International Journal of Affective Engineering
Online ISSN : 2187-5413
ISSN-L : 2187-5413
Original Articles
Using Feature Values of Statements to Improve the Estimation Accuracy of Factor Scores of Impressions of Question and Answer Statements
Yuya YOKOYAMATeruhisa HOCHINHiroki NOMIYA
Author information
JOURNAL FREE ACCESS

2014 Volume 13 Issue 1 Pages 19-26

Details
Abstract

In order to eliminate mismatches between the intentions of questioners and respondents of Question and Answer sites, we have experimentally evaluated the impressions of 60 questioners and their responses posted at Yahoo! Chiebukuro. By applying factor analysis to the scores of the experiment, the impression of the statements could be captured by nine factors. Factor scores of other features are interpreted as syntactic information, word imageability, and closing sentence expressions. As a result, the overall estimation accuracy is good: the accuracy of the estimated values of seven factors is good, while that of the other two factors is fairly good. The estimation accuracy of these two factors should be improved. This paper improves the estimation accuracy by adopting new feature values of statements: word familiarity and notation validity. We show that the estimation accuracy can sufficiently be improved by using them as well as the conventional feature values.

Content from these authors
© 2014 Japan Society of Kansei Engineering
Previous article Next article
feedback
Top