Ranking based on user comments with multiple criteria: the case of Greek restaurants in Athens

Dimitrios Novas, Dimitrios Papakyriakopoulos, Elizabeth Powlesland-Kartaloglou and Anastasia Griva

International Journal of Multicriteria Decision Making, 2023, vol. 9, issue 3, 204-230

Abstract: User generated content (UGC) is a valuable resource for the multi-criteria decision-making process. Platforms, such as TripAdvisor, enable the registration of comments and post rankings. However, existing ranking mechanisms are not transparent, making it impossible to evaluate their integrity and accuracy. Additionally, it has been shown that these rankings are, in some cases, inaccurate and misleading. This prompted the need for developing a ranking mechanism based on UGC to capture experiences and feelings, rather than quantitative data (bubbles/stars). The proposed ranking mechanism employs LDA to generate topics, which are transformed with fuzzy logic to variables, used to produce ranking results. We empirically studied the proposed ranking mechanism using TripAdvisor's user comments on a sample of restaurants located in Athens, Greece and compared the results to a simple quantitative ranking scheme. In some cases, the ranking differed. Further investigation is needed to address the limitations encountered in this research.

Keywords: multi-criteria analysis; text mining; TripAdvisor; ranking; fuzzy numbers; restaurants. (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=134135 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijmcdm:v:9:y:2023:i:3:p:204-230

Access Statistics for this article

More articles in International Journal of Multicriteria Decision Making from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().