۱- Introduction

۲- Theory and research hypotheses

۳- Data and approach

۴- Results and discussion

۵- Conclusions and implications

References

Abstract

Gamification is here to stay, and tourism and hospitality online review platforms are taking advantage of it to attract travelers and motivate them to contribute to their websites. Yet, literature in tourism is scarce in studying how effectively is users’ behavior changing through gamification features. This research aims at filling such gap through a data-driven approach based on a large volume of online reviews (a total of 67,685) collected from TripAdvisor between 2016 and 2017. Four artificial neural networks were trained to model title and review’s word length, and title and review’s sentiment score, using as input 12 gamification features used in TripAdvisor including points and badges. After validating the accuracy of the model for extracting knowledge, the data-based sensitivity analysis was applied to understand how each of the 12 features contributed to explaining review length and its sentiment score. Three badge features were considered the most relevant ones, including the total number of badges, the passport badges, and the explorer badges, providing evidence of a relation between gamification features and traveler’s behavior when writing reviews.

Introduction

Gamification has emerged as a powerful tool to provide an appealing environment through game-like features to build user attachment (Werbach & Hunter, 2012). Those features, which may include points or attractive badges, aim at exerting on each individual the desire to fulfill the needed accomplishments to be rewarded through recognition (Hamari & Koivisto, 2015). Gamification has been adopted in a wide array of contexts such as education, e-commerce, health, engineering, human resources, and tourism and hospitality, among others (Araújo & Pestana, 2017; Hamari, Koivisto, & Sarsa, 2014; Liu, Schuckert, & Law, 2015; Serna, Bachiller, & Serna, 2017). There is a hype surrounding gamification in several businesses (Dale, 2014), but the same does not happen specifically for tourism and hospitality online websites, as it was pointed out by Schuckert, Liu, and Law (2015), where the authors analyzed the impact of gamification in TripAdvisor. Nevertheless, those platforms clearly bet on this type of features, in an attempt of making them more appealing for users (e.g., Sigala, 2015). TripAdvisor and Airbnb are examples of those platforms, adopting points and badges’ systems to attract travelers to contribute with reviews and services (for the case of Airbnb). Therefore, research is needed to study gamification effects in tourism. Gamification empirical research traditionally adopts survey-based methods, focusing in a distinct group of characterizable individuals (Hamari et al., 2014). While this approach has the advantage of better framing the results and supporting the corresponding discussions drawn, it is narrowed to small groups, hindering generalizations (Gosling, Vazire, Srivastava, & John, 2004). Furthermore, many respondents are students, since researchers can easily access and persuade them to answer questionnaires, biasing results (Seaborn & Fels, 2015). This study takes a different step through a data-driven approach based on large volumes of information that were automatically collected from TripAdvisor. Reviews are freely written by travelers and express their direct opinions, without the need to persuade anyone to answer, who may rush anything just to be let alone (Calheiros, Moro, & Rita, 2017). Grounded on existing theory, this study raises and develops research hypotheses related to the influence of gamification features on the written online reviews about hotels. These hypotheses are evaluated through a data-driven empirical procedure focused on two specific review characteristics: the word length; and the sentiments expressed in it.