Aspect-Based Sentiment Analysis Using Smart Company and Hotel Aspect Review Data
DOI:
https://doi.org//10.32628/IJSRST207223Keywords:
Aspect frequency, aspect ranking, language processing technique, aspect-sentiment based embedding.Abstract
Digital sources such as smart applications opinions and online feedback statistics are crucial resources to be seeking for customers’ remarks and input. However, the reviews are often disorganized, leading to difficulties in information navigation and knowledge acquisition. The aforementioned problem is overcome by generating aspect-sentiment based embedding for the hotels and companies by looking into reliable reviews of them. The important product aspects are identified based on two observations: 1) the important aspects are usually commented on by a large number of consumers and 2) consumer opinions on the important aspects greatly influence their overall opinions. Aspect frequency and the influence of consumer opinions given to each aspect over their overall opinions are identified for hotel reviews whereas for company reviews approach adopts language processing techniques, policies, and lexicons to address several sentiment evaluation challenges, and convey summarized results. Moreover, aspect ranking achieve significant performance improvements, which demonstrate the capacity of aspect ranking in facilitating real-world applications.
References
- D. M. Blei, L. Carin and D. Dunson (2010), "Probabilistic topic models", IEEE Signal Process. Mag., vol. 27, no. 6, pp. 55-65, 2010.
- D. Borth, R. Ji, T. Chen, T. Breuel, S.-F. Chang, "Large-scale visual sentiment ontology and detectors using adjective noun pairs", Proc. 21st ACM Int. Conf. Multimedia, pp. 223-232, 2013.
- Z. Chen, A. Mukherjee, B. Liu, M. Hsu, M. Castellanos, R. Ghosh, "Leveraging multi-domain prior knowledge in topic models", Proc. 23th Int. Joint Conf. Artif. Intel., pp. 2071-2077, 2011.
- P. Isola, J. Xiao, A. Torralba, A. Oliva, "What makes an image memorable?", Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 145-152, 2013.
- Y. Jia, M. Salzmann, T. Darrell, "Learning cross-modality similarity for multinomial data", Proc. 13th IEEE Int. Conf. Comput. Vis., pp. 2407-2414, 2014.
- A.S. Manek, P.D. Shenoy, M.C. Mohan, K.R. Venugopal, Aspect term extraction for sentiment analysis in large movie reviews using Gini Index feature selection method and ELM classifier, World Wide Web. 20 (2017)135–154, https://doi.org/10.1007/s11280-015-0381-x.
- M.S. Mubarok, M. Adiwijiaya, AldhiDwi, Aspect-based sentiment analysis to review products using Naïve bayes, in: AIP Conference Proceedings, AIP Publishing, 2017, pp. 1–8, https://doi.org/10.1063/1.4994463.
- D. Pham, A. Le, Data & knowledge engineering learning multiple layers of knowledge representation for aspect based sentiment analysis, DataKnowl. Eng. 114 (2018)26–39, https://doi.org/10.1016/j.datak.2017.06.001.
- M. Rathan, V.R. Hulipalled, K.R. Venugopal, L.M. Patnaik, Consumer insight mining: aspect based Twitter opinion mining of mobile phone reviews, Appl. Soft Comput. J. 68 (2018) 765–773, https://doi.org/10.1016/j. asoc.2017.07.056.
- K. Schouten, O. van der Weijde, F. Frasincar, R. Dekker, Supervised and unsupervised aspect category detection for sentiment analysis with co- occurrence data, IEEE Trans. Cybern. 48 (2018) 1263–1275, https://doi.org/ 10.1109/TCYB.2017.2688801.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRST
This work is licensed under a Creative Commons Attribution 4.0 International License.
