Topical Stance Detection for Twitter: A Two-Phase LSTM Model Using Attention

TL;DR

This paper introduces T-PAN, a novel two-phase deep learning framework using attention-based LSTM models for topical stance detection on Twitter, significantly improving performance over previous methods.

Contribution

It presents the first deep learning-based two-phase architecture for topical stance detection, combining subjectivity and sentiment classification.

Findings

Achieved a macro F-score of 68.84% on SemEval dataset.

Attained a best-case accuracy of 60.2%.

Outperformed existing deep learning solutions.

Abstract

The topical stance detection problem addresses detecting the stance of the text content with respect to a given topic: whether the sentiment of the given text content is in FAVOR of (positive), is AGAINST (negative), or is NONE (neutral) towards the given topic. Using the concept of attention, we develop a two-phase solution. In the first phase, we classify subjectivity - whether a given tweet is neutral or subjective with respect to the given topic. In the second phase, we classify sentiment of the subjective tweets (ignoring the neutral tweets) - whether a given subjective tweet has a FAVOR or AGAINST stance towards the topic. We propose a Long Short-Term memory (LSTM) based deep neural network for each phase, and embed attention at each of the phases. On the SemEval 2016 stance detection Twitter task dataset, we obtain a best-case macro F-score of 68.84% and a best-case accuracy of 60.2%, outperforming the existing deep learning based solutions. Our framework, T-PAN, is the first in the topical stance detection literature, that uses deep learning within a two-phase architecture.