Enhancing Restaurant Management through Aspect-Based Sentiment Analysis and NLP Techniques.

This paper presents a flexible and automated methodology for extracting and analyzing customer sentiment in the restaurant industry through online reviews. The proposed approach is evaluated on a sample dataset of 1000 reviews, as well as applied within an accompanying web application that utilizes a large corpus of 880,000 reviews from 1581 restaurants located in the Algarve region. By leveraging advanced Natural Language Processing (NLP) techniques such as Aspect-Based Sentiment Analysis (ABSA), this study seeks to accurately classify customer sentiments according to specific attributes related to food quality, service, ambiance, pricing and location. To assess its performance against human classification processes, the results demonstrate that the proposed methodology effectively replicates them with three alternative approaches for attribute extraction and classification being presented; among which BART model consistently outperforms DeBERTa while ChatGPT achieves highest F1 Score. Named RestMON Algarve, the developed web application will allow restaurant managers to extract and analyze customer sentiment from online reviews; track attribute evolution over time; compare performance between competing restaurants - thus providing relevant insights into enhancing customer satisfaction levels leading towards overall success in hospitality industry. [ABSTRACT FROM AUTHOR]

Copyright of Procedia Computer Science is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)