Enrichment of semantic metadata based on interactions with user associations

More and more audio-visual information is available on the World Wide Web. There is an increasing amount of broadcast channels available. In such a situation, to attain a competitive advantage, content repositories must progress to collecting and managing knowledge about all types of information including films and TV programs. Semantic metadata is the most valuable one for the user who wants to get knowledge. It is usually created by a professional analyst in the labor-intensive activity. A new approach to the creation of semantic metadata including effective one is suggested. It is based on the collection of users' evaluation of audiovisual content. A cooperative interaction of a content repository and users associations results in the cooperative metadata enrichment. The main features of this method are: continuous evaluation in the course of time made by users associations with varying background, education and motivation; evaluation of different attributes of audiovisual events on different scales. Experiments were carried out to examine the approach suggested in the current paper. The aim of these experiments was to evaluate the emotional tension created by feature films' events and to select key frames of these events. The statistically proven results of these experiments. confirmed that users with different age (from children to adults) and varying background, education and motivation can indicate emotional tension on different scales (scales based on complexity or informational attributes, on the degrees qf interest and unpredictability of dramatic events). The story shapes made on the basis, of these experimental results look like ones made professional analysis. However regular dependences between users' profiles and their preferences were detected. It means that this method can be used to of efficiently create different types of summaries for different types of TV viewers and the Internet use.(1).