Online comments are increasingly mentioned as an important source of information, simplifying consumers' buying decisions. Online user-generated content has become one of the main sources of information for tourists, who themselves become creators of their own online content. This chapter focuses on sentiment analysis of comments made on TripAdvisor regarding one resort located in the Algarve region, in Portugal. The resort has good reviews, which means that the eWOM is positive. The highest scores relate to the resort's cleanliness, location and quality of sleep, and those that were less relevant were the value for money, the rooms and the service. The most dominant emotion is joy, followed by an analytical response. Negative emotions, such as sadness and anger, were not found very often in the online reviews. These results could be explained by the quality of the service, the kindness of the staff, the facilities for children, the entertainment, and the location, attributes that were often highlighted in the comments.
TopIntroduction
The Internet has become an essential tool for any user, either on a personal or on a professional level. The rapid evolution of information and communication technologies (ICT) has given rise to Web 2.0, mainly characterized by user-generated content (UGC), or electronic word of mouth (eWOM). Companies used to control the information they wanted to share, now users determine the information they want to see and to consume (Limberger, Anjos, Meira, & Anjos, 2014).
In tourism, social media predominates in terms of knowledge and information sharing, being recognized as an innovative knowledge sharing tool (e.g. product reviews, market trends, restaurant and hotel reviews, and travel blogs), allowing users to interconnect, share the desired information and interact with other users (Gaál, Szabó, Obermayer-Kovács, & Csepregi, 2015). This type of user-generated content allows to reach a greater number of users in a shorter time, eliminating restrictions of time, location and speed during the exchange of information. On the other hand, it can affect purchasing decisions, as well as consumer perceptions of product quality, since most of the comments on online platforms serve to recommend or discourage a product (Limberger et al., 2014).
Sentiment analysis can be applied to user-generated content, such as online reviews, survey responses and social media, aiming to identify ideas and opinions about a particular subject or event, classifying and quantifying them as positive, negative or neutral (Liu, 2015). Pang and Lee (2008) state that there are numerous companies in the world, especially in the United States, that provide sentiment analysis services on the Internet. It is considered that through sentimental analysis, e-commerce benefits can be realized, and companies tend to promote their products more on a website, blog or social networks. Organizations will have other benefits such as ease of designing marketing strategies, improved security policies, accurate perception of a product / service by a customer, among others.
Studies on sentiment analysis are still relatively scarce (e.g. Freitas & Vieira, 2015; Neethu & Rajasree, 2013; Pak & Paroubek, 2010; Serrano-Guerrero, Olivas, Romero, & Herrera-Viedma, 2015; Valdivia, Luzón, & Herrera, 2017), thus, this study aims to provide a contribution in the tourism sector. This chapter focuses on sentiment analysis of comments made on TripAdvisor regarding one resort located in the Algarve region, in Portugal. In general, this study aims to identify: (i) the profile of the visitor; (ii) the general and specific evaluation for each category of the resort; and (iii) the emotional intonations of the visitors’ comments. The methodology of the study is based on qualitative and quantitative analysis of secondary sources, i.e. comments posted by customers on TripAdvisor. A sample of 294 comments was used to perform the sentiment analysis, using IBM Watson Tone Analyzer. After this analysis, results were imported on IBM SPSS v. 25, where univariate and bivariate analyses were performed.
The chapter is organized as follows: first, the literature on social media and tourism is reviewed, following which user-generated content and eWOM are addressed. Subsequently, the methodology used for the empirical study is described in more detail. Finally, research findings are reported and discussed, and their implications for further research and applications are highlighted.