Search for: All records

Recent advances in Large Language Models (LLMs) show the potential to significantly augment or even replace complex human writing activities. However, for complex tasks where people need to make decisions as well as write a justification, the trade offs between making work efficient and hindering decisions remain unclear. In this paper, we explore this question in the context of designing intelligent scaffolding for writing meta-reviews for an academic peer review process. We prototyped a system called MetaWriter'' trained on five years of open peer review data to support meta-reviewing. The system highlights common topics in the original peer reviews, extracts key points by each reviewer, and on request, provides a preliminary draft of a meta-review that can be further edited. To understand how novice and experienced meta-reviewers use MetaWriter, we conducted a within-subject study with 32 participants. Each participant wrote meta-reviews for two papers: one with and one without MetaWriter. We found that MetaWriter significantly expedited the authoring process and improved the coverage of meta-reviews, as rated by experts, compared to the baseline. While participants recognized the efficiency benefits, they raised concerns around trust, over-reliance, and agency. We also interviewed six paper authors to understand their opinions of using machine intelligence to support the peer review process and reported critical reflections. We discuss implications for future interactive AI writing tools to support complex synthesis work. 

Traditional design galleries enable users to search for examples based on surface attributes (e.g., color or style), and largely obscure underlying principles (e.g., hierarchy or readability). We conducted three studies to explore how galleries could be constructed to help novices learn key design principles. Study 1 revealed that novices gain perspective by observing how designs evolve throughout a process. Study 2 found that novices are better at identifying design issues when viewing iterations that show improvements for just one principle at a time, rather than multiple. Building on these insights, we created ProcessGallery, a tool that enables users to browse contrasting pairs of early-and-late iterations of designs that highlight key improvements organized by design principles. In Study 3, a within-subjects experiment, sixteen participants iterated on a seed design after viewing examples in ProcessGallery versus a traditional gallery. Using ProcessGallery, participants found more appropriate examples, assessed designs better, and preferred ProcessGallery for learning compared to a traditional gallery. 

How does presenting comments in a news article affect the ways that readers engage with and retain information about news? This paper presents results from a controlled experiment investigating effects related to different strategies for promoting discussion at news websites (N=336 participants). The strategies include highlighting specific comments about a data visualization, providing prompts with the comments, and annotating prompts on the visualization. By comparison to a simple list of comments (baseline), our analysis found that annotations contributed to higher levels of participant engagement in the discussion, yet lower levels of knowledge retention related to the article. These findings raise new considerations about whether and how to integrate discussion content into news and points toward future content moderation systems that assist in representing and eliciting discussion at news websites.