arXiv subjects

Uichin Lee

Publications and source records attributed to Uichin Lee.

9 recordsLinked to original sources

arXiv2026

Ethics Training Agents: Facilitating Group-Based Ethics Education with Role-Playing and Discussion for Ethical Reflection and Exploration

Group-based ethics training for Science, Technology, Engineering and Mathematics (STEM) students is a complex challenge, requiring substantial resources and expertise. While activity-based teaching methods, such as role-playing and discussions, are commonly employed to simulate real-world scenarios, current practices are often manual and lack integration with effective online platforms for supporting group-based ethical discussions. In this work, we propose Ethics Training Agents, a group discussion system that leverages multiple LLM participants embodying distinct ethical orientations, along with a moderator agent, to enable structured human-AI group ethical discussions for collaborative reflection. We conduct a user study with 45 undergraduate STEM students to evaluate the learning outcomes and user experience. The results show that our system supports engagement, coordination, and perspective-taking in group discussions and has a positive influence on ethical sensitivity. We also discuss practical design strategies for integrating multiple LLM agents into multi-human group settings to facilitate ethics training for STEM students.

cs.HC↗

arXiv2026

Dual Perspectives in Emotion Attribution: A Generator-Interpreter Framework for Cross-Cultural Analysis of Emotion in LLMs

Large language models (LLMs) are increasingly used in cross-cultural systems to understand and adapt to human emotions, which are shaped by cultural norms of expression and interpretation. However, prior work on emotion attribution has focused mainly on interpretation, overlooking the cultural background of emotion generators. This assumption of universality neglects variation in how emotions are expressed and perceived across nations. To address this gap, we propose a Generator-Interpreter framework that captures dual perspectives of emotion attribution by considering both expression and interpretation. We systematically evaluate six LLMs on an emotion attribution task using data from 15 countries. Our analysis reveals that performance variations depend on the emotion type and cultural context. Generator-interpreter alignment effects are present; the generator's country of origin has a stronger impact on performance. We call for culturally sensitive emotion modeling in LLM-based systems to improve robustness and fairness in emotion understanding across diverse cultural contexts.

cs.CL↗

arXiv2025

AssurAI: Experience with Constructing Korean Socio-cultural Datasets to Discover Potential Risks of Generative AI

The rapid evolution of generative AI necessitates robust safety evaluations. However, current safety datasets are predominantly English-centric, failing to capture specific risks in non-English, socio-cultural contexts such as Korean, and are often limited to the text modality. To address this gap, we introduce AssurAI, a new quality-controlled Korean multimodal dataset for evaluating the safety of generative AI. First, we define a taxonomy of 35 distinct AI risk factors, adapted from established frameworks by a multidisciplinary expert group to cover both universal harms and relevance to the Korean socio-cultural context. Second, leveraging this taxonomy, we construct and release AssurAI, a large-scale Korean multimodal dataset comprising 11,480 instances across text, image, video, and audio. Third, we apply the rigorous quality control process used to ensure data integrity, featuring a two-phase construction (i.e., expert-led seeding and crowdsourced scaling), triple independent annotation, and an iterative expert red-teaming loop. Our pilot study validates AssurAI's effectiveness in assessing the safety of recent LLMs. We release AssurAI to the public to facilitate the development of safer and more reliable generative AI systems for the Korean community.

cs.AI↗

arXiv2025

HateBuffer: Safeguarding Content Moderators' Mental Well-Being through Hate Speech Content Modification

Hate speech remains a persistent and unresolved challenge in online platforms. Content moderators, working on the front lines to review user-generated content and shield viewers from hate speech, often find themselves unprotected from the mental burden as they continuously engage with offensive language. To safeguard moderators' mental well-being, we designed HateBuffer, which anonymizes targets of hate speech, paraphrases offensive expressions into less offensive forms, and shows the original expressions when moderators opt to see them. Our user study with 80 participants consisted of a simulated hate speech moderation task set on a fictional news platform, followed by semi-structured interviews. Although participants rated the hate severity of comments lower while using HateBuffer, contrary to our expectations, they did not experience improved emotion or reduced fatigue compared with the control group. In interviews, however, participants described HateBuffer as an effective buffer against emotional contagion and the normalization of biased opinions in hate speech. Notably, HateBuffer did not compromise moderation accuracy and even contributed to a slight increase in recall. We explore possible explanations for the discrepancy between the perceived benefits of HateBuffer and its measured impact on mental well-being. We also underscore the promise of text-based content modification techniques as tools for a healthier content moderation environment.

cs.HC↗

arXiv2022

Toward Data-Driven Digital Therapeutics Analytics: Literature Review and Research Directions

