Prognostic of depression levels due to pandemic using LSTM.

Bano, Shahana; Pranathi, Yerramreddy Lakshmi; Niharika, Gorsa Lakshmi; Sreya, Gorsa Datta Sai

Abstract

Depression is a medical illness that affects the way you think and how you react. It is a serious medical issue that impacts the stability of the mind. Depression occurs at many stages and situations. With the help of classification, the stage of depression the person is in can be tried to categorize. Nowadays, many users are sharing their views on social media, and it became a platform for knowing people around us. From the data that is shared on social media, the depressing posts are being classified using machine learning techniques. With these reports collected, the depressed person might be helped from making any sudden decisions. So, in our research study, the large datasets of the people in depression during the COVID-19 pandemic situations is analyzed and not in pandemic situations. Here to analyze the data, the neural networks have been trained with the current pandemic analysis report, and it has given a prediction that the people are less likely to get depressed when they are not in a pandemic situation like COVID-19.

Citation

BANO, S., PRANTHI, Y.L., NIHARIKA, G.L. and SREYA, G.D.S. 2021. Prognostic of depression levels due to pandemic using LSTM. In Shakya, S., Balas, V.E., Haoxiang, W. and Baig, Z. (eds.) Proceedings of the 2020 International conference on sustainable expert systems (ICSES 2020), 28-29 September 2020, Kirtipur, Nepal. Lecture notes in networks and systems, 176. Singapore: Springer [online], pages 11-22. Available from: https://doi.org/10.1007/978-981-33-4355-9_2

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2020 International conference on sustainable expert systems (ICSES 2020)
• Start Date: Sep 28, 2020
• End Date: Sep 29, 2020
• Acceptance Date: Aug 20, 2020
• Online Publication Date: Mar 31, 2021
• Publication Date: Dec 31, 2021
• Deposit Date: Nov 12, 2024
• Publicly Available Date: Nov 12, 2024
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 11-22
• Series Title: Lecture notes in networks and systems
• Series Number: 176
• Series ISSN: 2367-3370; 2367-3389
• ISBN: 9789813343542
• DOI: https://doi.org/10.1007/978-981-33-4355-9_2
• Keywords: Social media; Text mining; Depression; Mental health; Recurrent neural networks
• Public URL: https://rgu-repository.worktribe.com/output/2064034