Jeremy Ting’s research while affiliated with Rutgers, The State University of New Jersey and other places

We studied the experience of loneliness as communicated by thousands of people on Twitter. Using a data set of public Twitter posts containing explicit expressions of loneliness, we qualitatively developed a categorization scheme for these expressions, showing how the context of loneliness expressed on Twitter relates to existing theories about loneliness. A quantitative analysis of the data exposed categories and patterns in communication practices around loneliness. For example, users expressing more severe, enduring loneliness are more likely to be female, and less likely to include requests for social interaction in their tweets. Further, we studied the responses to expressions of loneliness in Twitter's social settings. Deriving from the same dataset, we examined factors that correlate with the existence and type of response, showing, for example, that men were more likely to receive responses to lonely tweets, and expressions of enduring loneliness are critically less likely to receive responses. Copyright © 2014, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

With the increasing volume of location-annotated content from various social media platforms like Twitter, Instagram and Foursquare, we now have real-time access to people's daily documentation of local activities, interests and attention. In this demo paper, we present CityBeat, a real-time visualization of hyper-local social media content for cities. The main objective of CityBeat is to provide users -- with a specific focus on journalists -- with information about the city's ongoings, and alert them to unusual activities. The system collects a stream of geo-tagged photos as input, uses time series analysis and classification techniques to detect hyper-local events, and compute trends and statistics. The demo includes a visualization of this information that is designed to be installed on a large-screen in a newsroom, as an ambient display.