ABSTRACT
A majority of blogs and websites utilize the five-star rating system with one being the lowest and five being the highest in rating the quality of experience or service in tourist spots. Customers leave reviews and suggestions in an effort to create an impact on the rating of the landmark as well as to help future customers. However, people usually skim through the reviews and base the quality of service on the star rating. This paper proposes that using Sentiment Analysis to evaluate the actual reviews will be a more standardized means of determining the quality of the establishment in comparison to user generated ratings. We conducted testing by choosing establishments in Cebu at random and collating reviews about the chosen places. These gathered reviews were then classified using Sentiment Analysis employing different methods and then compared. Future researchers may use or build upon the findings of this paper to improve ranking systems or replace the five-star rating system altogether.
- E. T. M. Yoke, S. Foo, D. Goh and T. Y. Leng, "An Analysis Of Services For The Mobile Tourist," The International Conference on Mobile Technology, Applications and Systems, pp. 10-12, 2007.Google Scholar
- M. Ochi, M. Okabe and R. Onai, "Rating Prediction using Feature Words Extracted from Customer Reviews," The 34th international ACM SIGIR conference on Research and development in Information Retrieval, no. 34, pp. 1205-1206, 2011 Google ScholarDigital Library
- R. Dong and B. Smyth, "From More-Like-This to Better-Than-This: Hotel Recommendations from User Generated Reviews," The 2016 Conference on User Modeling Adaptation and Personalization, pp. 309-310, 2016. Google ScholarDigital Library
- Y. Zhang, H. Zhang, M. Zhang, Y. Liu and S. Ma, "Do Users Rate or Review? Boost Phrase-level Sentiment Labeling with Review-level Sentiment Classification," The 37th international ACM SIGIR conference on Research & development in information retrieval, pp. 1027-1030, 2014. Google ScholarDigital Library
- L. Chen and F. Wang, "Sentiment-Enhanced Explanation of Product Recommendations," The 23rd International Conference on World Wide Web, no. 23, pp. 239-240, 2014. Google ScholarDigital Library
- D. Yang, D. Zhang, Z. Yu and Z. Wang, "A Sentiment-Enhanced Personalized Location Recommendation System," The 24th ACM Conference on Hypertext and Social Media, no. 24, pp. 119-128, 2013. Google ScholarDigital Library
- J. Kramer and C. Gordon, "Improvement of a Naive Bayes Sentiment Classifier Using MRS-Based Features," The 3rd Joint Conference on Lexical and Computational Semantics, no. 3, pp. 22-29, 2014.Google Scholar
- J. Juncal-Martinez, T. Alvzares-Lopez, M. Fernandez-Gavilanes, E. Costa-Montenegro and F. Gonzalez-Castano, "GTI at SemEval-2016 Task 4: Training a Naive Bayes Classifier using Features of an Unsupervised System," SemEval-2016, pages, pp. 115-119, 2016.Google Scholar
- Y. Suzuki, "Classifying Hotel Reviews into Criteria for Review Summarization," The 2nd Workshop on Sentiment Analysis where AI meets Psychology, no. 2, pp. 65-72, 2012.Google Scholar
- Maite Taboada, Julian Brooke, Milan Tofiloski, Kimberly Voll, and Manfred Stede. 2011. "Lexicon-based methods for sentiment analysis." Comput. Linguist., 37(2):267--307, June Google ScholarDigital Library
Index Terms
- A Comparative Study: Different Automatic Approaches of Stars Generation for Reviews
Recommendations
A comparative analysis of recommender systems based on item aspect opinions extracted from user reviews
In popular applications such as e-commerce sites and social media, users provide online reviews giving personal opinions about a wide array of items, such as products, services and people. These reviews are usually in the form of free text, and ...
NRPA: Neural Recommendation with Personalized Attention
SIGIR'19: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information RetrievalExisting review-based recommendation methods usually use the same model to learn the representations of all users/items from reviews posted by users towards items. However, different users have different preference and different items have different ...
Mining Online Reviews for Predicting Sales Performance: A Case Study in the Movie Domain
Posting reviews online has become an increasingly popular way for people to express opinions and sentiments toward the products bought or services received. Analyzing the large volume of online reviews available would produce useful actionable knowledge ...
Comments