Neutrality may matter: sentiment analysis in reviews of Airbnb, Booking, and Couchsurfing in Brazil and USA

• Published in: Social network analysis and mining Vol. 10; no. 1; p. 45
• Main Authors: Santos, Gustavo, Mota, Vinicius F. S., Benevenuto, Fabrício, Silva, Thiago H.
• Format: Journal Article
• Language: English
• Published: Vienna Springer Vienna 01.12.2020; Springer Nature B.V
• Subjects: Applications of Graph Theory and Complex Networks; Communications technology; Computer Science; Data mining; Data Mining and Knowledge Discovery; Decision making; Economics; Game Theory; Humanities; Information technology; Law; Methodology of the Social Sciences; Neutrality; Original Article; Product reviews; Ratings & rankings; Sentiment analysis; Sharing economy; Social and Behav. Sciences; Social networks; Statistics for Social Sciences; Volunteers; Brazil; United States > US; Sentiment analysis; Text analysis; Booking; Reviews; Airbnb; Couchsurfing
• ISSN: 1869-5450; 1869-5469
• DOI: 10.1007/s13278-020-00656-5

Information and communications technologies have enabled the rise of the phenomenon named sharing economy , which represents activities between people, coordinated by online platforms, to obtain, provide, or share access to goods and services. In hosting services of the sharing economy, it is common to have a personal contact between the host and guest, and this may affect users’ decision to do negative reviews, as negative reviews can damage the offered services. To evaluate this issue, we collected reviews from two sharing economy platforms, Airbnb and Couchsurfing, and from one platform that works mostly with hotels ( traditional economy ), Booking.com, for some cities in Brazil and the USA. Through a sentiment analysis, we found that reviews in the sharing economy tend to be considerably more positive than those in the traditional economy. This can represent a problem in those systems, as an experiment with volunteers performed in this study suggests. In addition, we discuss how to exploit the results obtained to help improve users’ decision making.