IDI@NTNU at SemEval-2016 Task 6: Detecting Stance in Tweets Using Shallow Features and GloVe Vectors for Word Representation

Proceedings of SemEval-2016, pages 445–450, San Diego, California, June 16-17, 2016. c⃝2016 Association for Computational Linguistics IDI@NTNU at SemEval-2016 Task 6: Detecting Stance in Tweets Using Shallow Features and GloVe Vectors for Word Representation Henrik Bøhler and Petter Fagerlund Asla and Erwin Marsi and Rune Sætre Norwegian University of Science and Technology Sem Sælands vei 9 Trondheim, 7491, NORWAY {henriboh,pettefas}@stud.ntnu.no, {emarsi,satre}@idi.ntnu.no Abstract This paper describes an approach to auto- amatically detect stance in tweets by building supervised system combining shallow features and pre-trained word vectors as word representation. The word vectors were obtained from several collections of large corpora using GloVe, an unsupervised learn- ing algorithm. We created feature vectors by selecting the word vectors relevant to the data and summing them for each unique word. Combining multiple classifiers into a voting classifier, representing the best of both approaches, shows a significant improvement over the baseline system. 1 Introduction This paper describes our submission to the SemEval 2016 competition Task 6A - Detecting Stance in Tweets. The goal of the task is to classify a tweet into one of the three classes – against, favor or none in regard to a certain topic. These classes represents the tweet’s stance towards the given target. Twitter, and other microblogging platforms, have in recent years become popular arenas to apply natu- ral language processing tasks. One of the most pop- ular tasks has been sentiment analysis. Stance de- tection differs from sentiment analysis because the sentiment of a text – generally positive or negative – does not necessarily agree with its stance regarding a certain topic of debate. For example, a tweet like ”all those climate-deniers are morons” is negative in its overall sentiment, but positive with regard to the stance that climate change is a real concern. We re- fer the reader to the official SemEval 20161 website for a detailed task description. Our approach to detect stance is based on shal- low features (Kohlsch¨utter et al., 2010; Hagen et al., 2015; Walker et al., 2012) and the use of GloVe word vectors (Pennington et al., 2014). During the development phase we explored several approaches by implementing features such as sentiment detec- tion (Hutto and Gilbert, 2014), number of tokens and number of capital words. The experiments later in this paper show that not all features enhanced the performance of the implemented system. The feature that turned out to boost performance the most, in combination with basic shallow fea- tures, was the use of pre-trained GloVe vectors (Pen- nington et al., 2014). The vector representations of tweets were created by summing the pre-trained word vectors for each unique word. No additional data was added to the training set used for our fi- nal submission, although we explored the possibility of gathering and automatically labelling additional tweets by using label propagation (Zhu and Ghahra- mani, 2002; Zhou et al., 2004). This did enhance our baseline system performance slightly, but not in combination with other features. 2 System description To predict the stance in …

Content truncated to 500 words