Food for Thought in Malaysian Borneo: Data Mining and Sentiment Analysis of Tripadvisor Reviews for Online Destination Branding

Abstract

Unique destination branding in tourism is crucial to gaining a competitive advantage. Local food is a significant component of a destination brand which Destination Management Organisations (DMOs) must integrate into their official marketing efforts. DMOs must monitor the popularity and perception of their food promotions against the competition. Online promotion and management are challenging due to the rise of user-generated content. Automatic data mining techniques were used to determine the extent to which tourist food choices on TripAdvisor matched foods promoted by DMOs and how distinct these choices were from a rival DMOs’ promotion. We compared online food promotion between the Sabah Tourism Board and the Sarawak Tourism Board. We developed a software system to automatically extract food branding business intelligence from TripAdvisor restaurant reviews. The application of web crawling and scraping technology was applied to extract data and use Sentiment Analysis for interpretation. Online foods promoted by DMOs for each region were found to contain only a few common dishes, but these were more popular than region-specific foods. Significantly different distributions of food choices were found for each region. Some potentially useful differences between foreign and domestic tourists and locals were also identified. Sentiment analysis revealed hidden information in reviews useful for potential food destination branding. Findings from TripAdvisor confirm practical suggestions for improving brand distinctiveness found in the literature. This study is the first to develop an actual system that DMOs could use to estimate the online popularity of their promoted foods and those of their competition.