Kaggle Automated topics identification in media monitoring
About: DataScouting run a Kaggle competition inviting researchers to build multi-label classifiers for the automated annotation of media articles into topics to support the work of human annotators by suggesting a list of all topics by order of relevance or even automate the annotation process for media and / or categories that are easier to predict.
Execution: The competition run for one month in June 2014, and attracted 121 teams, 128 players and 1210 entries. Prof. Alexander D’yakonov was the winner. DataScouting presented the results of the competition at the 15th International Conference on Web Information System Engineering (WISE 2014), held in Thessaloniki, Greece, on October 12-14, 2014.