Classification of Product Categories Based on Onomatopoeia Words in Product Reviews Using Cluster Analysis
-
- Uchida Yuzu
- Hokkai-Gakuen University
-
- Araki Kenji
- Graduate School of Information Science and Technology, Hokkaido University
Bibliographic Information
- Other Title
-
- クラスタ分析を用いた商品レビューに含まれるオノマトペに基づく商品カテゴリの類型化
Description
Nowadays, there are a number of product reviews on the Internet with the development of the consumer generated media as typified by social networking sites, blogs, and customer review sites. These reviews influence a consumer's buying decision and a company's market research. They are a lot valuable to both customers and companies, so that sentiment analysis becomes an active area of research. A sentiment polarity dictionary is essential to the sentiment analysis. We focus attention on onomatopoeia words in product reviews. It is noted that product reviews written by consumers in Japanese contain many onomatopoeia words. Japanese onomatopoeia can convey a subtle sense of features of products and customer's emotion. It is assumed that each onomatopoeia word in a product review provides a valuable clue to understanding a consumer's opinion. In this paper, we describe the appearance frequency of onomatopoeia words. After analysis of 729,865 reviews from Yahoo! Shopping, it is found that 482 words appeared in 52,121 reviews. We classify product categories in terms of the appearance frequency of onomatopoeia words with hierarchical cluster analysis and extract 978 pairs of product categories and onomatopoeia words which are likely connected to each other. Ten subjects judge the validity of these 978 pairs and consequently we conclude that 658 pairs are deemed appropriate for sentiment analysis. Further examination reveals the following two points: (1) it is highly possible that impressions of each product are described in the reviews containing onomatopoeias; and (2) the sentiment polarity of onomatopoeia differs depending on product categories.
Journal
-
- Transactions of the Japanese Society for Artificial Intelligence
-
Transactions of the Japanese Society for Artificial Intelligence 30 (1), 246-256, 2015
The Japanese Society for Artificial Intelligence
- Tweet
Details 詳細情報について
-
- CRID
- 1390001205108002304
-
- NII Article ID
- 130004927368
-
- ISSN
- 13468030
- 13460714
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
- OpenAIRE
-
- Abstract License Flag
- Disallowed