Abstract

PurposeThis paper aims to develop a model to predict online review ratings from multiple sources, which can be used to detect fraudulent reviews and create proprietary rating indexes, or which can be used as a measure of selection in recommender systems.Design/methodology/approachThis study applies machine learning and natural language processing approaches to combine features derived from the qualitative component of a review with the corresponding quantitative component and, therefore, generate a richer review rating.FindingsExperiments were performed over a collection of hotel online reviews – written in English, Spanish and Portuguese – which shows a significant improvement over the previously reported results, and it not only demonstrates the scientific value of the approach but also strengthens the value of review prediction applications in the business environment.Originality/valueThis study shows the importance of building predictive models for revenue management and the application of the index generated by the model. It also demonstrates that, although difficult and challenging, it is possible to achieve valuable results in the application of text analysis across multiple languages.

Highlights

  • Social reputation is one of the main aspects that influence a customer’s booking decision process (Anderson, 2012; Cantallops and Salvi, 2014; Kwok et al, 2017; Viglia et al, 2016; Zhao et al, 2015)

  • There is substantial literature concerning the study of online reviews, and much of it focuses on the impact that online reviews have on the hospitality industry, researchers have only recently started to take advantage of the power of the automated analysis of the textual component of online reviews

  • Jiang et al (2010) performed a manual classification of sentiment and found that there was a disconnection between the textual component of the review and the review rating, this present work has demonstrated that the text sentiment strength of a review is associated to the corresponding review rating, similar results were found by He et al (2017), Han et al (2016) and Duan et al (2016), who employed automated sentiment analysis

Read more

Summary

Introduction

Social reputation is one of the main aspects that influence a customer’s booking decision process (Anderson, 2012; Cantallops and Salvi, 2014; Kwok et al, 2017; Viglia et al, 2016; Zhao et al, 2015). This study uses existing features (in traditional statistics, these features are known as independent variables) such as hotel type, hotel stars, and review source and additional features, some of which have been derived from the application of sentiment analysis of the textual component of these reviews.

Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call