A Joint Sentiment-Target-Stance Model for Stance Classification in Tweets

Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2656–2665, Osaka, Japan, December 11-17 2016. A Joint Sentiment-Target-Stance Model for Stance Classification in Tweets Javid Ebrahimi, Dejing Dou, Daniel Lowd Department of Computer and Information Science, University of Oregon Eugene, Oregon 97403, USA {javid,dou,lowd}@cs.uoregon.edu Abstract Classifying the stance expressed in online microblogging social media is an emerging problem in opinion mining. We propose a probabilistic approach to stance classification in tweets, which models stance, target of stance, and sentiment of tweet, jointly. Instead of simply conjoining the sentiment or target variables as extra variables to the feature space, we use a novel formula- tion to incorporate three-way interactions among sentiment-stance-input variables and three-way interactions among target-stance-input variables. The proposed specification intuitively aims to discriminate sentiment features from target features for stance classification. In addition, regu- larizing a single stance classifier, which handles all targets, acts as a soft weight-sharing among them. We demonstrate that discriminative training of this model achieves the state-of-the-art re- sults in supervised stance classification, and its generative training obtains competitive results in the weakly supervised setting. 1 Introduction Stance Classification (SC) is the task of inferring from text whether the author is in favor of a given target, against it, or has a neutral position toward it. This task, which can be complex even for humans (Walker et al., 2012a), is related to argument mining, subjectivity analysis, and sentiment classification. Generic sentiment classification is formulated as determining whether a piece of text is positive, negative, or neutral. However, in SC, systems must detect favorability toward a given (pre-chosen) target of interest. In this sense, SC is more similar to target-dependent sentiment classification (Jiang et al., 2011), with a major difference that the target of the stance might not be explicitly mentioned in text or might not be the target of the opinion (Mohammad et al., 2016). For example, the tweet below implies a stance against Donald Trump, through expressing support for Hillary Clinton. Target: Donald Trump My vote is definitely for Hillary. Can’t trust #gop candidates. This is an interesting task to study on social networks because of the abundance of personalized and opinionated language. Given the growing significance of the role social media is playing in our world, studying stance classification can be beneficial among others, in identifying electoral issues and under- standing how public stance is shaped (Mohammad et al., 2015). SemEval 2016 Task 6 organizers (Mohammad et al., 2016) released a joint stance and sentiment an- notated dataset. Studying the correlation between sentiment and stance and how the former can help detect the latter is an important research question that we address in this paper. Our approach relies on one observation for stance detection in tweets. Ignoring general words and stopwords, a lot of the time, we can expect a rough dichotomy on the remaining n-grams of the tweets. Concretely, a stance-related n-gram either refers to a topic related to the target or bears a sentiment. In Table …

Content truncated to 500 words