Opinion Mining With Hotel Review using Latent Dirichlet Allocation-Fuzzy C-Means Clustering (LDA-FCM)
Main Article Content
Abstract
Indian tourism plays a significant role in Indian economic growth. The hotel booking and other stay-related inquiries are more important for every tourism manager. The tourist from the various country books their hotels based on the rating and reviews. The most remarkable improvement achieved through online hotel booking by customer review and rating. Customer opinions are more important for the growth of every business. This paper modelled the opinion mining system for hotel review. The wealth of customer thoughts and feelings has been identified by the review, and it also has a chance for the customer to reach their genuine opinion on social media. Most customers make online reviews and ratings. The opinion mining makes it very simple with a natural language process (NLP) that computers can easily understand every customer's human feelings and emotions. In this work, the NLP techniques of Part of Speech (POS) tagging, LEXICAL analysis, Latent Dirichlet allocation (LDA) has been used for an efficient opinion mining process. The fuzzy c-means clustering (FCM) has been used to cluster the opinion's positive and inclusive class determination. The proposed LDA-FCM based model works more efficiently than the conventional FCM algorithm. The performance has been evaluated by using Accuracy, precision, recall, and f1-score. The performance has been compared with the related work..
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.