Peeking inside the minds of tourists using a novel web analytics approach

Abstract

In the era of social media and travel websites, tourists increasingly post reviews about their travel experiences. These posts influence the travel plans and decisions of new tourists and hence; their content is important for businesses and governments. The purpose of this study is to propose a model to investigate tourists’ perceptions and underlying reasons for posting respective content on travel websites. A web analytics-based approach is proposed to conduct in-depth analyses of the data extracted from such websites and generate meaningful in sights. A combination of sentiment analysis and topic modeling through the Latent Dirichlet Allocation and machine learning algorithm is used for analyzing the data. The application of the proposed model is illustrated in the case of Goa, India. Findings reveal that the lack of cleanliness, safety, parking, price, facilities, and services are pertinent topics leading to negative sentiments. These topics also corroborate the social and economic events that took place during the period of study. Further clustering of tourist destinations across Goa reveals the presence of similar dissatisfiers. The above findings can be used for deciding the strategy for remedial action by relevant stakeholders. Moreover, the model can automatically classify and analyze future reviews in real-time.