AI-Driven Sentiment Analysis for Retail Management: A Graph-Based DSS Comparing Franchise and Company-Owned Stores

Analyse des sentiments basée sur l'IA pour la gestion du commerce de détail: un système d'aide à la décision par graphes comparant les magasins franchisés et les magasins en propriété directe

Jérôme Baray () and Gérard Cliquet ()
Additional contact information
Jérôme Baray: ARGUMans - Laboratoire de recherche en gestion Le Mans Université - UM - Le Mans Université
Gérard Cliquet: CREM - Centre de recherche en économie et management - UNICAEN - Université de Caen Normandie - NU - Normandie Université - UR - Université de Rennes - CNRS - Centre National de la Recherche Scientifique

Post-Print from HAL

Abstract: This paper introduces an AI-driven Decision Support System (DSS) for sentiment analysis of customer reviews in Starbucks UK. The methodology involves three main steps: collecting customer reviews from trusted sources, applying AI-driven preprocessing techniques to extract key attributes, and using Graph Machine Learning techniques to unveil customer satisfaction. A new Graph-Based Sentiment Analysis Algorithm is proposed to extract object–sentiment pairs from each comment and model relationships through a graph-based approach. Results indicate a superior performance in terms of accuracy and efficiency compared to cell-based methods. The analysis identifies drivers of customer satisfaction, including value for money, quality experience, and ambiance.

Keywords: customer reviews; customer satisfaction; franchising; natural language processing (NLP); semantic data processing; object-sentiment extraction; graph-based analysis; Graph Machine Learning; Avis clients; satisfaction client; franchise; traitement du langage naturel (NLP); traitement des données sémantiques; extraction objet-sentiment; analyse basée sur les graphes; apprentissage automatique par graphes (search for similar items in EconPapers)
Date: 2024-12-16
References: Add references at CitEc
Citations:

Published in Managerial and Decision Economics, 2024, ⟨10.1002/mde.4462⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

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:hal:journl:hal-04840524

DOI: 10.1002/mde.4462

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().