Abstract:

The increasing burden of mental health disorders-including depression, anxiety, OCD, and suicidal ideation-necessitates the development of advanced Al frameworks capable of interpreting complex emotional signals from language. Our research focuses on context-aware large language models (LLMs) that capture nuanced emotional and psychological patterns embedded in long, unstructured text. These models are designed to preserve semantic coherence and context across sequences, enabling more accurate detection of early mental health risk factors. We introduce a multi-task representation learning approach that integrates subject specific and context-specific features for detecting a range of mental health conditions from both psychiatric and social media texts. This strategy allows for task-specific adaptation while maintaining shared representations, enhancing generalization across related emotional and behavioral tasks. A key aspect of our work involves Hierarchical Explainable Al (XAI), where we employ layered attention mechanisms and graph-based interpretability techniques to identify critical risk-inducing patterns in suicidal and emotionally volatile texts. The framework not only highlights word-level and sentence-level importance but also models higher-order semantic dependencies across text segments, offering transparency in sensitive decision-making contexts. Our current direction explores the use of Explainable Graph Attention Networks and Deep Q-Learning to identify high-risk emotional states and generate context-aware intervention strategies. We further envision the integration of generative Al for producing personalized, real-time supportive responses.

Future extensions involve multimodal LLMs that combine text, image, and genetic data for a more holistic understanding of mental health.

 

Bio:

Dr. Dheeraj Kodati is currently an Assistant Professor in the Department of Computer Science and Engineering at Mahindra University, Hyderabad. Prior to this, he worked as a software developer in various organizations across the USA and India, accumulating over 10 years of experience in the software industry, R&D labs, and government organizations. He earned his Ph.D. in Computer Science and Engineering with a specialization in Natural Language Processing and Deep Learning from the National Institute of Technology (NIT) Warangal and holds a Master’s degree in Computer Science from the University of Central Missouri, USA. Dr. Dheeraj has published several impactful journal and conference papers and has also secured grants from industry-funded projects. His research areas include Natural Language Processing, Healthcare, Deep Learning, Large Language Models, Graph Mining, Explainable Al, and Bioinformatics. He also serves as a reviewer for reputed journals and conferences, including Computers in Biology and Medicine, Engineering Applications of Artificial Intelligence, The Journal of Supercomputing, Artificial Intelligence Review, PAKDD, and DASFAA.