Friends and Enemies of Clinton and Trump: Using Context for Detecting Stance in Political Tweets

Abstract

Abstract. Stance detection, the task of identifying the speaker's opinion towards a particular target, has attracted the attention of researchers. This paper describes a novel approach for detecting stance in Twitter. We define a set of features in order to consider the context surrounding a target of interest with the final aim of training a model for predicting the stance towards the mentioned targets. In particular, we are interested in investigating political debates in social media. For this reason we evaluated our approach focusing on two targets of the SemEval-2016 Task 6 on Detecting stance in tweets, which are related to the political campaign for the 2016 U.S. presidential elections: Hillary Clinton vs. Donald Trump. For the sake of comparison with the state of the art, we evaluated our model against the dataset released in the SemEval-2016 Task 6 shared task competition. Our results outperform the best ones obtained by participating teams, and show that information about enemies and friends of politicians help in detecting stance towards them.

Your Stance is Exposed! Analysing Possible Factors for Stance Detection on Social Media

“…There has been some work on studying the integration of network and content with a limited focus on the ideological political views [15,31,33,36]. For instance the study of [31] focused on the liberal and conservative on twitter.…”

“…detection to analyze social media as main component of investigating the users aligns toward a given topic or entity [3,7,33,34,36,40].…”

Extracting Graph Topological Information and Users’ Opinion

“…We aim to automatically estimate the stance of all users of our dataset in order to explore how the stance is distributed in the social network. Then, we propose a machine learning supervised approach using SVM to annotate the stance s of the remaining 3,948 users, using the following five features computed over a triplet: bag of words (BoW), structural-based (structural), sentiment-based (sentiment) (described in [5]), community-based (community), and temporal-based (temporal). The community feature returns the community of the user who wrote the triple, while the temporal one, the given time interval of the triplet.…”

On Language and Structure in Polarized Communities

“…The starting point of our proposal is to be found in the method proposed in Lai et al [43] in which the authors exploited three diverse groups of features: Structural such as punctuation and other Twitter marks, Sentiment i.e. lexica covering different facets of affect, and finally Context-based, which consider the relationship that exists between a given target and other entities in its domain.…”

“…Mohammad et al [62] took advantage of word-based and sentiment-based features to perform SD on the SemEval-2016 Task 6 dataset. Lai et al [43], instead, proposed an approach using context features to detect stance towards two targets related to politics in the U.S. presidential elections: Hillary Clinton and Donald Trump. The obtained results outperformed those from the shared task.…”