arXiv subjects

Tianying Chen

Publications and source records attributed to Tianying Chen.

3 recordsLinked to original sources

arXiv2024

Selenite: Scaffolding Online Sensemaking with Comprehensive Overviews Elicited from Large Language Models

Sensemaking in unfamiliar domains can be challenging, demanding considerable user effort to compare different options with respect to various criteria. Prior research and our formative study found that people would benefit from reading an overview of an information space upfront, including the criteria others previously found useful. However, existing sensemaking tools struggle with the "cold-start" problem -- it not only requires significant input from previous users to generate and share these overviews, but such overviews may also turn out to be biased and incomplete. In this work, we introduce a novel system, Selenite, which leverages Large Language Models (LLMs) as reasoning machines and knowledge retrievers to automatically produce a comprehensive overview of options and criteria to jumpstart users' sensemaking processes. Subsequently, Selenite also adapts as people use it, helping users find, read, and navigate unfamiliar information in a systematic yet personalized manner. Through three studies, we found that Selenite produced accurate and high-quality overviews reliably, significantly accelerated users' information processing, and effectively improved their overall comprehension and sensemaking experience.

cs.HC↗

arXiv2023

Assessing the Quality of Multiple-Choice Questions Using GPT-4 and Rule-Based Methods

Multiple-choice questions with item-writing flaws can negatively impact student learning and skew analytics. These flaws are often present in student-generated questions, making it difficult to assess their quality and suitability for classroom usage. Existing methods for evaluating multiple-choice questions often focus on machine readability metrics, without considering their intended use within course materials and their pedagogical implications. In this study, we compared the performance of a rule-based method we developed to a machine-learning based method utilizing GPT-4 for the task of automatically assessing multiple-choice questions based on 19 common item-writing flaws. By analyzing 200 student-generated questions from four different subject areas, we found that the rule-based method correctly detected 91% of the flaws identified by human annotators, as compared to 79% by GPT-4. We demonstrated the effectiveness of the two methods in identifying common item-writing flaws present in the student-generated questions across different subject areas. The rule-based method can accurately and efficiently evaluate multiple-choice questions from multiple domains, outperforming GPT-4 and going beyond existing metrics that do not account for the educational use of such questions. Finally, we discuss the potential for using these automated methods to improve the quality of questions based on the identified flaws.

cs.CL↗

arXiv2022

Auggie: Encouraging Effortful Communication through Handcrafted Digital Experiences

Digital communication is often brisk and automated. From auto-completed messages to "likes," research has shown that such lightweight interactions can affect perceptions of authenticity and closeness. On the other hand, effort in relationships can forge emotional bonds by conveying a sense of caring and is essential in building and maintaining relationships. To explore effortful communication, we designed and evaluated Auggie, an iOS app that encourages partners to create digitally handcrafted Augmented Reality (AR) experiences for each other. Auggie is centered around crafting a 3D character with photos, animated movements, drawings, and audio for someone else. We conducted a two-week-long field study with 30 participants (15 pairs), who used Auggie with their partners remotely. Our qualitative findings show that Auggie participants engaged in meaningful effort through the handcrafting process, and felt closer to their partners, although the tool may not be appropriate in all situations. We discuss design implications and future directions for systems that encourage effortful communication.

cs.HC↗