User Profiling for Personalization
This is a hybrid meeting. Please find the Teams link in the Abstract.
Dr. Huizhi (Elly) Liang is a senior Lecturer at the School of Computing, Newcastle University, UK. Huizhi received her PhD degree from the Queensland University of Technology, Australia. Before joining Newcastle University in 2022, she worked at University of Reading, LIP6, Pierre et Marie Curie University and French National Center for Scientific Research (CNRS), University of Melbourne, and Australian National University. Her research interests include Data Mining, Machine Learning, NLP, Dialogue Agents, Personalization, Recommender Systems.

Personalization is to provide information or services that are tailed to individual users. User profiling is a critical component of Personalization. How to profile users’ preferences, interests, and human level attributes such as personality accurately to facilitate effective personalization remains an open research topic. This talk will present our recent work in profiling information system users and literature characters for personalized item recommendation and dialogue generation. We proposed novel data mining and machine learning techniques including reinforcement learning, graph learning, Natural Language Processing on various types of modality data including rating, tags, review, item images, temporal information, and relations. Experiments were conducted on large-scale real-world datasets from online communities such as IMDB and Amazon and literature books.
Date: 19 February 2024, 13:00 (Monday, 6th week, Hilary 2024)
Venue: Wolfson College, Linton Road OX2 6UD
Venue Details: Buttery
Speaker: Dr. Huizhi (Elly) Liang (Newcastle University)
Organising department: Wolfson College
Organisers: Mr Csaba Botos (University of Oxford), Dr. Yi Yin (University of Oxford)
Organiser contact email address:
Part of: Oxford Cross-Disciplinary Machine Learning (OxfordXML) Research Cluster Seminar Series
Booking required?: Not required
Cost: Free (cake, tea and coffee provided)
Audience: Public
Editor: Yi Yin