Data-driven digital nudging: a systematic literature review and future agenda

Abstract

ABSTRACT Nudging, a concept rooted in behavioural economics, aims to influence decision-making for individuals’ benefit through non-coercive methods. While initially investigated in real-world contexts, the rise of digital devices has led to the emergence of digital nudging (DN), an area of research examining nudging techniques within digital environments. Integrating smart technologies, Big data analysis, and artificial intelligence (AI) algorithms with DN has garnered attention from Information Systems (IS) scholars and practitioners. Given the evolving and fragmented nature of research in this area, a Systematic Literature Review (SLR) was conducted to analyze data-driven DN literature. In this regard, 57 peer-reviewed papers were selected and analyzed to answer four research questions. The review begins by defining and outlining the characteristics of data-driven DN. It then identifies critical data sources for nudging interventions: user profiles, social media, and contextual data. Additionally, four closely intertwined categories of studies were explored: (1) Personalised nudging, (2) Big data-driven nudging, (3) AI-driven nudging, and (4) DN with recommender systems. The review also highlights challenges and issues within the field and concludes with a discussion on future research directions. This study provides a comprehensive perspective on the data-driven DN status quo and sheds light on relevant promising research agendas.