Are customer star ratings and sentiments aligned? A deep learning study of the customer service experience in tourism destinations

Abstract

This study explores the consistency between star ratings and sentiments expressed in online reviews and how they relate to the different components of the customer experience. We combine deep learning applied to natural language processing, machine learning and artificial neural networks to identify how the positive and negative components of 20,954 online reviews posted on TripAdvisor about tourism attractions in Venice impact on their overall polarity and star ratings. Our findings showed that sentiment valence is aligned with star ratings. A cancel-out effect operates between the positive and negative sentiments linked to the service experience dimensions in mixed-neutral reviews.

Understanding crowding perceptions and their impact on place experience: Insights from a mixed‐methods study

“…In the destination context, electronic word‐of‐mouth has been defined as informal communications made by tourists to inform others about the characteristics and use of tourism services and their providers through the internet (i.e., online platforms enabling social interaction, integrated tourism websites, social networks) (Litvin et al, 2018). Past studies have identified references to crowding in travel‐focused electronic word‐of‐mouth (Bigné et al, 2023; Buzova et al, 2019, 2020; Zanibellato et al, 2018). For example, in the cruise ship destination context, Buzova et al (2019) showed that visitors who perceive crowding during their visits tend to make unfavorable comments about their experiences on social media and integrated tourism websites (e.g., discouraging visits to the port of call, or certain attractions).…”

“…For example, in the cruise ship destination context, Buzova et al (2019) showed that visitors who perceive crowding during their visits tend to make unfavorable comments about their experiences on social media and integrated tourism websites (e.g., discouraging visits to the port of call, or certain attractions). Bigne et al (2023) also showed that negative online reviews about a destination were based mainly on perceptions of crowding or overcrowding. Based on the above evidence, we propose the following hypothesis:…”

Exploring Customer Review of Local Agriculture Product Acceptance in Malaysia: A Concept Paper on Sentiment Mining

“…It is proven ratings and reviews are significantly important to both businesses and customers during their purchases, but companies are losing sales, profits, and valuable information without ratings and reviews as their research demonstrated in the diagram below [55]. Similarly, results show a relationship between star rating and sentiments using deep learning via natural language processing, machine learning, and artificial neural networks [56].…”

Why are consumers dissatisfied? A text mining approach on Sri Lankan mobile banking apps

“…Apart from analyzing textual reviews, ratings and emojis have been of interest in deriving users' thoughts and emotions towards mobile apps. Bigne et al (2023) were concerned to find if the star ratings and the sentiment of the review of a customer are related. Although the results reveal that the star rating aligns with the overall sentiment of the review, the authors consider that there can be different dimensions of customer experience in a specific service.…”

“…By manual observation, it was revealed that, most of the neutral reviews were biased towards the negative or positive polarity. As (Bigne et al, 2023) mention, although consumers place a star rating as 3, in the review, either the positive or negative aspects get canceled out or the consumer gets biased towards a certain dimension which he is interested in discussing more about. Besides, there were entries where the sentiment of the text content is gainsaid to the sentiment of the rating.…”