Mental Illness Detection and Analysis on Social Media
1University of Petroleum & Energy Studies, Dehradun, India
2CIC-IPN, Mexico, Mexico
3St. John's University, New York, USA
4University of Bari Aldo Moro, Bari, Italy
Mental Illness Detection and Analysis on Social Media
Description
Academic researchers have shown sharp interest in social media data analysis for a few decades. Amid COVID-19 lockdown, the number of scientific studies on user-generated data and social connections has increased exponentially. Recently, advances in deep learning and soft computing have shown great improvements on mental health detection and analysis over social media data. As per existing studies, 80% of users who attempt suicide disclose their intentions over social media.
At present, shallow and deep learning are used for identifying mental illness on social media, however, recent research trends in graph neural network, federated learning, multitask classification, multilingual mental health classification and concept drift in streaming data have shown improvement in e-Health management. Many ethical issues and dataset concerns prevail and hence, there is a necessity to assemble recent advances in mental health detection and analysis approaches and challenges.
This Special Issue focuses on human - computer interaction analysis over mental healthcare with social media data. This Special Issue aims to provide a forum to disseminate and discuss recent advances in deep learning and computational intelligence techniques for mental healthcare on social media. We want to offer an opportunity for researchers and practitioners to identify new promising research and review articles directions in this area.
Potential topics include but are not limited to the following:
- Feature extraction for mental illness detection
- Multi-class mental illness detection and analysis
- Multi-task mental health status detection
- Multimodal information extraction for mental health analysis
- Multi-channel mental health detection
- Shallow, deep and federated learning for mental illness detection
- Ethical issues for mental illness detection and analysis on social media
- Information fusion and feature harvesting from social media data
- Transformation model for mental illness detection on social media
- Concept drift in mental illness detection from streaming data