Topical Stance Detection for Twitter: A Two-Phase LSTM Model Using Attention
This work addresses stance detection for social media analysis, presenting an incremental improvement with a novel two-phase deep learning architecture.
The paper tackles the problem of topical stance detection on Twitter by developing a two-phase LSTM model with attention, achieving a best-case macro F-score of 68.84% and accuracy of 60.2% on the SemEval 2016 dataset, outperforming existing deep learning solutions.
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.