Estimating the Rating of Reviewers Based on the Text
This work addresses the need for reliable rating predictions from online reviews to aid user decision-making, but it appears incremental as it builds on existing text analysis methods.
The paper tackled the problem of predicting review ratings from text by analyzing lexical and sentimental features, finding that words with high information gain scores are more efficient than those with high TF-IDF values, and exploring the optimal number of features for prediction.
User-generated texts such as reviews and social media are valuable sources of information. Online reviews are important assets for users to buy a product, see a movie, or make a decision. Therefore, rating of a review is one of the reliable factors for all users to read and trust the reviews. This paper analyzes the texts of the reviews to evaluate and predict the ratings. Moreover, we study the effect of lexical features generated from text as well as sentimental words on the accuracy of rating prediction. Our analysis show that words with high information gain score are more efficient compared to words with high TF-IDF value. In addition, we explore the best number of features for predicting the ratings of the reviews.