Opinion context extraction for aspect sentiment analysis.
MetadataShow full item record
BANDHAKAVI, A., WIRATUNGA, N., MASSIE, S. and LUHAR, R. 2018. Opinion context extraction for aspect sentiment analysis. In Proceedings of 12th International Association for the Advancement of Artificial Intelligence (AAAI) conference on web and social media 2018 (ICWSM 2018), 25-28 June 2018, Palo Alto, USA. Palo Alto: AAAI Press [online], pages 564-567. Available from: https://www.aaai.org/ocs/index.php/ICWSM/ICWSM18/paper/view/17859/17051
Sentiment analysis is the computational study of opinionated text and is becoming increasing important to online commercial applications. However, the majority of current approaches determine sentiment by attempting to detect the overall polarity of a sentence, paragraph, or text window, but without any knowledge about the entities mentioned (e.g. restaurant) and their aspects (e.g. price). Aspect-level sentiment analysis of customer feedback data when done accurately can be leveraged to understand strong and weak performance points of businesses and services, and can also support the formulation of critical action steps to improve performance. In this paper we focus on aspect-level sentiment classification, studying the role of opinion context extraction for a given aspect and the extent to which traditional and neural sentiment classifiers benefit when trained using the opinion context text. We propose four methods to aspect context extraction using lexical, syntactic and sentiment co-occurrence knowledge. Further, we evaluate the usefulness of the opinion contexts for aspect-sentiment analysis. Our experiments on benchmark data sets from SemEval and a real-world dataset from the insurance domain suggests that extracting the right opinion context is effective in improving classification performance.Specifically combining syntactical features with sentiment co-occurrence knowledge leads to the best aspect-sentiment classification performance.