SNOW 2014 Data Challenge: Assessing the Performance of News Topic Detection Methods in Social Media
Symeon Papadopoulos, David P. A. Corney, Luca Maria Aiello · 2014
The SNOW 2014 Data Challenge aimed at creating a public benchmark and evaluation resource for the problem of topic detection in streams of social content. In particular, given a set of tweets spanning a time interval of in-terest, the Challenge required the extraction of the most significant news topics in short timeslots within the selected interval. Here, we provide details with respect to the Chal-lenge definition, the data collection and eval-uation process, and the results achieved by the 11 teams that participated in it, along with a concise retrospective analysis of the main con-clusions and arising issues. 1