• Kumar, Chhotelal
• Kumar, Mukesh
• Kumar, Naween
• Kavitha, S.

Abstract

<jats:title>Abstract</jats:title><jats:p>Machine Learning (ML) is a branch of Artificial Intelligence (AI) in which data-driven schemes learn patterns by being exposed to relevant data. Natural Language Processing (NLP) has been benefiting greatly from ML. In this article, ML is used to anticipate hotel review ratings. This paper proposes an Ensemble Learning-based rating prediction model for predicting ratings based on user reviews. The main objective of this research article is to accurately predict the best user experience rating. The majority voting technique of Ensemble learning has been used to predict the ratings. In this research article, first, the dataset is cleaned and then processed through a series of Natural Language Processing (NLP) preprocessing steps. This article includes a comparison of various classifiers with various embedders. Stochastic Gradient Descent (SGD) Classifier, Logistic Regression (LR), Logistic Regression Cross Validation (LRCV), Support Vector Classifier (SVC), Decision Tree Classifier (DTC), Random Forest Classifier (RFC), and K-Nearest Neighbour (KNN) are the 7 classifiers used, along with 3 embedding techniques: Bag of Words (BoW), Word2Vec, and Term Frequency-Inverse Document Frequency (TF-IDF). Our proposed solution is more accurate and works well. Accuracy and count are used as performance measures to compare and validate classifiers and embedders. According to the simulation report, TF-IDF utilizing LRCV has a 61% accuracy rate.</jats:p>

Topics

• impedance spectroscopy
• simulation
• random
• machine learning