Classification of Product Categories Based on Onomatopoeia Words in Product Reviews

Abstract

Nowadays, there are a number of product reviews on the Internet. Product reviews written by consumers contain many onomatopoeia words which describe features of each product or consumer's emotions. It is assumed that each onomatopoeia word in a product review provides a valuable clue to a consumer's thoughts. In this paper, we describe the appearance frequency of onomatopoeia words in 729,865 reviews from Yahoo! Shopping. In addition, we classify product categories in terms of the appearance frequency of onomatopoeia words with hierarchical cluster analysis.