With the advent of Digital Therapeutics (DTx), the development of software as a medical device (SaMD) for mobile and wearable devices has gained significant attention in recent years. Existing DTx evaluations, such as randomized clinical trials, mostly focus on verifying the effectiveness of DTx products. To acquire a deeper understanding of DTx engagement and behavioral adherence, beyond efficacy, a large amount of contextual and interaction data from mobile and wearable devices during field deployment would be required for analysis. In this work, the overall flow of the data-driven DTx analytics is reviewed to help researchers and practitioners to explore DTx datasets, to investigate contextual patterns associated with DTx usage, and to establish the (causal) relationship of DTx engagement and behavioral adherence. This review of the key components of data-driven analytics provides novel research directions in the analysis of mobile sensor and interaction datasets, which helps to iteratively improve the receptivity of existing DTx.

cs.HC↗

arXiv2022

A Systematic Survey on Android API Usage for Data-Driven Analytics with Smartphones

Recent industrial and academic research has focused on data-driven analytics with smartphones by collecting user interaction, context, and device systems data through Application Programming interfaces (APIs) and sensors. The Android OS provides various APIs to collect such mobile usage and sensor data for third-party developers. Usage Statistics API (US API) and Accessibility Service API (AS API) are representative Android APIs for collecting app usage data and are used for various research purposes as they can collect fine-grained interaction data (e.g., app usage history, user interaction type). Furthermore, other sensor APIs help to collect a user's context and device state data, along with AS/US APIs. This review investigates mobile usage and sensor data-driven research using AS/US APIs, by categorizing the research purposes and the data types. In this paper, the surveyed studies are classified as follows: five themes and 21 subthemes, and a four-layer hierarchical data classification structure. This allows us to identify a data usage trend and derive insight into data collection according to research purposes. Several limitations and future research directions of mobile usage and sensor data-driven analytics research are discussed, including the impact of changes in the Android API versions on research, the privacy and data quality issues, and the mitigation of reproducibility risks with standardized data typology.

cs.HC↗

arXiv2022

LV-Linker: Supporting Linked Exploration of Phone Usage Log Data and Screen Video Data

Prior HCI studies often analyzed smartphone app usage data for usability and user experience research purposes. App usage videos are often collected by a screen recording app in order to better analyze the app usage behaviors (e.g., app usage time, screen transition, and notification handling). However, it is difficult to analyze app usage videos along with multiple user interaction stream data. When the length of a video is long, data analysis tends to take a long time due to the volume of user interaction data. This is even more difficult for novice researchers due to a lack of data analysis experience. In this paper, we propose LV-Linker (Log and Video Linker), a visualization tool that helps researchers quickly explore the app usage log and video data by linking multiple time series log data with the video data. We conducted a preliminary user study with eight participants to evaluate the benefits of linking, by measuring task completion time, helpfulness, and subjective task workload. Our results showed that offering a linking feature significantly lowers the task completion time and task workload.

cs.HC↗

arXiv2020

K-EmoCon, a multimodal sensor dataset for continuous emotion recognition in naturalistic conversations

Recognizing emotions during social interactions has many potential applications with the popularization of low-cost mobile sensors, but a challenge remains with the lack of naturalistic affective interaction data. Most existing emotion datasets do not support studying idiosyncratic emotions arising in the wild as they were collected in constrained environments. Therefore, studying emotions in the context of social interactions requires a novel dataset, and K-EmoCon is such a multimodal dataset with comprehensive annotations of continuous emotions during naturalistic conversations. The dataset contains multimodal measurements, including audiovisual recordings, EEG, and peripheral physiological signals, acquired with off-the-shelf devices from 16 sessions of approximately 10-minute long paired debates on a social issue. Distinct from previous datasets, it includes emotion annotations from all three available perspectives: self, debate partner, and external observers. Raters annotated emotional displays at intervals of every 5 seconds while viewing the debate footage, in terms of arousal-valence and 18 additional categorical emotions. The resulting K-EmoCon is the first publicly available emotion dataset accommodating the multiperspective assessment of emotions during social interactions.

cs.HC↗

arXiv2015

Secure Personal Content Networking over Untrusted Devices

Securely sharing and managing personal content is a challenging task in multi-device environments. In this paper, we design and implement a new platform called Personal Content Networking (PCN). Our work is inspired by Content-Centric Networking (CCN) because we aim to enable access to personal content using its name instead of its location. The unique challenge of PCN is to support secure file operations such as replication, updates, and access control over distributed untrusted devices. The primary contribution of this work is the design and implementation of a secure content management platform that supports secure updates, replications, and fine-grained content-centric access control of files. Furthermore, we demonstrate its feasibility through a prototype implementation on the CCNx skeleton.

cs.CR↗