Influence of Explainable Artificial Intelligence (XAI) in the acceptance of online product recommendations

Abstract

The latest advances in artificial intelligence have produced increasingly personalized online product recommendations for consumers. However, the models underlying these recommendations are often perceived as "black boxes" and raise ethical issues. In the first part of this thesis, after a brief introduction, a review of the literature identified that the use of explanations could help solve these ethical and comprehension problems. However, to date, very few experiments have been conducted in the area of explanation of online product recommendations. To fill this gap, a quantitative study was conducted with Belgian consumers. At the end of this thesis, the analysis of the results has identified that certain types of explanations can be exploited so that consumers trust the system using artificial intelligence and accept to receive recommendations.

Date of Award	29 Nov 2021
Original language	English
Awarding Institution	University of Namur
Supervisor	Wafa Hammedi (Supervisor)