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

Autor(es)

Santos, Gustavo ^[1] ; Mota, Vinicius F. S. ^[2] ; Benevenuto, Fabricio ^[3] ; Silva, Thiago H. ^{[1, 4, 5]}

Afiliação do(s) autor(es)

^[1] Univ Tecnol Fed Parana, Curitiba, Parana - Brazil

^[2] Univ Fed Espirito Santo, Vitoria, ES - Brazil

^[3] Univ Fed Minas Gerais, Belo Horizonte, MG - Brazil

^[4] Univ Toronto, Toronto, ON - Canada

^[5] Silva, Thiago H., Univ Toronto, Toronto, ON, Canada.Santos, Gustavo, Univ Tecnol Fed Parana, Curitiba, Parana - Brazil

• Tipo de documento: Artigo Científico
• Fonte: SOCIAL NETWORK ANALYSIS AND MINING; v. 10, n. 1 JUN 10 2020.
• Citações Web of Science: 0

Resumo

Information and communications technologies have enabled the rise of the phenomenon namedsharing 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. (AU)

• Processo FAPESP: 18/23011-1 - GoodWeb: uso de sensoriamento social para aprimorar a qualidade de vida em cidades e alavancar novos serviços
• Beneficiário: Thiago Henrique Silva
• Modalidade de apoio: Auxílio à Pesquisa - Regular