Literature Review on N-Gram Text Classification Models for Hotel Reviews Sentiment Analysis

Evaluations and blogs obtained from social networking sites are valuable sources for further analysis and decision-making in the context of the continually growing demand for Internet marketing. However, due to the often nonsensical and disorganized nature of these evaluations and blogs, processing approaches such as categorization or clustering are necessary to generate useful information for subsequent applications. These comments and posts can then be categorized into groups such as positive, negative, and neutral to extract information from the input database. To categorize these reviews, supervised machine learning methods such as Naive Bayes, Random Forest, Support Vector Machine, Maximum Entropy Classifier, and others are employed. Additionally, the use of n-grams is examined for data classification. We employ effective machine learning algorithms to generate n-gram features for hotel reviews. Subsequently, the system generates a generalized rating for the service as an output. This classification process enhances accuracy, making the product valuable for both developers and end-users.