Designing Computational Tools for Exploring Causal Relationships in Qualitative Data
Department of Computer Science, National University of Singapore（国立新加坡大学计算机科学系）；Wee Kim Wee School of Communication and Information, Nanyang Technological University（南洋理工大学Wee Kim Wee通讯与信息学院）；Dept of Computer Science, National Yang Ming Chiao Tung University（阳明交通大学计算机科学系）
Han Meng, Qiuyuan Lyu, Peinuan Qin, Yitian Yang, Renwen Zhang, Wen-Chieh Lin, Yi-Chieh Lee
备注：
19 pages, 5 figures, conditionally accepted by CHI26
Exploring causal relationships for qualitative data analysis in HCI and social science research enables the understanding of user needs and theory building. However, current computational tools primarily characterize and categorize qualitative data; the few systems that analyze causal relationships either inadequately consider context, lack credibility, or produce overly complex outputs. We first conducted a formative study with 15 participants interested in using computational tools for exploring causal relationships in qualitative data to understand their needs and derive design guidelines. Based on these findings, we designed and implemented QualCausal, a system that extracts and illustrates causal relationships through interactive causal network construction and multi-view visualization. A feedback study (n = 15) revealed that participants valued our system for reducing the analytical burden and providing cognitive scaffolding, yet navigated how such systems fit within their established research paradigms, practices, and habits. We discuss broader implications for designing computational tools that support qualitative data analysis.
Exploring the Human-LLM Synergy in Advancing Theory-driven Qualitative Analysis
Department of Computer Science, National University of Singapore（计算机科学系，国立新加坡大学）；Amazon Research, Amazon.com Inc（亚马逊研究，亚马逊公司）；Department of Social Work, National University of Singapore（社会工作系，国立新加坡大学）
Designing Harvesting Tools for Olive Trees: Methodological Reflections on Exploring and Incorporating Plant Perspectives in the Early Stages of Design Process
Exploring Multidimensional Checkworthiness: Designing AI-assisted Claim Prioritization for Human Fact-checkers
School of Information, University of Texas at Austin（德克萨斯大学奥斯汀分校信息学院）；Institute of Applied Computer Science, Łódź University of Technology（罗兹理工大学应用计算机科学研究所）
Designing for Interconnected Islamic Learning: A Qualitative Study of Muslim Women's Experiences with Qur'an, Hadith, and Seerah Apps
University of Technology Sydney（悉尼科技大学）；ZNRF University of Management Sciences（ZNRF管理科学大学）；Greentech Apps Foundation（绿科技应用基金会）；Queen Mary University of London（伦敦大学玛丽女王学院）
From Fake Perfects to Conversational Imperfects: Exploring Image-Generative AI as a Boundary Object for Participatory Design of Public Spaces
College of Computing and Information Science, Cornell University（康奈尔大学计算与信息科学学院）；University of Southern California（南加州大学）；College of Agriculture and Life Sciences, Cornell University（康奈尔大学农业与生命科学学院）；Studio-MLA
Data Comets: Designing a Visualization Tool for Analyzing Autonomous Aerial Vehicle Logs with Grounded Evaluation
自主无人驾驶飞行器是硬件、软件和人工输入的复杂系统。理解这种复杂性是其开发和操作的关键。信息可视化已经存在，用于探索飞行日志，但全面的分析目前需要几个不同的自定义工具。这项设计研究有助于解决自主无人机开发人员和操作人员面临的痛点。我们的贡献：一个螺旋式开发过程模型，用于地面评估可视化开发，重点是逐步扩大目标用户参与和细化用户目标;作为开发已部署和采用的可视化系统的一部分，演示该模型;为开发人员和运营商进行自主无人驾驶航空器日志飞行后分析提供数据和任务抽象; DATA COMETS的设计和实现，一个开源和基于Web的交互式可视化工具，用于飞行后日志分析，包括时间，地理空间和多变量数据;以及可视化系统的总结性评估结果和我们基于野外使用的抽象。这篇论文的免费副本和源代码可以在www.example.com上获得
