Recommender systems for learning: Building user and expert models through long-term observation of application use

Information technology has recently become the medium in which much profess ional office work is performed. This change offers an unprecedented opportu nity to observe and record exactly how that work is performed. We describe our observation and logging processes and present an overview of the result s of our long-term observations of a number of users of one desktop applica tion. We then present our method of providing individualized instruction to each user by employing a new kind of user model and a new kind of expert m odel. The user model is based on observing the individual's behavior in a n atural environment, while the expert model is based on pooling the knowledg e of numerous individuals. Individualized instructional topics are selected by comparing an individual's knowledge to the pooled knowledge of her peer s.