An empirical characterisation of file retrieval

Retrieving files on personal computers is a fundamental component of interaction, yet there is surprisingly little empirical data characterising how it is carried out in realistic settings. We developed software, called FileMonitor, to dynamically record users׳ file retrieval activities, including data describing the files retrieved and the tools used to retrieve them. We then deployed the system in a four week log study of 26 participants׳ actual file retrievals on their personal computers. Follow-up interviews contextualised the findings. Results are presented in two sections focusing on the files (the number of files, patterns of revisitation, file types, etc.) and on the interface mechanisms used to retrieve them (file browsers, search tools, 'recent files' lists, etc.). We conclude by discussing implications for the design of next-generation file retrieval interfaces.