Extracting Opinions Relating to Consumer Electronic Goods from Web Pages

被引：0

作者：

Nakamura, Taichi ^{[1
]}

Maruyama, Hiroshi ^{[1
]}

机构：

[1] Tokyo Univ Technol, Tokyo, Japan

来源：

KNOWLEDGE-BASED SOFTWARE ENGINEERING | 2006年 / 140卷

关键词：

Elicitation; Web pages; Co-occurrence; Text Mining;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes a means of extracting the highly credible opinion ratings from Web pages. The principle behind our proposal is based on extracting the co-occurrence relation between a word representing a feature in the specification of a product or service produced by a company and a word showing a consumer's evaluation and then enlarging the dictionaries by registering additional words or phrases that appear in the co-occurrence relation.

引用

页码：206 / 209

页数：4