Urban air pollution is a major health crisis causing millions of premature deaths annually, underscoring the urgent need for accurate and scalable monitoring of air quality (AQ). While low-cost sensors (LCS) offer a scalable alternative to expensive reference-grade stations, their readings are affected by drift, calibration errors, and environmental interference. To address these challenges, we introduce Veli (Reference free Variational Estimation via Latent Inference), an unsupervised Bayesian model that leverages variational inference to correct LCS readings without requiring co-location with reference stations, eliminating a major deployment barrier. Specifically, Veli constructs a disentangled representation of the LCS readings, effectively separating the true pollutant reading from the sensor noise. To build our model and address the lack of standardized benchmarks in AQ monitoring, we also introduce the Air Quality Sensor Data Repository (AQ-SDR). AQ-SDR is the largest AQ sensor benchmark to date, with readings from 23,737 LCS and reference stations across multiple regions. Veli demonstrates strong generalization across both in-distribution and out-of-distribution settings, effectively handling sensor drift and erratic sensor behavior. Appendices are available in the extended version.

This paper explores pair collaboration as a novel approach for making sense of personal data. Pair collaboration - characterized by dyadic comparison and structured roles for questioning and reasoning - has proven effective for co-constructing knowledge. However, current collaborative visualization tools primarily focus on group comparisons, overlooking the challenges of accommodating pair collaboration in the context of personal data. To address this gap, we propose a set of design rationales supporting subjective data analysis through dyadic comparison and mixed-focus collaboration styles for co-constructing personal narratives. We operationalize these principles in a tangible visualization toolkit, PAIRcolator. Our user study demonstrates that pairwise collaboration facilitated by the toolkit: 1) reveals detailed data insights that are effective for recalling personal experiences, and 2) fosters a structured, reciprocal sensemaking process for interpreting and reconstructing personal experiences beyond data insights. Our results shed light on the design rationales for, and the processes of pair sensemaking of personal data, and their effects to foster deep levels of reflection.

Digitally-supported participatory methods are often used in policy-making to develop inclusive policies by collecting and integrating citizen's opinions. However, these methods fail to capture the complexity and nuances in citizen's needs, i.e., citizens are generally unaware of other's needs, perspectives, and experiences. Consequently, policies developed with this underlying gap tend to overlook the alignment of multistakeholder perspectives, and design policies based on the optimization of high-level demographic features. In our contribution, we propose a method to enable citizens understand other's perspectives and calibrate their positions. First, we collected requirements and design principles to develop our approach by involving stakeholders and experts in policymaking in a series of workshops. Then, we conducted a crowdsourcing study with 420 participants to compare the effect of different text and images, on people's initial and final motivations and their willingness to change opinions. We observed that both influence participant's opinion change, however, the effect is more pronounced for textual modality. Finally, we discuss overarching implications of designing with empathy to mediate alignment of citizen's perspectives.

Hate speech moderation remains a challenging task for social media platforms. Human-AI collaborative systems offer the potential to combine the strengths of humans’ reliability and the scalability of machine learning to tackle this issue effectively. While methods for task handover in human-AI collaboration exist that consider the costs of incorrect predictions, insufficient attention has been paid to accurately estimating these costs. In this work, we propose a value-sensitive rejection mechanism that automatically rejects machine decisions for human moderation based on users’ value perceptions regarding machine decisions. We conduct a crowdsourced survey study with 160 participants to evaluate their perception of correct and incorrect machine decisions in the domain of hate speech detection, as well as occurrences where the system rejects making a prediction. Here, we introduce Magnitude Estimation, an unbounded scale, as the preferred method for measuring user (dis)agreement with machine decisions. Our results show that Magnitude Estimation can provide a reliable measurement of participants’ perception of machine decisions. By integrating user-perceived value into human-AI collaboration, we further show that it can guide us in 1) determining when to accept or reject machine decisions to obtain the optimal total value a model can deliver and 2) selecting better classification models as compared to the more widely used target of model accuracy.

