Performing Stance Detection on Twitter Data using Computational Linguistics Techniques
This work addresses the problem of automatically identifying user opinions on social media for applications like sentiment analysis, but it is incremental as it builds on existing computational linguistics techniques.
The paper tackled stance detection on Twitter by applying a supervised approach with various feature extraction methods, achieving improved accuracy through optimization and lexicon integration.
As humans, we can often detect from a persons utterances if he or she is in favor of or against a given target entity (topic, product, another person, etc). But from the perspective of a computer, we need means to automatically deduce the stance of the tweeter, given just the tweet text. In this paper, we present our results of performing stance detection on twitter data using a supervised approach. We begin by extracting bag-of-words to perform classification using TIMBL, then try and optimize the features to improve stance detection accuracy, followed by extending the dataset with two sets of lexicons - arguing, and MPQA subjectivity; next we explore the MALT parser and construct features using its dependency triples, finally we perform analysis using Scikit-learn Random Forest implementation.