Discriminatory Expressions to Improve Model Comprehensibility in Short Documents

Abstract

Microblogging sites are being used as analysis avenues due to their peculiarities (promptness, short texts...). Lately, researchers have focused mainly in classification performance rather than interpretability. When the problem requires transparency, it is necessary to build interpretable pipelines, and even though, resulting models are too complex to be considered comprehensible, making it impossible for humans to understand the actual decisions. This paper presents a feature selection mechanism that is able to improve comprehensibility by using less but more meaningful features. Results show that our proposal is better and the most stable one in terms of accuracy, generalisation and comprehensibility in microblogging context.