Papers by Thushari Atapattu
Exploring the Role of Mental Health Conversational Agents in Training Medical Students and Professionals: A Systematic Literature Review (2025.findings-acl)
Copied to clipboard
| Challenge: | This systematic review analyses 38 studies on AI-powered conversational agents in mental health education and training . traditional training methods provide valuable but expensive and inherently limited learning opportunities . early pioneers like Woebot and Wysa demonstrated a groundbreaking insight: machines could engage in meaningful therapeutic interactions. |
| Approach: | They analyse 38 studies on AI-powered conversational agents in mental health education and training . findings reveal that AI-based approaches dominate the field, with training as the application area being the most prevalent . |
| Outcome: | The systematic review of 38 studies on AI-powered conversational agents in mental health education and training (MHET) reveals that AI-based approaches dominate the field, with training as the application area being the most prevalent. |
Automatic Detection of Cross-Disciplinary Knowledge Associations (P18-3)
Copied to clipboard
| Challenge: | Currently, scientists tend to deal with fragments of the literature according to their specialisation, resulting in important and hidden associations among fragmented knowledge. |
| Approach: | a doctoral thesis examines cross-disciplinary knowledge associations hidden in scientific literature . the aim is to identify most promising research pathways by analysing existing scientific literature. |
| Outcome: | The proposed approach suggests most promising research pathways by analysing the existing scientific literature. |
EmoMent: An Emotion Annotated Mental Health Corpus from Two South Asian Countries (2022.coling-1)
Copied to clipboard
Thushari Atapattu, Mahen Herath, Charitha Elvitigala, Piyanjali de Zoysa, Kasun Gunawardana, Menasha Thilakaratne, Kasun de Zoysa, Katrina Falkner
| Challenge: | Recent research using AI and NLP demonstrates strong potential to automatically detect mental health issues from digital footprints such that professionals could provide timely interventions and mental health resources to vulnerable persons. |
| Approach: | They developed an emotion-annotated mental health corpus from 2802 Facebook posts extracted from two South Asian countries, Sri Lanka and India. |
| Outcome: | The proposed model achieved 98.3% agreement between the annotators and a Fleiss’ Kappa of 0.82. |