A Combination Approach to Web User Profiling

Abstract

In this article, we study the problem of Web user profiling, which is aimed at finding, extracting, and fusing the “semantic”-based user profile from the Web. Previously, Web user profiling was often undertaken by creating a list of keywords for the user, which is (sometimes even highly) insufficient for main applications. This article formalizes the profiling problem as several subtasks: profile extraction, profile integration, and user interest discovery. We propose a combination approach to deal with the profiling tasks. Specifically, we employ a classification model to identify relevant documents for a user from the Web and propose a Tree-Structured Conditional Random Fields (TCRF) to extract the profile information from the identified documents; we propose a unified probabilistic model to deal with the name ambiguity problem (several users with the same name) when integrating the profile information extracted from different sources; finally, we use a probabilistic topic model to model the extracted user profiles, and construct the user interest model. Experimental results on an online system show that the combination approach to different profiling tasks clearly outperforms several baseline methods. The extracted profiles have been applied to expert finding, an important application on the Web. Experiments show that the accuracy of expert finding can be improved (ranging from +6% to +26% in terms of MAP) by taking advantage of the profiles.

Review and Analysis of Machine Learning and Soft Computing Approaches for User Modeling

“…al. [9] used SVM for identifying the homepage of a person, and to define features where whether the title of the page contains the person name and whether the URL address (partly) contains the person name. Gershman et.…”

Intelligent information processing for building university knowledge base

“…Arnetminer relies on rich researcher description created by Web user profiling, i.e. finding, extracting and fusing the "semantic-based" user profile from various Internet sources (Tang et al 2010).…”

“…To deal with the disambiguation problem, as a starting point we used the algorithm proposed by Tang et al (2010), which consists in grouping publications with matching authors' first and middle names, and then clustering each group, taking into account co-authorship, citations, extended co-authorship, and user restrictions. When comparing this with the original algorithm, for the distance measure in the clustering algorithm we added the similarity of the titles, as it is known that scientists often use the same words in their publication titles.…”

Identifying Transformative Scientific Research

“…The other dataset is the DBLP-Citation-network V5 (DBLP) available at Arnetminer.org [19], [20], [21], [22], which consists of two major computer science bibliographic datasets, DBLP and ACM, covering publications from 1936 to 2011. The DBLP dataset contains some of the important papers in computer science that describe widely used techniques and algorithms.…”