[3Rin4] Interactive 1

[3Rin4-37] Extracting Kansei Evaluation Index Using Time Series Text Data: Examining Universality and Temporality

〇Runa Yamada¹, Sho Hashimoto¹, Noriko Nagata¹ (1.Kwansei Gakuin University)

Keywords:text mining, time series analysis, evaluation index

In recent years, attention has been paid to the value of sensibility in addition to the value such as function and price. Therefore, when designing the overall design, it is necessary to clarify the emotions and impressions of the evaluation target, it is assumed to constant regardless of time series when we express them quantitatively. Actually, impressions that are influenced by time-series and impressions that are used universally within a certain period are mixed, and it is necessary to deal with these separately. In this study, we work on the extraction of Kansei indexes that are influenced by time-series using time-series changes of the appearance frequency of evaluation words. This method was applied to the fashion field where time-series effects clearly exist. As a result, it was confirmed that there were two patterns of seasonal variation and four patterns of trend tendency in the impression of fashion in general, and multiple universal impressions were extracted.