Enhanced Lexical Based Technique For Opinion Mining In Tourism

Today is the era of online shopping. Most of the people do online shopping for their convenience. It includes both M-Commerce and E-Commerce. Important part of the online shopping are the reviews given by the customer which gives the rating to the product they have purchased. In addition to the product reviews, customer also give reviews about company and post purchase experience. These reviews effects the promotion of the product and also helps others to take wise decisions regarding the purchase of goods. This research is focused on studying the reviews on tourism. In which people gives reviews regarding Hotels, Recreation places etc. They also reviews regarding Food, Room, Room Service, Parking, Pick up facility etc. In this research lexical based approach is used to identify the collective analysis for positive and negative reviews. So that people who are trying to take the services following the reviews can see the collective scenario. Current lexical based approach is better than the previous research which was based on sentiwordnet. In sentiwordnet the marks or grade given to the positive, negative, and neutral word. With the help of lexical approach reviews have been tokenized. Positive, negatives and neutral reviews are compared with established Ontology. This mined information will provide better view regarding the total reviews rather than studying all the individual reviews. Experimental results shows much better performance to have collective analysis by automated tool in terms of accuracy and time taken.

REFERENCES

[1] Kamal AMAROUCHE, Houda BENBRAHIM, Ismail KASSOU, ”Product Opinion Mining for Competitive Intelligence”, vol. 73, pp.358– 365,2015.
[2] Cristian Bucur,” Using Opinion Mining Techniques in Tourism”,vol. 23, pp.1666-1673,2015.
[3] Jumayel Islam, Zubair Azami Badhon and Pintu Chandra Shill, ”An Effective Approach of Intrinsic and Extrinsic Domain Relevance Technique for Feature Extraction In Opinion Mining”,vol. 1, pp.1269-75,2016.
[4] Shahab Saquib Sohail, Jamshed Siddiqui, Rashid Ali, ”UMW: AMODEL FOR ENHANCEMENT IN WEARABLE TECHNOLOGY BASED ON OPINION MINING TECHNIQUE”,vol. 1, pp.46-52, 2015.
[5] Shoiab Ahmed, Ajit Danti, ”A Novel Approach for Sentimental Analysis and Opinion Mining based on sentiwordnet using Web Data”,vol. 1 pp.15-20,2015.
[6] Dhanalakshmi V., Dhivya Bino, Saravanan A. M.,”Opinion mining from student feedback data using Supervised learning algorithms”,vol. 1. pp. 84-97,2016.
[7] Aliaksei Severyn, Alessandro Moschitti, Olga Uryupina , Barbara Plank , Katja Filippova ,” Multi-lingual opinion mining on youtube”,vol. 4, pp.45-54,2015.
[8] Agarwal, Sonali, G. N. Pandey, and M. D. Tiwari. "Data mining in education: data classification and decision tree approach." International Journal of e-Education, vol.. 2, pp. 140-145, 2012.
[9] Balahur, Alexandra, Ralf Steinberger, Mijail Kabadjov, Vanni Zavarella, Erik Van Der Goot, Matina Halkia, Bruno Pouliquen, and Jenya Belyaeva. "Sentiment analysis in the news." Vol. 3,pp.1309,6202 ,2013.
[10] Bhowmick, Plaban Kumar, Anupam Basu, and Pabitra Mitra. "Classifying emotion in news sentences: When machine classification meets human classification." International Journal on Computer Science and Engineering2, vol. 1, pp. 98-108,2010.
[11] Bhukya, Devi Prasad, and S. Ramachandram. "Decision tree induction: an approach for data classification using AVL-tree." International Journal of Computer and Electrical Engineering 2, vol. 4,pp:660-670,2010.
[12] Vandana Korde, Verónica, Noelia Sánchez-Marono, and Amparo Alonso-Betanzos. "Data classification using an ensemble of filters." Neurocomputing vol. 135,pp. 13-20,2010.
[13] Byun, Hyeran, and Seong-Whan Lee. "Applications of support vector machines for pattern recognition: A survey." In Pattern recognition with support vector machines, vol. 4, pp. 213-236,2002.
[14] Zanaty, Radu George, and N. VINŢAN Lucian. "Contributions to Document Classification System Design." Vol. 1, pp. 89-97, 2011.
[15] Patil , Limeng, Fan Meng, Yong Shi, Minqiang Li, and An Liu. "A Hierarchy Method Based on LDA and SVM for News Classification." In Data Mining Workshop (ICDMW), 2014 IEEE International Conference on,vol. 4, pp. 60-64,2014.