Citation

Sekar A, Chen RB, Cruzat A, Nagappan M. Transp. Res. Rec. 2017; 2666: 10-18.

Copyright

(Copyright © 2017, Transportation Research Board, National Research Council, National Academy of Sciences USA, Publisher SAGE Publishing)

DOI

10.3141/2666-02

PMID

unavailable

Abstract

As the market penetration of mobile information and communication technologies continues to grow, visitor feedback, such as online reviews of locations or sites visited, will continue to grow in parallel at finer temporal and geographic scales. This growth in data opens the opportunity for travel demand analysts to assess location attractiveness on the basis of online reviews and subsequently inform destination choice models. In geography and urban planning, the construct of sense of place (SOP) has emerged as an indicator for visitor association or connection with a place or site. An opportunity exists for examining SOP through the lens of text mining (i.e., extracting information from online text reviews and forming digital narratives of place). Several websites devoted to sharing feedback on experiences and overall perceptions exist, including Yelp and TripAdvisor. With text-mining methods, previously unidentified SOP-related topics and issues may emerge from online reviews and serve as a basis for subsequent analysis. The results from this study indicate that these emerging topics or terms require more contextual information and interpretation. As a stand-alone method, text mining is insufficient for identifying SOP topics, given the complexity of dimensions that characterize SOP. In addition, the results suggest that timing and seasonality play an important role in visitors' evaluation of a site; these factors have received less attention in the literature. With respect to text mining as a methodology to gain insights into SOP and supplement existing travel analysis, several barriers exist, including interpretation of topics from topic models. Nonetheless, these approaches are promising and require more research to guide practical implementation for inferring SOP from online text reviews and integration with existing travel analysis approaches.

Language: en