Abstract
This paper proposes an approach for Sentiment Analysis on online textual reviews that leverages polarity switches and domain ontologies to first perform Aspect Based Sentiment Analysis and uses it to then refine the overall sentiment scores. It segregates the review text into different fragments using sentiment polarity switching information. Then, it maps each of these fragments with the domain ontology to determine the aspect each fragment refers to and carries out corresponding Aspect Based Sentiment Analysis. Finally, the sentiments from all the aspects are clubbed together taking into account the hierarchical level of aspects in the domain ontology to refine the overall review polarity. Hontology was used to map the textual fragments to different aspects in the hotel domain like service, room, etc. Experiments carried out in the hotel domain on 800 hotel reviews extracted from Tripadvisor, Yelp, Expedia, Orbitz, Hotels.com and Priceline show that Aspect Based SA and domain ontologies together can indeed be used to refine SA. The macro level F1 score for the proposed approach is 3.96% higher than the baseline approach.
References
Wei, W., Gulla J.A.: Enhancing the HL-SOT approach to sentiment analysis via a localized: feature selection framework. In: Proceedings of the 5th International Joint Conference on Natural Language Processing, Chiang Mai, Thailand (2011)
Jiang, L., Yu, M., Zhou, M., Liu, X., Zhao, T.: Target-dependent twitter sentiment classification. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, pp. 151–160. Portland, Oregon (2011)
Thet, T.T., Na, J.-C., Khoo, C.S.: Aspect-based sentiment analysis of movie reviews on discussion boards. J. Inf. Sci. 36(6), 823–848 (2010)
Singh, V.K., Piryani, R., Uddin, A., Walia, P.: Sentiment analysis of movie reviews a new feature-based heuristic for aspect-level sentiment classification. In: Proceedings of the 2013 International Muli-Conference on Automation, Communication, Computing, Control and Compressed Sensing, pp. 712–717. Kerala, India (2013)
Taboada, M., Brooke, J., Stede, M.: Genre-based paragraph classification for sentiment analysis. In: Proceedings of SIGDIAL 2009: The 10th Annual Meeting of the Special Interest Group in Discourse and Dialogue, pp. 62–70. Queen Mary University of London (2009)
Saeidi, M., Bouchard, G., Liakata, M., Riedel, S.: SentiHood: targeted aspect based sentiment analysis dataset for urban neighbourhoods. In: COLING (2016)
Thakor, P., Sasi, S.: Ontology-based sentiment analysis process for social media content. In: INNS Conference on Big Data (2015)
Kontopoulos, E., Berberidis, C., Dergiades, T., Bassiliades, N.: Ontology-based sentiment analysis of twitter posts. Expert Syst. Appl. 40(10), 4065–4074 (2013)
Word Sense Disambiguation - Lesk Algorithm. http://www.nltk.org/howto/wsd.html
Esuli, A., Sebastiani, F.: SentiWordNet: a publicly available lexical resource for opinion mining. In: Proceedings of the 5th Conference on Language Resources and Evaluation, (LREC 2006), pp. 417–422. Genova (2006)
Deceptive Opinion Spam Corpus v1.4. http://myleott.com/op_spam/
Chaves, M.S., Freitas, L., Vieira, R.: Hontology: a multilingual ontology for the accommodation sector in the tourism industry. In: KEOD2012-International Conference on Knowledge Engineering and Ontology Development, pp. 149–154 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sharma, S., Chakraverty, S., Jauhari, A. (2017). Leveraging Polarity Switches and Domain Ontologies for Sentiment Analysis in Text. In: Mandal, J., Dutta, P., Mukhopadhyay, S. (eds) Computational Intelligence, Communications, and Business Analytics. CICBA 2017. Communications in Computer and Information Science, vol 775. Springer, Singapore. https://doi.org/10.1007/978-981-10-6427-2_7
Download citation
DOI: https://doi.org/10.1007/978-981-10-6427-2_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6426-5
Online ISBN: 978-981-10-6427-2
eBook Packages: Computer ScienceComputer Science (R0)