Without achieving a clear understanding of the learning domain, it is difficult to develop a successful serious game that enables users to achieve the desired learning outcomes. Thus, the first step in serious game design is to establish an understandding of the particular learning domain, usually through consultation with domain experts. Whilst game design is inherently a creative process, we believe the capturing of the knowledge domain can be systematised and we present a structured approach to knowledge elicitation and representation as a basis for serious game design. We have adapted and extended the applied cognitive task analysis (ACTA) method and have combined it with additional knowledge representation frameworks. We explain how the outputs of this approach can inform the game mechanic and the development of non-player characters, and apply it to the design of a serious game aimed at reducing time-to-competence in soft project management skills for professionals working in corporate environments. A total of 26 domain experts from five different countries were involved in a two-stage interview process. The interviews yielded more than 300 task elements, and information about the cognition underlying the more challenging tasks. This data was incorporated into several representation frameworks and used to indicate features to be implemented in the game and the game mechanics of the supported features.
Contextual word embedding techniques for semantic shift detection are receiving more and more attention. In this paper, we present What is Done is Done (WiDiD), an incremental approach to semantic shift detection based on incremental clustering techniques and contextual embedding methods to capture the changes over the meanings of a target word along a diachronic corpus. In WiDiD, the word contexts observed in the past are consolidated as a set of clusters that constitute the "memory" of the word meanings observed so far. Such a memory is exploited as a basis for subsequent word observations, so that the meanings observed in the present are stratified over the past ones.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.