What drives the helpfulness of online reviews? A deep learning study of sentiment analysis, pictorial content and reviewer expertise for mature destinations

Tourist destinations are increasingly affected by travel-related information shared through social media. Drawing on dual-process theories on how individuals process information, this study examines the role of central and peripheral information processing routes in the formation of consumers' perceptions of the helpfulness of online reviews of mature destinations. We carried out a two-step process to address the perceived helpfulness of usergenerated content, a sentiment analysis using advanced machine-learning techniques (deep learning), and a regression analysis. The database was 2023 comments posted on TripAdvisor about two iconic Venetian cultural attractions, St. Mark's Square (an open, free attraction) and the Doge's Palace (which charges an entry fee). Using deep-learning techniques, with logistic regression, we first identified which factors influenced whether a review received a helpful vote. Second, we selected those reviews which received at least one helpful vote to identify, through linear regression, the significant determinants of TripAdvisor users' voting behaviour. The results showed that reviewer expertise is influential in both free and paid-for attractions, although the impact of central cues (sentiment polarity, subjectivity, pictorial content) differs for both attractions. Our study suggests that managers should look beyond individual ratings and focus on the sentiment analysis of online reviews, which are shown to be based on the nature of the attraction (free vs. paid-for).

Automated summary

This study explored the impact of online reviews on tourists' helpfulness evaluations using deep learning techniques and statistical regression analysis. It found that reviewer expertise plays a role in both free and paid-for attractions, while sentiment polarity, subjectivity, and pictorial content also influence users' voting behavior.