involved in the CFSLDA feature selection process improve the accuracy of model. Having the right of features in hand, the contextual feature-based sentiment analysis and predictive analytics are possible with the dataset using supervised machine learning techniques.
1.8 Applications
Much of the social media text research have been undertaken for ranking public/private sectors or products [41], for improving customer satisfaction [64], or for recommending new services of products [50]. Multi-Criteria Decision Making (MCDM) problem can be solved by using the OnSI model. Here OnSI model can be applied to extract the set of features from the given set of review documents. Ranking methods use suitable weights for each feature and the sentiment score from the sentiment analysis process. The MCDM hierarchy problem for determining the better healthcare service provider is shown in Figure 1.13.
Figure 1.13 Hierarchy of MCDM problem.
There are many MCDM methods available like SAW (simple additive weight), TOPSIS, VIKOR and so on. This chapter focuses on applying VIKOR technique for determining the better hospital based on their features. VIKOR is one of the ranking methods for optimizing the multi-response process through compromise [42]. It compares the closeness of each criterion with the alternative and derives ranking index for each criterion. The core concept of VIKOR is that ranking the criteria from the set of different alternatives in the presence of conflicting criteria [43]. Figure 1.14 shows the ranking of features for various alternatives (hospitals) under consideration.
Figure 1.14 Ranking of features by VIKOR method.
Figure 1.7 shows that the alternative H10 scored rank 1 for the features “Cost,” “Medicare,” and “Infrastructure,” the alternative H6 for the feature “Staff” and the alternative H9 for the feature “Time.” These data can be used for benchmarking by all the hospitals to improve their process.
1.9 Conclusion
Social media text analytics can be used in “brand experience” research. It gives the experience and strategy for building the long term customer-brand relationship. Text analytics research found that applying content analysis to user-generated content provides a rich opportunity to study users’ style of writing, patterns, or preferences. Content analysis research helps all other data analysts to change their research direction to social media text analytics. The reports from different healthcare service providers recommended that the hospital status and the service quality are the two important factors that go hand-in-hand. They also reported that the hospitals have to be keen on their online reputation so as to manage the trust and relationship with their clients or patients. The chapter focused on identifying the features from the users’ reviews, ranked them using multi-criteria decision making techniques, and identified the areas for improvement in specific aspects of healthcare services and its operations. This work can be extended to time-series based sentiment analysis for the features extract which would be much helpful for predicting the profit of a product or Organization and the customer satisfaction. Sarcasm in the review documents and classification of fake reviews would give further improvement in this text analytics.
1.10 Future Work
This work can be improved with complete automation in building the domain Ontology, and exploring various methods for visualizing the results, which enables the users to get more information. In this study, individuals, siblings, and concepts are the only items considered for Ontology learning. It can be further extended and modeled as “sentiment domain dictionary” with the set of positive and negative words.
However, the work can be extended to map relationship between concepts, in addition to the existing terms. It can be done by the development of multi-agent system for integration of different domain Ontology using their properties. This in turn helps to develop expert systems solution or decision support system for any decision-making problem.
References
1. Somprasertsri, G. and Lalitrojwong, P., Mining feature-opinion in online customer reviews for opinion summarization. J. Universal Comput. Sci., 16, 6, 938–955, 2010.
2. Yang, J.Y., Kim, H.J., Lee, S.G., Feature-based product review summarization utilizing user score. J. Inf. Sci. Eng., 26, 6, 1973–1990, 2010.
3. Jacobsen, J.S. and Munar, A.M., Motivations for sharing tourism experiences through social media. Tourism Management, 43, 46–54, 2014.
4. Olga, L.P. and Raj, R., Evolution of social media and consumer behaviour changes in tourism destination promotion. Int. J. Bus. Globalisation, 12, 3, 358–368, 2014.
5. Varanasi, P. and Tanniru, M., Seeking intelligence from Patient experience using text mining: analysis of emergency data. Inf. Syst. Manage., 32, 3, 220– 228, 2015.
6. Ittoo, A., Nguyen, L.M., Bosch, A., Text analytics in industry: Challenges, desiderata and trends. Comput. Ind., 78, 96–107, 2016.
7. Nedellec, C. and Nazarenko, A., Ontology and information extraction: A necessary symbiosis, in: Ontology Learning from Text: Methods, Evaluation and Applications, P. Buitelaar, P. Cimiano, B. Magnini (Eds.), pp. 3–14, IOS Press Publications, Amsterdam, The Netherlands, 2005.
8. Maedche, A., Pekar, V., Staab, S., Ontology learning part one—on discovering taxonomic relations from the web, N. Zhong (Ed.), pp. 301–320, Web Intelligence, Springer, Berlin Heidelberg, 2003.
9. Rindflesch, T.C., Tanabe, L., Weinstein, J.N., Hunter, L., EDGAR: Extraction of Drugs, Genes and Relations from the Biomedical Literature, in: Proceedings of Pacific Symposium on Biocomputing, Singapore, pp. 517–528, NIH Public Access, 2000.
10. Chen, M., Ebert, D., Hagen, H., Data, information, and knowledge in visualization. J. IEEE Comput. Graphics Appl., 29, 1, 12–19, 2009.
11. Guo, H., Zhu, H., Guo, Z., Su, Z., Product feature categorization with multilevel latent semantic association, in: Proceedings of the Eighteenth ACM Conference on Information and Knowledge Management CIKM ‘09, Association for Computing Machinery, New York, NY, USA, pp. 1087–1096, 2009.
12. Blei, D.M. and Lafferty, J.D., A coorelated topic model of science. Ann. Appl. Stat., 1, 1, 17–35, 2007.
13. Colace, F., Santo, M.D., Greco, L., Moscato, V., Picariello, A., Probabilistic approaches for sentiment analysis: Latent dirichlet allocation for ontology building and sentiment extraction, in: Studies in Computational Intelligence: Sentiment Analysis and Ontology Engineering, W. Pedrycz and S.-M. Chen (Eds.), vol. 639, pp. 75–91, Springer, Switzerland, 2016.
14. Maynard, D., Bontcheva, K., Cunninham, H., Towards a semantic extraction of named entities. Recent Adv. Nat. Lang. Process., Bulgaria, Vol. 1, pp. 257– 263, 2003.
15. Castells, P.,
