Yong, "Sentiment Analysis for Depression Detection," Springer International Publishing, pp. 807-810, 2016. [12] D.E. Losada, and F. Crestani, "A test collection for research on depression and language use," N. Q. Fuhr, Ed.) CLEF LNCS, Springer, Cham, vol. 9822, pp. 28-39, 2016. [13] R. L. Rosa, D. Z. Rodriquez., G. M. Schwartz, I. de Campos Ribeiro, and G. Bressan, "Monitoring system for potential users with depression using sentiment analysis," in IEEE International Conference on Consumer Electronics (ICCE), 2016, pp. 381-382. [14] V. Leiva, and A. Freire, ""Towards Suicide Prevention: Early Detection of Depression on Social Media," Springer International Publishing, pp. pp. 428-436, 2017. [15] myvocabulary.com, "Depression Vocabulary Word List," 2016. [Online]. Available: https://myvocabulary.com/word-list/depression-vocabulary/. [16] Dictionary.com, "Depression," 2016. [Online]. Available: http://www.thesaurus.com/browse/depression.