Research + Teaching

Exploring technology and society with multimodal data harmonisation

Integrating text, images, sensors and social signals to understand population health, research trends, and societal dynamics.

Interdisciplinary, reproducible, and designed for practical impact.

Current focus

Digital Health
Language Systems
Social Computing
Research

Methods built for complex public questions

Work across language, health, behaviour, and knowledge systems. Each area is treated as a discrete block with clear inputs, methods, and outputs.

Area

Natural Language Processing

Developing advanced NLP techniques for text analysis, sentiment analysis, and information extraction from large-scale textual data across multiple languages and domains.

NLPDeep LearningText Analysis
Area

Data Science and Analytics

Applying machine learning and statistical methods to extract insights from complex datasets, with focus on social media data, healthcare data, and business intelligence.

Machine LearningBig DataAnalytics
Area

Text Mining

Creating innovative text mining approaches for knowledge discovery, pattern recognition, and automated information extraction from unstructured textual data.

Text MiningInformation ExtractionKnowledge Discovery
Area

Computational Social Science

Using computational methods to study social phenomena, online behaviour, and information diffusion in digital platforms and social networks.

Social MediaNetwork AnalysisBehaviour Modelling
Projects

Active work in clearly defined blocks

Research projects are presented as flat blocks of status, scope, and funding context.

ActiveP01

Chinese Fashion Aesthetics: Current Landscape, Trends, and Changes

This study examines the dynamics of Chinese fashion aesthetics through social media analysis using multimodal data, and explores how fashion trends are represented, communicated, and diffused online.

NLPSocial MediaText Mining
Funding: Funding welcome
Learn more
PlannedP02

Chronic Disease Healthcare Platform

An intelligent platform integrating multimodal data to predict chronic disease flare-ups and recommend personalised behavioural changes, and will evolve into a digital twin powered by federated learning for privacy-preserving, adaptive healthcare.

HealthcareDigital TwinPrecision Medicine
Funding: Funding welcome
Learn more
ActiveP03

Assistant for Visually Impaired

An assistive algorithm for visually impaired users that combines multi-camera vision to enhance spatial perception and object awareness and integrating vLLM for contextual understanding and optional LiDAR input for enhanced depth sensing, aiming to deliver robust, real-time assistance to improve user independence and environmental interaction.

Text MiningOpen SourceNLP
Funding: Funding welcome
Learn more