|
|||||
|
|
| 基于用户生成内容的产品搜索模型 | |
| 引用本文： | 王海雷,章彦星,赵海玉,张铭.基于用户生成内容的产品搜索模型[J].中文信息学报,2013,27(4):89-96. |
| 作者姓名： | 王海雷 章彦星 赵海玉 张铭 |
| 作者单位： | 1. 北京大学 光华管理学院,北京 100871; 2. 中国民生银行 博士后工作站,北京 100031; 3. 北京大学 信息科学技术学院,北京 100871 |
| 基金项目： | 自然科学基金资助项目，教育部科技发展中心专项研究资助课题资助博士点基金项目 |
| 摘 要： | 以消费者行为分析和离散选择的相关理论为基础,通过对用户生成内容进行特征粒度的情感分析,同时从产品的客观数据和用户生成的主观内容中提取模型特征,使用有监督的学习训练MNL模型预测产品的消费者剩余作为搜索排序的依据,并实现了手机、笔记本电脑和数码相机类的产品搜索系统。双盲实验表明,该文提出的产品搜索模型搜索效果比基准算法有显著的提高。 |
| 关 键 词： | 产品搜索 MNL模型 情感分析 特征选取 用户生成内容 |
A Product Search Model Based on User Generated Content |
|
| WANG Hailei , ZHANG Yanxing , ZHAO Haiyu , ZHANG Ming.A Product Search Model Based on User Generated Content[J].Journal of Chinese Information Processing,2013,27(4):89-96. | |
| Authors: | WANG Hailei ZHANG Yanxing ZHAO Haiyu ZHANG Ming |
| Affiliation: | 1. Guanghua School of Management, Peking University, Beijing 100871, China;2. Postdoctoral Workstation, China Minsheng Banking Corp. Ltd., Beijing 100031, China;3. School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China |
| Abstract: | Based on theories of consumer behavior analysis and discrete choice analysis, we perform the feature based sentiment analysis on user reviews with features selected from both objective product features and subjective user opinion data. Then we \ train a MNL model to predict products consumer surplus as the ranking criterion. With this method, we implemented product search engine for cell phone, laptop and digital camera. Double-blind trial on users shows that our model significantly outperforms the baselines. Key wordsproduct search; MNL model; sentiment analysis; feature selection; user generated content |
| Keywords: | product search MNL model sentiment analysis feature selection user generated content |
| 本文献已被 万方数据 等数据库收录！ | |
| 点击此处可从《中文信息学报》浏览原始摘要信息 | |
| 点击此处可从《中文信息学报》下载全文 | |