基于向量空间模型的个性化网页搜索算法研究

为解决信息检索时不同用户对搜索结果有不同期望的问题，提出了一种基于向量空间模型的个性化网页搜索算法。针对用户不同兴趣，利用用户画像能够更加全面地表示用户兴趣的特点，通过向量空间模型建立用户画像来表达用户兴趣，结合传统的网页排序算法得出最终的网页排序结果。对于不同用户可得到不同的网页搜索结果，排序靠前的网页中符合用户兴趣的网页数量增多。通过对模拟网页搜索实验结果的分析，证明所提算法较传统PageRank算法在个性化网页搜索方面有所提高。

Research on Personalized Web Search Algorithm Based on Vector Space Model

In order to solve the problem that different users have different expectations for search results in information retrieval, a personalized web search algorithm based on vector space model was proposed.In view of the different interests of users, user portraits could more comprehensively express the characteristics of user interests. The vector space model was used to establish user portraits to express user interests, combined with traditional web page ranking algorithms to obtain the final web page ranking results. Different web search results could be obtained for different users, and the number of web pages that meet user interests increases in the top ranking web pages. Through the analysis of the experimental results of simulated web search, it was proved that this algorithm was better than the traditional PageRank algorithm in personalized web search.