arXiv subjects

Qile Wang

Publications and source records attributed to Qile Wang.

5 recordsLinked to original sources

arXiv2026

Echoes in the Sky: Computational Thematic Analysis of Online Public Discourse on Bluesky Across Trump's Reelection

As political disruption intensifies online discourse, Bluesky has become an important platform for political discussion and public reaction. In this study, we examine large-scale discourse on Bluesky related to U.S. policy developments associated with the Trump administration. Using the historical retrieval API, we collected all available posts matching Trump and related keywords from 2019 to 2026, yielding 38.5 million posts. We leverage a large language model (LLM)-assisted clustering pipeline, combined with human validation, to identify 14 interpretable thematic domains in English-language posts and 19 thematic categories across 258 executive orders (EOs) signed between January 20, 2025, and May 1, 2026. Our findings identify several dominant themes in Bluesky discourse, including executive governance, political identity, and national security, as well as recurring themes in EOs, including executive task forces, border enforcement, and foreign policy. We also find substantial variation in the persistence and volatility of issue attention, accompanied by an increasing proportion of negative sentiment over time. The dataset and resources are publicly available at https://github.com/Sensify-Lab/Echoes-in-the-Sky

cs.HC↗

arXiv2026

"The explanation makes sense": An Empirical Study on LLM Performance in News Classification and its Influence on Judgment in Human-AI Collaborative Annotation

The spread of media bias is a significant concern as political discourse shapes beliefs and opinions. Addressing this challenge computationally requires improved methods for interpreting news. While large language models (LLMs) can scale classification tasks, concerns remain about their trustworthiness. To advance human-AI collaboration, we investigate the feasibility of using LLMs to classify U.S. news by political ideology and examine their effect on user decision-making. We first compared GPT models with prompt engineering to state-of-the-art supervised machine learning on a 34k public dataset. We then collected 17k news articles and tested GPT-4 predictions with brief and detailed explanations. In a between-subjects study (N=124), we evaluated how LLM-generated explanations influence human annotation, judgment, and confidence. Results show that AI assistance significantly increases confidence ($p<.001$), with detailed explanations more persuasive and more likely to alter decisions. We highlight recommendations for AI explanations through thematic analysis and provide our dataset for further research.

cs.HC↗

arXiv2026

Wisdom of the LLM Crowd: A Large Scale Benchmark of Multi-Label U.S. Election-Related Harmful Social Media Content

The spread of election misinformation and harmful political content conveys misleading narratives and poses a serious threat to democratic integrity. Detecting harmful content at early stages is essential for understanding and potentially mitigating its downstream spread. In this study, we introduce USE24-XD, a large-scale dataset of nearly 100k posts collected from X (formerly Twitter) during the 2024 U.S. presidential election cycle, enriched with spatio-temporal metadata. To substantially reduce the cost of manual annotation while enabling scalable categorization, we employ six large language models (LLMs) to systematically annotate posts across five nuanced categories: Conspiracy, Sensationalism, Hate Speech, Speculation, and Satire. We validate LLM annotations with crowdsourcing (n = 34) and benchmark them against human annotators. Inter-rater reliability analyses show comparable agreement patterns between LLMs and humans, with LLMs exhibiting higher internal consistency and achieving up to 0.90 recall on Speculation. We apply a wisdom-of-the-crowd approach across LLMs to aggregate annotations and curate a robust multi-label dataset. 60% of posts receive at least one label. We further analyze how human annotator demographics, including political ideology and affiliation, shape labeling behavior, highlighting systematic sources of subjectivity in judgments of harmful content. The USE24-XD dataset is publicly released to support future research.

cs.HC↗

arXiv2024

A Large-Scale Feasibility Study of Screen-based 3D Visualization and Augmented Reality Tools for Human Anatomy Education: Exploring Gender Perspectives in Learning Experience

Anatomy education is an indispensable part of medical training, but traditional methods face challenges like limited resources for dissection in large classes and difficulties understanding 2D anatomy in textbooks. Advanced technologies, such as 3D visualization and augmented reality (AR), are transforming anatomy learning. This paper presents two in-house solutions that use handheld tablets or screen-based AR to visualize 3D anatomy models with informative labels and in-situ visualizations of the muscle anatomy. To assess these tools, a user study of muscle anatomy education involved 236 premedical students in dyadic teams, with results showing that the tablet-based 3D visualization and screen-based AR tools led to significantly higher learning experience scores than traditional textbook. While knowledge retention didn't differ significantly, ethnographic and gender analysis showed that male students generally reported more positive learning experiences than female students. This study discusses the implications for anatomy and medical education, highlighting the potential of these innovative learning tools considering gender and team dynamics in body painting anatomy learning interventions.

cs.HC↗

arXiv2023

Immersive Virtual Reality and Robotics for Upper Extremity Rehabilitation

Stroke patients often experience upper limb impairments that restrict their mobility and daily activities. Physical therapy (PT) is the most effective method to improve impairments, but low patient adherence and participation in PT exercises pose significant challenges. To overcome these barriers, a combination of virtual reality (VR) and robotics in PT is promising. However, few systems effectively integrate VR with robotics, especially for upper limb rehabilitation. This work introduces a new virtual rehabilitation solution that combines VR with robotics and a wearable sensor to analyze elbow joint movements. The framework also enhances the capabilities of a traditional robotic device (KinArm) used for motor dysfunction assessment and rehabilitation. A pilot user study (n = 16) was conducted to evaluate the effectiveness and usability of the proposed VR framework. We used a two-way repeated measures experimental design where participants performed two tasks (Circle and Diamond) with two conditions (VR and VR KinArm). We observed no significant differences in the main effect of conditions for task completion time. However, there were significant differences in both the normalized number of mistakes and recorded elbow joint angles (captured as resistance change values from the wearable sleeve sensor) between the Circle and Diamond tasks. Additionally, we report the system usability, task load, and presence in the proposed VR framework. This system demonstrates the potential advantages of an immersive, multi-sensory approach and provides future avenues for research in developing more cost-effective, tailored, and personalized upper limb solutions for home therapy applications.

cs.HC↗