Summary
Ting Su, PhD (2022) is a Post-Doctoral Researcher at Imperial College London focusing on developing and designing AI and LLM systems to support wellbeing in areas of dementia and asthma. Dr Ting Su works closely with Professor Rafael A. Calvo in developing chatbots that help asthma patients manage their symptoms. Dr Ting Su also works closely with Professor Ravi Vaidyanathan in collaboration with UKDRI CR&T in developing a chatbot-based care system for people living with dementia.
Dr Ting Su is also interested in developing LLMs with constraints to further medical usage of LLM, which should minimise the potential risk of LLMs, and facilitate wider adoption of LLM in the medical domain.
Furthermore, Dr Ting Su is trained in constructing and developing language model structures to suit niche usages, as well as developing network-based deep learning models for fake news detection and community detection on Twitter.
Publications
Journals
Raposo de Lima M, Vaidyanathan R, Barnaghi P, 2023, Discovering behavioural patterns using conversational technology for in-home health and well-being monitoring, Ieee Internet of Things Journal, Vol:10, ISSN:2327-4662, Pages:18537-18552
Su T, Calvo RA, Jouaiti M, et al., 2023, Assessing a sleep interviewing chatbot to improve subjective and objective sleep: protocol for an observational feasibility study, Jmir Research Protocols, Vol:12, ISSN:1929-0748, Pages:1-10
Conference
Su T, Macdonald C, Ounis I, Entity detection for check-worthiness prediction: Glasgow Terrier at CLEF CheckThat! 2019, Conference and Labs of the Evaluation Forum
Su T, Macdonald C, Ounis I, 2019, Ensembles of Recurrent Networks for Classifying the Relationship of Fake News Titles, SIGIR '19: The 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM
Su T, Fang A, McCreadie R, et al., 2018, On Refining Twitter Lists as Ground Truth Data for Multi-community User Classification, 40th European Conference on Information Retrieval Research (ECIR), SPRINGER INTERNATIONAL PUBLISHING AG, Pages:765-772, ISSN:0302-9743