Given only the URL of a web page, can we identify its topic? This is the question that we examine in this paper.Usually, web pages are classified using their content [7], but a URL-only classifier is preferable, (i) when speed is crucial, (ii) to enable content filtering before an (objectionable) web page is downloaded, (iii) when a page's content is hidden in images, (iv) to annotate hyperlinks in a personalized web browser, without fetching the target page, and (v) when a focused crawler wants to infer the topic of a target page before devoting bandwidth to download it.We apply a machine learning approach to the topic identification task and evaluate its performance in extensive experiments on categorized web pages from the Open Directory Project (ODP). When training separate binary classifiers for each topic, we achieve typical F-measure values between 80 and 85, and a typical precision of around 85.We also ran experiments on a small data set of university web pages. For the task of classifying these pages into faculty, student, course and project pages, our methods improve over previous approaches by 13.8 points of F-measure.

Given only the URL of a Web page, can we identify its topic? We study this problem in detail by exploring a large number of different feature sets and algorithms on several datasets. We also show that the inherent overlap between topics and the sparsity of the information in URLs makes this a very challenging problem. Web page classification without a page’s content is desirable when the content is not available at all, when a classification is needed before obtaining the content, or when classification speed is of utmost importance. For our experiments we used five different corpora comprising a total of about 3 million (URL, classification) pairs. We evaluated several techniques for feature generation and classification algorithms. The individual binary classifiers were then combined via boosting into metabinary classifiers. We achieve typical F-measure values between 80 and 85, and a typical precision of around 86. The precision can be pushed further over 90 while maintaining a typical level of recall between 30 and 40.

Abstract. Invenio is the web-based integrated digital library system developed at CERN. Within this framework, we present four types of ranking models based on the citation graph that complement the simple approach based on citation counts: time-dependent citation counts, a relevancy ranking which extends the PageRank model, a time-dependent ranking which combines the freshness of citations with PageRank and a ranking that takes into consideration the external citations. We present our analysis and results obtained on two main data sets: Inspire and CERN Document Server. Our main contributions are: (i) a study of the currently available ranking methods based on the citation graph; (ii) the development of new ranking methods that correct some of the identified limitations of the current methods such as treating all citations of equal importance, not taking time into account or considering the citation graph complete; (iii) a detailed study of the key parameters for these ranking methods.

No abstract

No abstract