A multi‐layer contextual model for recommender systems in digital libraries

Purpose – The aim of this paper is to investigate contextual information that has an impact on the process of selection and decision making in recommender systems (RSs) in digital libraries. Design/methodology/approach – Using a grounded theory method of qualitative research, semi‐structured interviews were carried out with 22 information specialists, and IT and computer engineering students and professors. Data resulting from interviews were analysed in two stages using open coding, followed by axial and selective coding. Findings – The central idea (concept) developed in this study, named scientific research ground (SRG), is an information ground users step into with scholarly purposes. Within SRG they start interacting with information systems. SRG has contexts which situate users in a range of situations while interacting with information systems. Users' characteristics such as purpose, activity, literacy, mental state, expectations, and assumptions, occupational and social status are some contexts that should be taken into account for making a recommendation. Research limitations/implications – This study sought to explore contextual information in the academic community and the academic contextual information cannot be generalized to RSs in other environments such as e‐commerce. Practical implications – Identifying and implementing contextual information in information systems can help make better recommendations as well as improve interaction between users and information systems. Originality/value – Based on the SRG idea and its contexts, a multi‐layer contextual model for a recommender system is proposed.