AI-DRIVEN REAL-TIME PREDICTION OF ANXIOUS DEPRESSION FROM DYNAMIC SOCIAL MEDIA ACTIVITY

Read full text Summarise with VIRAT
Authors: Kaushik Chanda
Cited by: 0
References: 3

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

In this study, we present an ensemble model that can correctly detect anxious depression in realtime social media streams.Based on the linguistic and behavioural conventions, it was necessary to develop a five-entry device which is spoon fed by the specific anxiety lexicon.It is used to look for the corresponding mood shifts in the message and the irregular publishing behaviour of the users.The model is implemented as a combination of a multinomial Naïve Bayes, gradient boosting, and random forest classifiers with a majority vote.The framework is tested for 100 people's tweets and shows 85.09% accuracy in user classification, which is a good indication of its potential for prediction.

Fields of Study & Subjects

Mental Health via Writing Emotion and Mood Recognition Sentiment Analysis and Opinion Mining

Publication details

Journal / source
Science and Culture
Volume
92
Publication date
17 March 2026
Language
EN