7 papers · 1 filter
From Standard English to Singlish: A Retrieval-Augmented Approach for Code-Switched Creole Generation in Large Language Models
Foong Ming Lai, Yujin Tan, Han Meng +1
Code-switching in contact varieties like Singaporean English (Singlish) challenges natural language generation due to limited parallel data and rapid lexical evolution. We propose…
ConvScale: Conversational Interviews for Scale-Aligned Measurement
Peinuan Qin, Jingzhu Chen, Yitian Yang +3
Conversational interviews are commonly used to complement structured surveys by eliciting rich and contextualized responses, which are typically analyzed qualitatively. However, th…
Designing Computational Tools for Exploring Causal Relationships in Qualitative Data
Han Meng, Qiuyuan Lyu, Peinuan Qin +4
Exploring causal relationships for qualitative data analysis in HCI and social science research enables the understanding of user needs and theory building. However, current comput…
Exploring the Human-LLM Synergy in Advancing Theory-driven Qualitative Analysis
Han Meng, Yitian Yang, Wayne Fu +3
Qualitative coding is a demanding yet crucial research method in the field of Human-Computer Interaction (HCI). While recent studies have shown the capability of large language mod…
Empowering Social Service with AI: Insights from a Participatory Design Study with Practitioners
Yugin Tan, Kai Xin Soh, Renwen Zhang +4
In social service, administrative burdens and decision-making challenges often hinder practitioners from performing effective casework. Generative AI (GenAI) offers significant pot…
Deconstructing Depression Stigma: Integrating AI-driven Data Collection and Analysis with Causal Knowledge Graphs
Han Meng, Renwen Zhang, Ganyi Wang +4
Mental-illness stigma is a persistent social problem, hampering both treatment-seeking and recovery. Accordingly, there is a pressing need to understand it more clearly, but analyz…