DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs

TL;DR

This paper presents a deep learning approach for stance detection in tweets using combined character and word-level CNN models, enhanced by data augmentation, achieving competitive classification performance.

Contribution

Introduces a hybrid CNN-based system with data augmentation for stance detection in tweets, improving robustness and performance.

Findings

Achieved macro-average F1-score of 0.635

Combined character and word-level CNNs outperform individual models

Data augmentation improved model robustness

Abstract

This paper describes our approach for the Detecting Stance in Tweets task (SemEval-2016 Task 6). We utilized recent advances in short text categorization using deep learning to create word-level and character-level models. The choice between word-level and character-level models in each particular case was informed through validation performance. Our final system is a combination of classifiers using word-level or character-level models. We also employed novel data augmentation techniques to expand and diversify our training dataset, thus making our system more robust. Our system achieved a macro-average precision, recall and F1-scores of 0.67, 0.61 and 0.635 respectively.