User modelling for evaluation of direct manipulation interfaces

This thesis applies models of user action to usability evaluation of direct manipulation interfaces. In particular, the utility of a Model of Action for assisting novice evaluators in usability tests is investigated. An initial model of user action is proposed, based on the theory of action proposed by Norman (1986). This model includes a description of knowledge sources used in interaction, error types and user responses to errors. The model is used to interpret data on user behaviour and errors in an empirical study of MacDraw I. This study used the Protocol Analysis technique proposed by Ericsson and Simon (1984). Protocol evidence shows that the search and specification stages of user action could usefully be treated as separate in terms of user knowledge recruitment and the nature of system support. The Model of Action is then expanded and modified to account for the empirical findings. The new model distinguishes knowledge-based, rule-based and skill-based processing in Direct Manipulation (DM) interaction, using the distinction drawn by Rasmussen (1986). These processing levels are explicitly linked to types of presentation technique and categories of user error. This is developed into a technique for determining system causes of usability problems. A set of mental dialogue tokens (roles) are developed to assist novice evaluators in the interpretation of error causes. Roles are linked to types of user error in the cycle of action in a diagnostic model. This model forms the basis of a budget method for use by novice evaluators, named Model Mismatch Analysis (MMA). These developments are tested by a two-tier study of user performance on Microsoft Word. The empirical evidence validated the taxonomy of errors, and tests the utility of five retrospective data analysis techniques. A study of novice evaluator performance is reported, comparing the MMA method to the Usability Checklist proposed by Ravden and Johnson (1989). The MMA method is shown to be the more efficient approach. To summarise, models of Direct Manipulation action are shown to assist novice evaluators both in the diagnosis of usability problems, and the selection of remedies