April Wang

Last Name

Wang

First Name

April

ORCID

0000-0001-8724-4662

Organisational unit

09820 - Wang, April Yi / Wang, April Yi

Show all metadata

Search Results

Publications 1 - 10 of 14

Do It For Me vs. Do It With Me: Investigating User Perceptions of Different Paradigms of Automation in Copilots for Feature-Rich Software
Khurana, Anjali; Su, Xiaotian; Wang, April; et al. (2025)
CHI '25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
Large Language Model (LLM)-based in-application assistants, or copilots, can automate software tasks, but users often prefer learning by doing, raising questions about the optimal level of automation for an effective user experience. We investigated two automation paradigms by designing and implementing a fully automated copilot (AutoCopilot) and a semi-automated copilot (GuidedCopilot) that automates trivial steps while offering step-by-step visual guidance. In a user study (N=20) across data analysis and visual design tasks, GuidedCopilot outperformed AutoCopilot in user control, software utility, and learnability, especially for exploratory and creative tasks, while AutoCopilot saved time for simpler visual tasks. A follow-up design exploration (N=10) enhanced GuidedCopilot with task-and state-aware features, including in-context preview clips and adaptive instructions. Our findings highlight the critical role of user control and tailored guidance in designing the next generation of copilots that enhance productivity, support diverse skill levels, and foster deeper software engagement.
Don't Step on My Toes: Resolving Editing Conflicts in Real-Time Collaboration in Computational Notebooks
Wang, April; Wu, Zihan; Brooks, Christopher; et al. (2024)
IDE '24: Proceedings of the 1st ACM/IEEE Workshop on Integrated Development Environments
Real-time collaborative editing in computational notebooks can improve the efficiency of teamwork for data scientists. However, working together through synchronous editing of notebooks introduces new challenges. Data scientists may inadvertently interfere with each others' work by altering the shared codebase and runtime state if they do not set up a social protocol for working together and monitoring their collaborators' progress. In this paper, we propose a real-time collaborative editing model for resolving conflict edits in computational notebooks that introduces three levels of edit protection to help collaborators avoid introducing errors to both the program source code and changes to the runtime state.
CompetiLearn: A Retrieval-Augmented System for Complementing Learnersourcing and AI for Data Science Learners
Wang, Junling; Wang, April (2025)
Proceedings of Learnersourcing: Student-generated Content @ Scale (Learning @ Scale 2024)
Recent advancements in Large Language Model (LLM)-based intelligent support systems like ChatGPT have been trained on a vast amount of data available on the internet, including learner-generated content that is publicly accessible online. While these tools can generate high-quality responses to learners’ queries, they may inadvertently discourage interaction within the online learner community by providing direct answers instead of fostering discussion among learners in forums. Rather than replacing the learner community, how can AI systems foster its development? In this paper, we studied a data science learning community, Kaggle, and explored how AI models like Retrieval-Augmented Generation can complement learner sourcing with AI. We designed a Jupyter note-book extension, CompetiLearn, which generates responses to learners’ questions about a particular competition. These responses can be traced back to other learners’ sharing of high-quality analysis notebooks from the Kaggle platform. We propose to evaluate this approach through a comparative study, examining how learners perceive the quality, relevance, and trustworthiness of the gener ated content. Additionally, we will collect feedback on how learners perceive that this approach can help them engage with the broader data science learning community.
DBox: Scaffolding Algorithmic Programming Learning through Learner-LLM Co-Decomposition
Ma, Shuai; Wang, Junling; Zhang, Yuanhao; et al. (2025)
CHI '25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
Decomposition is a fundamental skill in algorithmic programming, requiring learners to break down complex problems into smaller, manageable parts. However, current self-study methods, such as browsing reference solutions or using LLM assistants, often provide excessive or generic assistance that misaligns with learners’ decomposition strategies, hindering independent problem-solving and critical thinking. To address this, we introduce Decomposition Box (DBox), an interactive LLM-based system that scaffolds and adapts to learners’ personalized construction of a step tree through a “learner-LLM co-decomposition” approach, providing tailored support at an appropriate level. A within-subjects study (N=24) found that compared to the baseline, DBox significantly improved learning gains, cognitive engagement, and critical thinking. Learners also reported a stronger sense of achievement and found the assistance appropriate and helpful for learning. Additionally, we examined DBox’s impact on cognitive load, identified usage patterns, and analyzed learners’ strategies for managing system errors. We conclude with design implications for future AI-powered tools to better support algorithmic programming education.
