SwatCS: Combining Simple Classifiers With Estimated Accuracy
Seventh International Workshop On Semantic Evaluation
This paper is an overview of the SwatCS system submitted to SemEval-2013 Task 2A: Contextual Polarity Disambiguation. The sentiment of individual phrases within a tweet are labeled using a combination of classifiers trained on a range of lexical features. The classifiers are combined by estimating the accuracy of the classifiers on each tweet. Performance is measured when using only the provided trainng data, and separtaely when including external data.
7th International Workshop On Semantic Evaluation
June 14-15, 2013
Samuel M. Clark , '13 and Richard H. Wicentowski.
"SwatCS: Combining Simple Classifiers With Estimated Accuracy".
Seventh International Workshop On Semantic Evaluation.