基于用户生成内容的产品搜索模型

A Product Search Model Based on User Generated Content

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。

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 product＇s 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.