Emotionally Aware Moderation: The Potential of Emotion Monitoring in Shaping Healthier Social Media Conversations
Su , Xiaotian; Zierau , Naim; Kim , Soomin; et al. (2025)
Proceedings of the ACM on Human-Computer Interaction
Social media platforms increasingly employ proactive moderation techniques, such as detecting and curbing toxic and uncivil comments, to prevent the spread of harmful content. Despite these efforts, such approaches are often criticized for creating a climate of censorship and failing to address the underlying causes of uncivil behavior. Our work makes both theoretical and practical contributions by proposing and evaluating two types of emotion monitoring dashboards to enhance users’ emotional awareness and mitigate hate speech. In a study involving 211 participants, we evaluate the effects of the two mechanisms on user commenting behavior and emotional experiences. The results reveal that these interventions effectively increase users’ awareness of their emotional states and reduce hate speech. However, our findings also indicate potential unintended effects, including increased expression of negative emotions (Angry, Fear, and Sad) when discussing sensitive issues. These insights provide a basis for further research on integrating proactive emotion regulation tools into social media platforms to foster healthier digital interactions.
Can GPT4 Generate Effective Feedback on Code Readability?
Su, Xiaotian; Song, Yajie; Messer, Marcus; et al. (2025)
ITiCSE 2025: Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education
Effective feedback is often timely and consistent but, with large cohorts, this is not always achievable. This study explored the potential of GPT4 to generate feedback on code readability for students enrolled in a CS1 Java course. We developed rubrics based on three readability criteria: naming, commenting, and formatting. We defined feedback criteria and incorporated them into GPT4 prompts to guide feedback generation. Results were mixed: while some feedback messages closely aligned with the rubrics, offering valuable insights, others fell short in providing corrective guidance. This highlights the potential and limitations of using LLMs to generate feedback on code readability. Future research could refine these methods to improve feedback consistency and quality.
Merlin: A Markup Language for Algorithm Animations
Wang, Shu; Wang, April (2025)
Towards Dialogic and On-Demand Metaphors for Interdisciplinary Reading
Yarmand, Matin; Reed, Courtney N.; Tandon, Udayan; et al. (2025)
CHI '25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
The interdisciplinary field of Human-Computer Interaction (HCI) thrives on productive engagement with different domains, yet this engagement often breaks due to idiosyncratic writing styles and unfamiliar concepts. Inspired by the dialogic model of abstract metaphors, as well as the potential of Large Language Models (LLMs) to produce on-demand support, we investigate the use of metaphors to facilitate engagement between Science and Technology Studies (STS) and System HCI. Our reflective-style survey with early-career HCI researchers (N=48) reported that limited prior exposure to STS research can hinder perceived openness of the work, and ultimately interest in reading. The survey also revealed that metaphors enhance likelihood to continue reading STS papers, and alternative perspectives can build critical thinking skills to mitigate potential risks of LLM-generated metaphors. We lastly offer a specified model of metaphor exchange (within this generative context) that incorporates alternative perspectives to construct shared understanding in interdisciplinary engagement.
datAR: A Situated Learning Approach for Data Literacy Through Everyday Objects
Lopez, Lilian; Xiong, Zeyu; Chau, Kiara; et al. (2025)
ITiCSE 2025: Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education
Data literacy, the ability to work with data, is essential for the younger generation. However, high school instructors often struggle to engage students from diverse backgrounds with abstract concepts that may not seem immediately tangible to them. This paper introduces datAR, an augmented reality application grounded in situated learning theory that integrates data into everyday objects. The tablet-based application uses tangible analysis blocks to help students explore and interact with data. We present a case study for the use of datAR in a local high school, where 15 students with little to no prior data science experience were introduced to data literacy through the analysis of nutrition information in familiar snacks. Our findings show that, despite students struggling to recognize the relevance of the learned concepts for their daily lives, datAR helped them develop data science skills through hands-on interaction with familiar objects.
From Workbook to Notebook: Collaborative Data Story Authoring with Spreadsheet
Xiong, Zeyu; Masoudi, Behnood; Schmit, Catherine; et al. (2025)

Publications 1 - 10 of 14

April Wang

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results