Background Eliminating disparities in the burden of COVID-19 requires equitable access to control measures across socio-economic groups. Limited research on socio-economic differences in mobility hampers our ability to understand whether inequalities in social distancing are occurring during the SARS-CoV-2 pandemic. Objective We aimed to assess how mobility patterns have varied across the United States during the COVID-19 pandemic and to identify associations with socioeconomic factors of populations. Methods We used anonymized mobility data from tens of millions of devices to measure the speed and depth of social distancing at the county level in the United States between February and May 2020, the period during which social distancing was widespread in this country. Using linear mixed models, we assessed the associations between social distancing and socioeconomic variables, including the proportion of people in the population below the poverty level, the proportion of Black people, the proportion of essential workers, and the population density. Results We found that the speed, depth, and duration of social distancing in the United States are heterogeneous. We particularly show that social distancing is slower and less intense in counties with higher proportions of people below the poverty level and essential workers; in contrast, we show that social distancing is intensely adopted in counties with higher population densities and larger Black populations. Conclusions Socioeconomic inequalities appear to be associated with the levels of adoption of social distancing, potentially resulting in wide-ranging differences in the impact of the COVID-19 pandemic in communities across the United States. These inequalities are likely to amplify existing health disparities and must be addressed to ensure the success of ongoing pandemic mitigation efforts.

In this work we address the development of a smart personal assistant that is capable of anticipating a user's information needs based on a novel type of context: the person's activity inferred from her check-in records on a location-based social network. Our main contribution is a method that translates a check-in activity into an information need, which is in turn addressed with an appropriate information card. This task is challenging because of the large number of possible activities and related information needs, which need to be addressed in a mobile dashboard that is limited in size. Our approach considers each possible activity that might follow after the last (and already finished) activity, and selects the top information cards such that they maximize the likelihood of satisfying the user's information needs for all possible future scenarios. The proposed models also incorporate knowledge about the temporal dynamics of information needs. Using a combination of historical check-in data and manual assessments collected via crowdsourcing, we show experimentally the effectiveness of our approach.

We address the problem of extracting structured representations of economic events from a large corpus of news articles, using a combination of natural language processing and machine learning techniques. The developed techniques allow for semi-automatic population of a financial knowledge base, which, in turn, may be used to support a range of data mining and exploration tasks. The key challenge we face in this domain is that the same event is often reported multiple times, with varying correctness of details. We address this challenge by first collecting all information pertinent to a given event from the entire corpus, then considering all possible representations of the event, and finally, using a supervised learning method, to rank these representations by the associated confidence scores. A main innovative element of our approach is that it jointly extracts and stores all attributes of the event as a single representation (quintuple). Using a purpose-built test set we demonstrate that our supervised learning approach can achieve 25% improvement in F1-score over baseline methods that consider the earliest, the latest or the most frequent reporting of the event.

No abstract