Local governments around the world are making consequential decisions on behalf of their constituents, and these constituents are responding with requests, advice, and assessments of their officials at public meetings. So many small meetings cannot be covered by traditional newsrooms at scale. We propose PublicSpeak, a probabilistic framework which can utilize meeting structure, domain knowledge, and linguistic information to discover public remarks in local government meetings. We then use our approach to inspect the issues raised by constituents in 7 cities across the United States. We evaluate our approach on a novel dataset of local government meetings and find that PublicSpeak improves over state-of-the-art by 10% on average, and by up to 40%.

People are increasingly avoiding the news in a phenomenon termed news avoidance. Prior work has found that many people are not following political news, with the median American consuming zero articles per year from traditional news outlets. This behavior has troubling implications, as a well-informed public is typically considered essential to a functioning democracy. However, it is possible that people are accidentally picking up political information through entertainment or "soft news" outlets. The subject of this paper is People Magazine, a soft news outlet selected for its popularity (with an average of 187.1 million monthly visits). To understand how political news is covered by entertainment and soft news outlets, we make the following contributions: (1) we propose two potential and complementary frameworks for differentiating hard news content from soft news content; (2) we collect a large dataset of articles published on People Magazine's website; (3) we apply our frameworks to this dataset and contribute an analysis of the political content offered by a soft news outlet; (4) we evaluate our framework on two additional platforms. Together, these contributions additively result in the first exploration of the political content of individual news stories - all prior work has labeled entire outlets as hard or soft. As people increasingly avoid outlets with hard news, our work shows that they may still encounter political information through soft news outlets, a finding that has critical implications for political communication.

The everyday consumption of household goods is a significant source of environmental pollution. The increase of online shopping affords an opportunity to provide consumers with actionable feedback on the social and environmental impact of potential purchases, at the exact moment when it is relevant. Unfortunately, consumers are inundated with ambiguous sustainability information. For example, greenwashing can make it difficult to identify environmentally friendly products. The highest-quality options, such as Life Cycle Assessment (LCA) scores or tailored impact certificates (e.g., environmentally friendly tags), designed for assessing the environmental impact of consumption, are ineffective in the setting of online shopping. They are simply too costly to provide a feasible solution when scaled up, and often rely on data from self-interested market players. We contribute an analysis of this online environment, exploring how the dynamic between sellers and consumers surfaces claims and concerns regarding sustainable consumption. In order to better provide information to consumers, we propose a machine learning method that can discover signals of sustainability from these interactions. Our method, SustainableSignals, is a first step in scaling up the provision of sustainability cues to online consumers.

Cyberbullying is a serious threat to both the short and long-term well-being of social media users. Addressing this problem in online environments demands the ability to automatically detect cyberbullying and to identify the roles that participants assume in social interactions. As cyberbullying occurs within online communities, it is also vital to understand the group dynamics that support bullying behavior. To this end, we propose a socio-linguistic model which jointly detects cyberbullying content in messages, discovers latent text categories, identifies participant roles and exploits social interactions. While our method makes use of content that is labeled as bullying, it does not require category, role or relationship labels. Furthermore, as bullying labels are often subjective, noisy and inconsistent, an important contribution of our paper is effective methods for leveraging inconsistent labels. Rather than discard inconsistent labels, we evaluate different methods for learning from them, demonstrating that incorporating uncertainty allows for better generalization. Our proposed socio-linguistic model achieves an 18% improvement over state-of-the-art methods.

Severe environmental events have extreme effects on all segments of society, including criminal activity. Extreme weather events, such as tropical storms, fires, and floods create instability in communities, and can be exploited by criminal organizations. Here we investigate the potential impact of catastrophic storms on the criminal activity of human trafficking. We propose three theories of how these catastrophic storms might impact trafficking and provide evidence for each. Researching human trafficking is made difficult by its illicit nature and the obscurity of high-quality data. Here, we analyze online advertisements for services which can be collected at scale and provide insights into traffickers' behavior. To successfully combine relevant heterogenous sources of information, as well as spatial and temporal structure, we propose a collective, probabilistic approach. We implement this approach with Probabilistic Soft Logic, a probabilistic programming framework which can flexibly model relational structure and for which inference of future locations is highly efficient. Furthermore, this framework can be used to model hidden structure, such as latent links between locations. Our proposed approach can model and predict how traffickers move. In addition, we propose a model which learns connections between locations. This model is then adapted to have knowledge of environmental events, and we demonstrate that incorporating knowledge of environmental events can improve prediction of future locations. While we have validated our models on the impact of severe weather on human trafficking, we believe our models can be generalized to a variety of other settings in which environmental events impact human behavior.

Finding sustainable products and evaluating their claims is a significant barrier facing sustainability-minded customers. Tools that reduce both these burdens are likely to boost the sale of sustainable products. However, it is difficult to determine the sustainability characteristics of these products --- there are a variety of certifications and definitions of sustainability, and quality labeling requires input from domain experts. In this paper, we propose a flexible probabilistic framework that uses domain knowledge to identify sustainable products and customers, and uses these labels to predict customer purchases. We evaluate our approach on grocery items from the Amazon catalog. Our proposed approach outperforms established recommender system models in predicting future purchases while jointly inferring sustainability scores for customers and products.

Reducing household energy usage is a priority for improving the resiliency and stability of the power grid and decreasing the negative impact of energy consumption on the environment and public health.Relevant and timely feedback about the power consumption of specific appliances can help household residents to reduce their energy demand. Given only a total energy reading, such as that collected from a residential meter, energy disaggregation strives to discover the consumption of individual appliances. Existing disaggregation algorithms are computationally inefficient and rely heavily on high-resolution ground truth data. We introduce a probabilistic framework which infers the energy consumption of individual appliances using a hinge-loss Markov random field (HL-MRF), which admits highly scalable inference. To further enhance efficiency, we introduce a temporal representation which leverages state duration. We also explore how contextual information impacts solution quality with low-resolution data. Our framework is flexible in its ability to incorporate additional constraints; by constraining appliance usage with context and duration we can better disambiguate appliances with similar energy consumption profiles. We demonstrate the effectiveness of our framework on two public real-world datasets, reducing the error relative to a previous state-of-the-art method by as much as 50%.