Congratulations to members of the 2013/14 Magic Grant CityBeat, whose paper was accepted to the demo track at WWW 2014. Their paper, “CityBeat: Real-time Social Media Visualization of Hyper-local City Data,” presents City Beat, a real-time visualization of hyper-local content, including event detection and trends, for cities. Explore all of the WWW 2014 Accepted Demos!
Abstract: As an increasing volume of location-annotated content from social media platforms like Twitter, Instagram and Foursquare becomes publicly available, 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 content, including event detection and trends, for cities. As a monitoring system for a city, the main objective of CityBeat is to provide users such as city government employees and journalists with information about the city’s ongoings and alert them to unusual activities. By utilizing machine learning techniques, this system collects a stream of geotagged photos as input, detects hyper-local events and computes trends and statistics. In the current demo, the visualization of this information is designed to be installed on a large-screen in a newsroom or control center as an ambient display.