To make users feel a specific impression, a number of studies have provided a way to estimate product impressions with physical features. Although the methodologies of these studies are useful in a wide range of areas, they require a large number of evaluation experiments to reveal the relation between them, and their costs are very high. To solve them, we proposed a method to score each product on the important impression of its domains. This consists of categorizing evaluation terms into internalized and externalized evaluation by using the appraisal dictionary, discovering the important impressions by using only externalized evaluations, and conclusively scoring these product impressions numerically from the term-score and affinity of words. The result of the verification experiment indicated that the obtained scores are valid in terms of their correlations with people's evaluation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.