Increasing the expressive power of task analysis: Systematic comparison and empirical assessment of tool-supported task models

Task analysis is a critical step in the design process of interactive systems. The large set of task models available today may lead to the assumption that this step is well supported. However, very few task models are tool-supported. And in this latter category, few of them are based on a clear semantics (in this article, the word semantics is used with the following definition: “the meaning of a word, phrase, sentence, or text” from Compact Oxford English Dictionary®). This paper focuses on tool-supported task models and provides an assessment of the features that have been considered as essential in task modelling. It compares the different tool-supported methods, and evaluates the actual use of these features in K-MADe, a tool aimed at contributing to the incorporation of ergonomics into the design process of interactive systems through activity and task analysis. The originality of the K-MADe tool is to be based on a model whose expressive power lies on computable syntax while trying to be usable by every modelling knowledge designer. This facilitates task description and analysis, but also model query and the migration within software engineering models and software lifecycle steps. Evaluation results demonstrate the usefulness of an increased expressive power for task models, and their acceptance by users. They also enlighten some weaknesses in the K-MAD method and suggest further improvements.

Research highlights
► To represent real-life activities, task models must integrate the concepts of tasks, objects, actors and events.
► Computable attributes in task model tools are mandatory but they are difficult to be used.
► K-MAD includes computable aspects that provide the simulation of the more realistic models that take into account conditions, events and evolutions of the state-of-the-world.
► On task modelling, The use of computable aspects are easier (using K-MADe) for computer scientists than for others.