URESHII- Improving one’s Mental Wellbeing
Keywords:
Mental health, Teenage behavioral issues, Mental state assessment, Machine learning, Web-app, ML based mental health analysis, Clustering algorithmAbstract
Ureshii (Happiness in Japanese) is a mental health app. Based on behavioral activation therapy, it uses machine learning technology with clustering algorithms to recommend the apt activities and create the best mental health path for each user. The app starts by asking you 5 questions (based on the PHQ-9 test) everyday to monitor your dopamine, serotonin, oxytocin, and endorphin levels and scores and tracks your responses. Our app tracks which activities improve your hormonal levels more and uses the “K nearest neighbors” machine learning algorithm to cluster people with similar profiles and a similar difference in scores together. Based on this, our app uses a recommender system to suggest similar activities which it thinks will help improve your mental wellbeing. For example if ‘user A’ finds dancing to be a rewarding activity and has shown to have a score of 5/10, the app will cluster them with someone (‘user B’) who also finds dancing to be a rewarding activity and who also has a score of 5/10. If ‘user B’ finds yoga to be another rewarding activity, the app will recommend yoga to ‘user A’ as well. It learns from the user’s responses and changes its recommendation as well as the cluster the user has been put in once it notices that the user is not being affected positively. Beyond recommending activities to the user, the app also keeps track of their mental health, provides easy-access to trained therapists, and helps people take control of their mental health.
References
The therapeutic effectiveness of creative activities on mental well-being: a systematic review of the literature, J. LECKEY RN RMN RNCT RNT BSc (Hons) MEd Pg Dip PSI Dip Group Work, First published: 17 February 2011 https://doi.org/10.1111/j.1365-2850.2011.01693.x
Rodríguez, Fernando M. and Garza, Sara E. ‘Predicting Emotional Intensity in Social Networks’. 1 Jan. 2019 : 4709 – 4719.
Patel, Kuldeep Kumar,et al. "Mental Health Detection Using Transformer BERT." Handbook of Research on Lifestyle Sustainability and Management Solutions Using AI, Big Data Analytics, and Visualization, edited by Sailesh Suryanarayan Iyer, et al., IGI Global, 2022, pp. 91-108. https://doi.org/10.4018/978-1-7998-8786-7.ch006
Zhao, L., Li, Q., Xue, Y. et al. A systematic exploration of the micro-blog feature space for teens stress detection. Health Inf Sci Syst 4, 3 (2016). https://doi.org/10.1186/s13755-016-0016-3
Chancellor, S., De Choudhury, M. Methods in predictive techniques for mental health status on social media: a critical review. npj Digit. Med. 3, 43 (2020). https://doi.org/10.1038/s41746-020-0233-7
Anja Thieme, Danielle Belgrave, and Gavin Doherty. 2020. Machine Learning in Mental Health: A Systematic Review of the HCI Literature to Support the Development of Effective and Implementable ML Systems. ACM Trans. Comput.-Hum. Interact. 27, 5, Article 34 (October 2020), 53 pages. https://doi.org/10.1145/3398069
Teenagers’ Stress Detection Based on Time-Sensitive Micro-blog Comment/Response Actions, Artificial Intelligence in Theory and Practice IV, 2015, Volume 465, ISBN : 978-3-319-25260-5,Liang Zhao, Jia Jia, Ling Feng, https://link.springer.com/chapter/10.1007/978-3-319-25261-2_3
Kilgarriff-Foster, A. and O'Cathain, A. (2015).Exploring the components and impact of social prescribing. Journal of Public Mental Health, 14(3), 127-134
