LENS 2017 - 1st ACM SIGSPATIAL International Workshop on Analytics for Local Events and News (LENS 2017)

The advances in software and hardware technologies together with the rapid urbanization process globally over the last decade have changed the ways people interact as groups, both offline (physically), and online (virtually). The growing urban population and diversity has led to more frequent social events of different types ranging from sports games and traffic congestion to ad-hoc gatherings and social protests. They may bring impacts on public safety, traffic, and business. In addition, online forums and social media have emerged as a new generator and information source for events and news. In 2016, social media outstripped TV as a news source for young people for the first time in history (according to BBC). Nevertheless, both online and offline events and news play important roles in modern societies. Consequently, identifying, forecasting, and understanding events and news has emerged as an important topic. By nature, events and news have spatial and temporal extents, suggesting that they are localized social phenomena. In fact, they have generated several challenges and research problems that are inherently spatio-temporal problems. Addressing these problems at a local scale is becoming more challenging over time due to the various sources of data, e.g., social media, traffic sensors, vehicle trajectories, and location-based check-ins, that help to address the topic. This variety in data sources bring several research challenges including dealing with large volumes, high levels of heterogeneity, and noisy user-generated data.
The workshop is intended to bring together experts from the research community and industry to exchange ideas on opportunities, challenges and cutting-edge techniques for local events and news analytics.
We invite submissions of both full research papers that present novel and original research results and short position papers that discuss challenges and opportunities. Topics of interest include, but not limited to, the following:
Urban event detection and prediction on mobility and transportation data.
Detecting local environmental events such as disasters and environmental changes.
Online event monitoring and local trend analysis.
Spatio-temporal correlation analysis of events/news.
Location-based news detection and analysis.
Social unrest prediction from social media.
Event chain analysis and event graphs.
Spatio-temporal event diffusion models.
Fusion of multiple data sources to analyze local events.