Artificial intelligence applications in fake review detection: Bibliometric analysis and future avenues for research

Abstract

Artificial intelligence (AI) and machine learning (ML) are emergent tools for fake review detection. This study provides a comprehensive overview of AI applications in fake review detection, using a hybrid integrated review and by combining bibliometric analysis with a framework-based review: the 4Ws (What, Where, Why, and How). We draw on the thematic structure of AI and ML research in fake review detection for the 2012–2021 period by conducting bibliometric coupling, keyword co-occurrence, and conceptual thematic, social network, and cluster-based content analyses of scientific articles. The findings indicate that field research has thus far concentrated on three overarching groups of fake review detection: (a) word of mouth, quality, reputation, and price; (b) classification, moderating role, intention, and analytics; and (c) impact and participation. This article provides researchers, companies and policymakers with insights into how AI can detect fraudulent reviews and drives further research on the adequate use of advanced AI techniques in fake review detection.