Breaking News Detection mit Node.js - Thomas Steiner - University of Hamburg
- Lecture2Go
- Catalog
- F.6 - Mathematik, Informatik, Naturwissenschaften
- MIN-Fakultät
- Externe IT-Vorträge
Catalog
Breaking News Detection mit Node.js
We have developed an application called Wikipedia Live Monitor thatmonitors article edits on different language versions of Wikipedia—asthey happen in realtime. Wikipedia articles in different languages arehighly interlinked. For example, the English article“en:2013_Russian_meteor_event” on the topic of the February 15meteoroid that exploded over the region of Chelyabinsk Oblast, Russia,is interlinked with “ru:Падение_метеорита_на_Урале_в_2013_году”, theRussian article on the same topic. As we monitor multiple languageversions of Wikipedia in parallel, we can exploit this fact to detectconcurrent edit spikes of Wikipedia articles covering the same topics,both in only one, and in different languages. We treat such concurrentedit spikes as signals for potential breaking news events, whoseplausibility we then check with full-text cross-language searches onmultiple social networks. Unlike the reverse approach of monitoringsocial networks first, and potentially checking plausibility onWikipedia second, the approach proposed in this talk has the advantageof being less prone to false positive alerts, while being equallysensitive to true-positive events, however, at only a fraction of theprocessing cost. A live demo of our application is available online atthe URL http://wikipedia-irc.herokuapp.com/, the source code isavailable under the terms of the Apache 2.0 license athttps://github.com/tomayac/wikipedia-irc.