Computer Engineering and Applications ›› 2015, Vol. 51 ›› Issue (8): 245-249.

Previous Articles     Next Articles

Evaluating user satisfaction of search engine using click log

DENG Xiaomei, WU Gang   

  1. School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China
  • Online:2015-04-15 Published:2015-04-29

基于点击日志的搜索引擎用户满意度评价研究

邓晓妹,武  刚   

  1. 北京林业大学 信息学院,北京 100083

Abstract: To solve the problem that traditional search engine evaluation method is of large cost and low efficiency, this paper presents a method to evaluate the user satisfaction of search engine based on user click log in this paper. Based on the analysis of search engine user click log, search result ranking, click rate and average browsing time are selected as indicators to estimate user satisfaction. Then it builds search engine evaluation models using linear regression analysis, logistic regression analysis and BP neural network method respectively. Experimental results verify the validity of the models by comparing the performance of different models.

Key words: search engine evaluation, user satisfaction, user click log, Back Propagation(BP) neural network

摘要: 针对传统的搜索引擎人工评价方法效率低、成本大的问题,提出一种利用用户点击日志来评价搜索引擎用户满意度的方法。通过分析搜索引擎的用户点击日志,选择网页搜索结果排名、网页点击率、网页平均浏览时间作为用户满意度特征,分别运用多元线性回归分析、多元对数回归分析和BP神经网络方法,建立了基于用户点击日志的搜索引擎用户满意度评价模型。结合具体的实验数据集,通过实验对线性回归模型、对数回归模型和BP神经网络模型的结果进行了比较与分析,验证了模型的有效性。

关键词: 搜索引擎评价, 用户满意度, 用户点击日志, 反向传播(BP)神经网络