Authoring support by interactive genetic algorithm and case based retrieval

Abstract

Authoring work for multimedia contents is knowledge-lean work. Elementary school pupils frequently have difficult acquiring authoring skills, i.e. how to develop the idea or materials to be expressed, how to compose the materials of the outcome or contents. We focus on the problems of how to support authoring work to arrange materials in order to formulate ideas as the stories develop. The basic ideas behind the method are that (1) a basic story is automatically generated by genetic algorithm (GA) based operations and shown to a user as sequences of pictures, (2) an interactive GA is used to evaluate and select a preferred story, (3) the results are compared with previously stored stories using case-based techniques. Based on these ideas, we have developed a computer supported environment for this purpose and conducted related experiments.