Purpose: The purpose of this paper is to discuss the process of analysing online discussion and argue for the merits of mixed methods. Much research of online participation and e-learning has been either message-focused or person-focused. The former covers methodologies such as content and discourse analysis, the latter interviewing and surveys. The paper discusses the strengths and weaknesses of these approaches in the context of a study of an online social educational network for gifted students. Design/methodology/approach: The design of this study included the use of content analysis, visualisation diagrams, interviews and questionnaire survey to understand the nature of online discussion and the experience of taking part. Findings: It was found that the message-focused analysis provided insight into participation and interaction patterns, whereas the surveys and interviews enabled access to members' preferences and attitudes. Originality/value: The contribution of the paper is to argue for a mixed approach in which different types of data can be compared and contrasted. While the use of mixed methods in social research in general has long been suggested, its adoption in the field of online learning is yet to be widely established, possibly because of its time-consuming and demanding nature. Despite these constraints, a mixed-methods approach is advocated, as it allows for a comprehensive picture of the use of the network and the experience of online participation.