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

arXiv: https://arxiv.org/abs/1606.05694 · HTML: https://mlsanity.com/paper/1606.05694/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2016.

## Built on by (most cited first, 9 of 9)

- [FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning](https://mlsanity.com/paper/2108.06332/) (2021)
- [MGTAB: A Multi-Relational Graph-Based Twitter Account Detection Benchmark](https://mlsanity.com/paper/2301.01123/) (2023)
- [Character-level HyperNetworks for Hate Speech Detection](https://mlsanity.com/paper/2111.06336/) (2021)
- [Hashtag-Guided Low-Resource Tweet Classification](https://mlsanity.com/paper/2302.10143/) (2023)
- [Guiding Computational Stance Detection with Expanded Stance Triangle Framework](https://mlsanity.com/paper/2305.19845/) (2023)
- [KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP](https://mlsanity.com/paper/2206.10265/) (2022)
- [A Unified Knowledge Graph Augmentation Service for Boosting Domain-specific NLP Tasks](https://mlsanity.com/paper/2212.05251/) (2022)
- [Multi-label and Multi-target Sampling of Machine Annotation for Computational Stance Detection](https://mlsanity.com/paper/2311.04495/) (2023)
- [Disentangled VAD Representations via a Variational Framework for Political Stance Detection](https://mlsanity.com/paper/2502.19276/) (2025)

## Abstract (arXiv)

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.