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

Authors: Enrique Bigne Carla Ruíz Antonio Cuenca Carmen Pérez Aitor García Pablos

Date: 04.03.2021

Journal of Destination Marketing & Management


Abstract

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 user-generated 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).

BIB_text

@Article {
title = {What drives the helpfulness of online reviews? A deep learning study of sentiment analysis, pictorial content and reviewer expertise for mature destinations},
journal = {Journal of Destination Marketing & Management},
pages = {100570},
volume = {20},
keywds = {
Perceived helpfulness, Dual-processing theory, User-generated content, Sentiment analysis, Deep learning, Mature destinations
}
abstract = {

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 user-generated 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).


}
doi = {10.1016/j.jdmm.2021.100570},
date = {2021-03-04},
}
Vicomtech

Parque Científico y Tecnológico de Gipuzkoa,
Paseo Mikeletegi 57,
20009 Donostia / San Sebastián (Spain)

+(34) 943 309 230

Zorrotzaurreko Erribera 2, Deusto,
48014 Bilbao (Spain)

close overlay

Behavioral advertising cookies are necessary to load this content

Accept behavioral advertising cookies