This paper identifies and validates eight core UX principles for human-AI agent interaction in the workplace using a multi-method approach.

The paper introduces PersTurnBench, a novel benchmark and evaluator for assessing personalized user conversation satisfaction at specific turns, addressing the limitation of generic response quality m…

AutoForest is an end-to-end system that automatically generates publication-ready forest plots directly from biomedical papers, streamlining the labor-intensive process of meta-analysis.

The paper introduces a Generative AI-augmented User Experience Research (UXR) methodology, operationalized through a four-stage process, to create actionable, stigma-aware design guidance for digital…

This paper demonstrates the development of a culturally grounded, AI-augmented User Experience Research Point of View (POV) for a telemedicine dementia care framework in Nigeria, providing a replicabl…

This paper presents a large-scale analysis of AI-based learning assistant (Syntea) usage in higher education using log data from 77,543 students.

This paper identifies and categorizes digital security and privacy questions asked to large language models using a dataset of user-LLM conversations, and evaluates the response quality and consistenc…

This paper analyzes large-scale human-LLM conversations to identify learning behaviors and their associated factors.

The paper proposes a structured framework, the Cognitive Accessibility UXR Playbook, that uses UXR principles and Generative AI to transform ambiguous requirements into measurable, actionable specific…

This paper investigates the impact of performance-based financial incentives on task performance in visualization studies.

This paper compares the effectiveness of classical and neural speech codecs using P.808 and P.800 DCR tests in crowdsourced and conventional evaluations. It proposes suitable screening methods for imp…

The paper develops an AI-augmented UX Research Point-of-View (PoV) framework to guide the design of digital wellbeing tools for high-stress Emergency and Public Safety Personnel (EPSP), finding that s…

This study investigated user reactions to inferred personal information from their own ChatGPT histories, finding that acceptability is governed by context-sensitive norms regarding generation, retent…

This study compares various authorship attribution methods on Japanese web reviews, finding that while BERT fine-tuning performs best, TF-IDF+LR offers superior stability and efficiency for large-scal…

This paper analyzes the shift in student adoption and accountability practices of GenAI tools in a graduate-level HCI prototyping course across three cohorts using GitHub data.

This study investigated the stability and prompt-responsiveness of AI tools in classifying the cognitive demand of math tasks, finding that few-shot prompting was a more reliable performance booster t…

The paper investigates how digital devices in U.S. prisons create privacy and security risks for incarcerated users, finding that pervasive surveillance and arbitrary policies negatively impact their…