Abstract
Suicidal ideation is a major psychological problem, and preventing this social risk is recognized as an important research topic. In reality, there can be several reasons why a person experiences suicidal ideation. Each individual can express views, emotions, and several types of symptoms related to suicidal ideation on the most popular social media platforms. In online social networks (OSNs), identification of suicidal ideation is one of the major challenging tasks. Existing studies have shown that the delay in understanding and identifying various risk factors can cause the suicidal event to occur. Due to the scarcity of data and understanding, the genuine intentions of people in their posts are the major challenges to improve the efficacy of suicidal ideation detection. Motivated by the existing psychological research, this article first analyzes an individual's social behavior from different perspectives, namely, stress-oriented knowledge, tweet behavior, emotion transition sequence, social interaction, and other psychological factors. Next, a tweet inspection framework based on fuzzy deep reinforcement learning (FDRL) model is proposed to detect users with suicidal ideation in OSNs. In addition, a suicidal influential user is proposed by considering a suicidal influence minimization with minimum contextual modification model (SIM-MCM), which reduces the impact of suicidal influence without major changes in the contextual information during the cascading process in OSNs. Experimental results illustrate that the proposed model effectively detects users with suicidal ideation when compared with other deep learning classifier models.
Recommended Citation
G. Lingam and S. K. Das, "Fuzzy-Based Deep Reinforcement Learning for Suicidal Ideation Detection in Online Social Networks," IEEE Transactions on Computational Social Systems, Institute of Electrical and Electronics Engineers; Computer Society; Systems, Man, and Cybernetics Society, Jan 2025.
The definitive version is available at https://doi.org/10.1109/TCSS.2025.3622536
Department(s)
Computer Science
Publication Status
Early Access
Keywords and Phrases
Deep reinforcement learning (DRL); fuzzy; online social networks (OSNs); suicidal ideation; suicidal influential user
International Standard Serial Number (ISSN)
2329-924X
Document Type
Article - Journal
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2025 Institute of Electrical and Electronics Engineers; Computer Society; Systems, Man, and Cybernetics Society, All rights reserved.
Publication Date
01 Jan 2025
