@inproceedings{www2009135, booktitle = {18th International World Wide Web Conference}, month = {April}, title = {Purely URL-based Topic Classification}, author = {Eda Baykan and Monika Henzinger and Ludmila Marian and Ingmar Weber}, year = {2009}, pages = {1109--1109}, url = {http://www2009.eprints.org/135/}, abstract = {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 classi?ed using their content [7], but a URL-only classi?er is preferable, (i) when speed is crucial, (ii) to enable content ?ltering 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 identi?cation task and evaluate its performance in extensive experiments on categorized web pages from the Open Directory Project (ODP). When training separate binary classi?ers 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.} }