Study of Discussion Record Analysis Using Temporal Data Crystallization and Its Application to TV Scene Analysis

Abstract : Methods to analyze discussion records have been explored and a basic framework developed. Discussion records were analyzed by two methods -- Scene analysis and Logical analysis. Scene analysis focuses on topic change in the record and divides a record into several scenes using Temporal Data Crystallization (TDC). Then, by measuring the polarity of words and the volume of utterance, the atmosphere and emotion in the scene were analyzed. Logical analysis focuses on the role of phrases in utterances, and attaches logical labels to phrases based on Toulmin diagram. By these labels, logical structure of arguments in the discussion was extracted, its semantics were calculated based on Theory of Computational Argumentation and various argumentation skills of the discussion record was evaluated. In addition to discussion analysis, the scene analysis techniques were applied to caption data of TV programs to recognize change of scenes, which requires real time analysis.