基于群体智慧的Web访问日志会话主题划分研究.pdfVIP

基于群体智慧的Web 访问日志会话主题划分研究* 方奇，刘奕群，张敏，茹立云，马少平 智能技术与系统国家重点实验室 清华信息科学与技术国家实验室（筹） 清华大学计算机系，北京，100084 E-mail: fangqi2003@ 摘 要：Web 访问日志中的会话（session ）是指特定用户在一定时间范围内的访问行为的连续序列。会话 中的主题（topic ）是指会话中具有相同用户意图的部分。将 session 进一步划分成能体现用户意图的处理 单元 （topic ）是进行用户访问行为分析的重要基础。目前相关工作主要集中在边界识别上，无法处理用户 意图交叉情况。为了解决该问题，本文重新形式化定义了session 和topic 的相关概念，提出最大划分的求 解任务，并设计出了基于用户群体智慧的会话主题划分算法。在使用大规模真实Web 访问日志的实验中， 我们的算法取得了不错的效果。 关键词：会话主题划分，Web 访问日志 Web Access Log Session Topic Segmentation Based on Wisdom of Crowds Qi Fang, Yiqun Liu, Min Zhang, Liyun Run, Shaoping Ma State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China E-mail: fangqi2003@ Abstract: A session in Web access log denotes a continuous-time sequence of user’s Web browsing behavior. A topic of a session represents a hidden browsing intent of a Web user. It is fundamental to split a session into several topic-based log units. Existing work mainly focuses on detecting boundaries without considering the common situation in which different topics often overlap in one session. In this paper, we first re-define the concept of session and topic, and then the task of largest segmentation is proposed. We further design the session topic segmentation algorithm based on crowd wisdom of Web users. The effectiveness of the algorithm is validated by the experiments performed on large scale of realistic Web access logs. Keywords: session topic segmentation, Web access log 1 引言 随着互联网技术的迅猛发展，Web 上存储的信息量日新月异。如今万维网已经