RTRGO: Enhancing the GU-MLT-LT System for Sentiment Analysis of Short Messages

@inProceedings{Günther-Tobias2014-201512, title = {RTRGO: Enhancing the GU-MLT-LT System for Sentiment Analysis of Short Messages}, abstract = {This paper describes the enhancements made to our GU-MLT-LT system (Günther and Furrer, 2013) for the SemEval-2014 re-run of the SemEval-2013 shared task on sentiment analysis in Twitter. The changes include the usage of a Twitter-specific tokenizer, additional features and sentiment lexica, feature weighting and random subspace learning. The improvements result in an increase of 4.18 F-measure points on this year’s Twitter test set, ranking 3rd. }, booktitle = {Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014) August 23-24, 2014 Dublin, Ireland}, author = {Günther, Tobias and Vancoppenolle, Jean and Johansson, Richard}, year = {2014}, ISBN = {978-1-941643-24-2}, pages = {497--502}, }