Industrial smoke emissions pose a significant concern to human health. Prior works have shown that using Computer Vision (CV) techniques to identify smoke as visual evidence can influence the attitude of regulators and empower citizens to pursue environmental justice. However, existing datasets are not of sufficient quality nor quantity to train the robust CV models needed to support air quality advocacy. We introduce RISE, the first large-scale video dataset for Recognizing Industrial Smoke Emissions. We adopted a citizen science approach to collaborate with local community members to annotate whether a video clip has smoke emissions. Our dataset contains 12,567 clips from 19 distinct views from cameras that monitored three industrial facilities. These daytime clips span 30 days over two years, including all four seasons. We ran experiments using deep neural networks to establish a strong performance baseline and reveal smoke recognition challenges. Our survey study discussed community feedback, and our data analysis displayed opportunities for integrating citizen scientists and crowd workers into the application of Artificial Intelligence for Social Impact.

Urban air pollution has been linked to various human health concerns, including cardiopulmonary diseases. Communities who suffer from poor air quality often rely on experts to identify pollution sources due to the lack of accessible tools. Taking this into account, we developedSmell Pittsburgh, a system that enables community members to report odors and track where these odors are frequently concentrated. All smell report data are publicly accessible online. These reports are also sent to the local health department and visualized on a map along with air quality data from monitoring stations. This visualization provides a comprehensive overview of the local pollution landscape. Additionally, with these reports and air quality data, we developed a model to predict upcoming smell events and send push notifications to inform communities. We also applied regression analysis to identify statistically significant effects of push notifications on user engagement. Our evaluation of this system demonstrates that engaging residents in documenting their experiences with pollution odors can help identify local air pollution patterns and can empower communities to advocate for better air quality. All citizen-contributed smell data are publicly accessible and can be downloaded fromhttps://smellpgh.org.

We introduce the first dataset for human edits of machine-generated visual stories and explore how these collected edits may be used for the visual story post-editing task.The dataset, VIST-Edit 1 , includes 14,905 humanedited versions of 2,981 machine-generated visual stories.The stories were generated by two state-of-the-art visual storytelling models, each aligned to 5 human-edited versions.We establish baselines for the task, showing how a relatively small set of human edits can be leveraged to boost the performance of large visual storytelling models.We also discuss the weak correlation between automatic evaluation scores and human ratings, motivating the need for new automatic metrics.

Urban air pollution has been linked to various human health considerations, including cardiopulmonary diseases. Communities who suffer from poor air quality often rely on experts to identify pollution sources due to the lack of accessible tools. Taking this into account, we developed Smell Pittsburgh, a system that enables community members to report odors and track where these odors are frequently concentrated. All smell report data are publicly accessible online. These reports are also sent to the local health department and visualized on a map along with air quality data from monitoring stations. This visualization provides a comprehensive overview of the local pollution landscape. Additionally, with these reports and air quality data, we developed a model to predict upcoming smell events and send push notifications to inform communities. Our evaluation of this system demonstrates that engaging residents in documenting their experiences with pollution odors can help identify local air pollution patterns, and can empower communities to advocate for better air quality.

Developing information technology to democratize scientific knowledge and support citizen empowerment is a challenging task. In our case, a local community suffered from air pollution caused by industrial activity. The residents lacked the technological fluency to gather and curate diverse scientific data to advocate for regulatory change. We collaborated with the community in developing an air quality monitoring system which integrated heterogeneous data over a large spatial and temporal scale. The system afforded strong scientific evidence by using animated smoke images, air quality data, crowdsourced smell reports, and wind data. In our evaluation, we report patterns of sharing smoke images among stakeholders. Our survey study shows that the scientific knowledge provided by the system encourages agonistic discussions with regulators, empowers the community to support policy making, and rebalances the power relationship between stakeholders.

Real-time video streaming has been widely used in multimedia learning environments. As production of online videos is increasing exponentially, it is becoming more difficult for users to reach relevant content. In this paper, we propose SynTag, a web-based platform that enables users to label three types of tags -- Good, Question, and Disagree -- and to make comments synchronously and asynchronously with visualization of time-stamp video previews on an interactive timeline. SynTag generates real-time thumbnails by using real-time tags for presenters to receive instant feedback and for other users to retrieve presentation videos. In a pilot study, we found our users' tagging behaviors significantly different when they were in lecture events or discussion events. We envision that enabling users to apply tags in real-time will help reduce the complexity of classification of videos.