Evaluating hotels rating prediction based on sentiment analysis services

Abstract

Purpose – The purpose of this paper is to assess the reliability of numerical ratings of hotels calculated by three sentiment analysis algorithms. Design/methodology/approach – More than one million reviews and numerical ratings of hotels in seven cities in four countries were extracted from TripAdvisor web site. Reviews were classified as positive or negative using three sentiment analysis tools. The percentage of positive reviews was used to predict numerical ratings that were then compared with actual ratings. Findings – All tools classified reviews as positive or negative in a way that correlated positively with numerical ratings. More complex algorithms worked better, yet predicted ratings showed reasonable agreement with actual ratings for most cities. Predictions for hotels were less reliable if based on less than 50-60 percent of available reviews. Practical implications – These results validate that sentiment analysis can be used to transform unstructured qualitative data on user opinion into quantitative ratings. Current tools may be useful for summarizing opinions of user reviews of products and services on web sites that do not require users to post numerical ratings such as traveler forums. This summarizing may be valuable not just to potential users, but also to the service and product providers and offers validation and benchmarking for future improvement of opinion mining and prediction techniques. Originality/value – This work assesses the correlation between sentiment analysis of hotels’ reviews and their actual ratings. The authors also evaluated the reliability of results of sentiment analysis calculated by three different algorithms.

Semantic Features for Optimizing Supervised Approach of Sentiment Analysis on Product Reviews

“…The implications comprise practical implication for both online marketers and customers, as well as academic implications for the researcher in the field of text processing. The results of study affirm that our proposed SA technique can be employed to generate quantitative ratings from unstructured text data within the product review [34]. The online marketers could, therefore, apply the technique to foresee consumer satisfaction toward a certain product [35].…”

Hotel online reviews: creating a multi-source aggregated index

“…Recently, the number of published studies taking advantage of the textual component of reviews has increased, focusing on issues such as identifying relevant topics mentioned in reviews (Calheiros et al, 2017), understanding what satisfied and unsatisfied customers mention (Berezina et al, 2016;Xu et al, 2017), assessing the impact of social media on a hotel's service (Duan et al, 2016), understanding what guests think of hotels (Han et al, 2016;He et al, 2017;Xiang et al, 2015;Xu and Li, 2016), examining the consumers' prepurchase decisions (Noone and McGuire, 2014), identifying deceptive review comments (Lin et al, 2017), and review opinion classification predictions (Bjørkelund et al, 2012;Salehan and Kim, 2016). Although some of these works resort to sentiment analysis and machine learning, to the extent of the authors knowledge, only three of them use these tools to predict review ratings (i.e., Ganu et al, 2013;Lei and Qian, 2015;López Barbosa et al, 2015).…”

Estimating point-of-interest rating based on visitors geospatial behaviour

“…Other useful information could be extracted from different reviews of the same place. The most common approach is to use sentiment analysis to evaluate hotel ratings [12,20]. There have also been studies dealing with the correlation between hotel star-rating and review rating [18].…”