Brent Hecht

Jing Ma, Mengting Wan, Longqi Yang et al.

Hypergraphs provide an effective abstraction for modeling multi-way group interactions among nodes, where each hyperedge can connect any number of nodes. Different from most existing studies which leverage statistical dependencies, we study hypergraphs from the perspective of causality. Specifically, in this paper, we focus on the problem of individual treatment effect (ITE) estimation on hypergraphs, aiming to estimate how much an intervention (e.g., wearing face covering) would causally affect an outcome (e.g., COVID-19 infection) of each individual node. Existing works on ITE estimation either assume that the outcome on one individual should not be influenced by the treatment assignments on other individuals (i.e., no interference), or assume the interference only exists between pairs of connected individuals in an ordinary graph. We argue that these assumptions can be unrealistic on real-world hypergraphs, where higher-order interference can affect the ultimate ITE estimations due to the presence of group interactions. In this work, we investigate high-order interference modeling, and propose a new causality learning framework powered by hypergraph neural networks. Extensive experiments on real-world hypergraphs verify the superiority of our framework over existing baselines.

Ying-Chun Lin, Jennifer Neville, Jack W. Stokes et al.

Accurate and interpretable user satisfaction estimation (USE) is critical for understanding, evaluating, and continuously improving conversational systems. Users express their satisfaction or dissatisfaction with diverse conversational patterns in both general-purpose (ChatGPT and Bing Copilot) and task-oriented (customer service chatbot) conversational systems. Existing approaches based on featurized ML models or text embeddings fall short in extracting generalizable patterns and are hard to interpret. In this work, we show that LLMs can extract interpretable signals of user satisfaction from their natural language utterances more effectively than embedding-based approaches. Moreover, an LLM can be tailored for USE via an iterative prompting framework using supervision from labeled examples. The resulting method, Supervised Prompting for User satisfaction Rubrics (SPUR), not only has higher accuracy but is more interpretable as it scores user satisfaction via learned rubrics with a detailed breakdown.

Longqi Yang, Sonia Jaffe, David Holtz et al.

The COVID-19 pandemic has had a wide-ranging impact on information workers such as higher stress levels, increased workloads, new workstreams, and more caregiving responsibilities during lockdown. COVID-19 also caused the overwhelming majority of information workers to rapidly shift to working from home (WFH). The central question this work addresses is: can we isolate the effects of WFH on information workers' collaboration activities from all other factors, especially the other effects of COVID-19? This is important because in the future, WFH will likely to be more common than it was prior to the pandemic. We use difference-in-differences (DiD), a causal identification strategy commonly used in the social sciences, to control for unobserved confounding factors and estimate the causal effect of WFH. Our analysis relies on measuring the difference in changes between those who WFH prior to COVID-19 and those who did not. Our preliminary results suggest that on average, people spent more time on collaboration in April (Post WFH mandate) than in February (Pre WFH mandate), but this is primarily due to factors other than WFH, such as lockdowns during the pandemic. The change attributable to WFH specifically is in the opposite direction: less time on collaboration and more focus time. This reversal shows the importance of using causal inference: a simple analysis would have resulted in the wrong conclusion. We further find that the effect of WFH is moderated by individual remote collaboration experience prior to WFH. Meanwhile, the medium for collaboration has also shifted due to WFH: instant messages were used more, whereas scheduled meetings were used less. We discuss design implications -- how future WFH may affect focused work, collaborative work, and creative work.

Runsheng Xu, Shibo Zhang, Yue Zhao et al.

Recent research has found that navigation systems usually assume that all roads are equally safe, directing drivers to dangerous routes, which led to catastrophic consequences. To address this problem, this paper aims to begin the process of adding road safety awareness to navigation systems. To do so, we first created a definition for road safety that navigation systems can easily understand by adapting well-established safety standards from transportation studies. Based on this road safety definition, we then developed a machine learning-based road safety classifier that predicts the safety level for road segments using a diverse feature set constructed only from large-scale publicly available geographic data. Evaluations in four different countries show that our road safety classifier achieves satisfactory performance. Finally, we discuss the factors to consider when extending our road safety classifier to other regions and potential new safety designs enabled by our road safety predictions.

Nicholas Vincent, Brent Hecht

A growing body of work has highlighted the important role that Wikipedia's volunteer-created content plays in helping search engines achieve their core goal of addressing the information needs of millions of people. In this paper, we report the results of an investigation into the incidence of Wikipedia links in search engine results pages (SERPs). Our results extend prior work by considering three U.S. search engines, simulating both mobile and desktop devices, and using a spatial analysis approach designed to study modern SERPs that are no longer just "ten blue links". We find that Wikipedia links are extremely common in important search contexts, appearing in 67-84% of all SERPs for common and trending queries, but less often for medical queries. Furthermore, we observe that Wikipedia links often appear in "Knowledge Panel" SERP elements and are in positions visible to users without scrolling, although Wikipedia appears less in prominent positions on mobile devices. Our findings reinforce the complementary notions that (1) Wikipedia content and research has major impact outside of the Wikipedia domain and (2) powerful technologies like search engines are highly reliant on free content created by volunteers.

Isaac Johnson, Allen Yilun Lin, Toby Jia-Jun Li et al.

Wikipedia articles about places, OpenStreetMap features, and other forms of peer-produced content have become critical sources of geographic knowledge for humans and intelligent technologies. In this paper, we explore the effectiveness of the peer production model across the rural/urban divide, a divide that has been shown to be an important factor in many online social systems. We find that in both Wikipedia and OpenStreetMap, peer-produced content about rural areas is of systematically lower quality, is less likely to have been produced by contributors who focus on the local area, and is more likely to have been generated by automated software agents (i.e. bots). We then codify the systemic challenges inherent to characterizing rural phenomena through peer production and discuss potential solutions.

B. Hecht, D. Gergle

This study explores language's fragmenting effect on user-generated content by examining the diversity of knowledge representations across 25 different Wikipedia language editions. This diversity is measured at two levels: the concepts that are included in each edition and the ways in which these concepts are described. We demonstrate that the diversity present is greater than has been presumed in the literature and has a significant influence on applications that use Wikipedia as a source of world knowledge. We close by explicating how knowledge diversity can be beneficially leveraged to create "culturally-aware applications" and "hyperlingual applications".

Ashley Colley, Jacob Thebault-Spieker, Allen Yilun Lin et al.

The widespread popularity of Pokémon GO presents the first opportunity to observe the geographic effects of location-based gaming at scale. This paper reports the results of a mixed methods study of the geography of Pokémon GO that includes a five-country field survey of 375 Pokémon GO players and a large scale geostatistical analysis of game elements. Focusing on the key geographic themes of places and movement, we find that the design of Pokémon GO reinforces existing geographically-linked biases (e.g. the game advantages urban areas and neighborhoods with smaller minority populations), that Pokémon GO may have instigated a relatively rare large-scale shift in global human mobility patterns, and that Pokémon GO has geographically-linked safety risks, but not those typically emphasized by the media. Our results point to geographic design implications for future systems in this space such as a means through which the geographic biases present in Pokémon GO may be counteracted.