“Revyew” Hotel Maintenance Issue Classifier and Analyzer using Machine Learning and Natural Language Processing

Hospitality and tourism industry websites attract a lot of customers that book hotels on a regular basis. The modern trend to book hotels is through online websites due to the convenience and discounts offered. When a customer visits a hotel they usually post a positive or negative review about their experience on the respective booking website. Identifying maintenance related issues from these reviews is a major problem that even most large hotel chains face. There are many applications for customers related to that area (such as hotel aggregators) but there are only a very few applications for the hotel management to improve their workflow and provide a better service to the customers. This research is to explore a method to analyze hotel reviews and extract maintenance related problems and present them in a user-friendly manner for the hotel management to take the necessary action. It explores the use of machine learning techniques such as binary classifiers, multiclass classifiers along with natural language processing techniques such as sentiment analysis to extract maintenance related issues from text and categorize the issues. A publicly available data source of reviews was used to test and the results show that the SVM classifier performs best for both cases.