Sentiment Analysis User Regarding Hotel Reviews by Aspect Based Using Latent Dirichlet Allocation, Semantic Similarity, and Support Vector Machine Method

The Hotel website always provide sentiment reviews of the service, then users can easily choose the desired facility according to the best advice results from the previous user. In this study, the sentiment of the reviews are determined based on five hotel aspects, those are: food, service, location, comfort and cleanliness. Every data hotel reviews is pre-processed to produce a term list. Extract related hidden topics using Latent Dirichlet Allocation (LDA). The extracted documents are categorized by matching for similarity to determine the term documents into five hotel aspects. Each term document is expanded using synonyms to increase the similarity value to LDA with 100% expanded document using Cosine Similarity produces the highest performance value of 0.856. Labeling the sentiment of each review based on the aspect and sentiment classification using the Support Vector Machine method gets an average value of 0.940 for all fifth aspects. The ranking of the most important aspects shows that users talk a lot about the cleanliness aspect, having the highest positive sentiment value of 39.450 and having a negative sentiment of 3.861, indicating that each review sentiment is influenced by certain aspects.