[{"oa_version":"None","_id":"11673","publication":"ACM Transactions on the Web","scopus_import":"1","author":[{"last_name":"Baykan","full_name":"Baykan, Eda","first_name":"Eda"},{"orcid":"0000-0002-5008-6530","first_name":"Monika H","last_name":"Henzinger","full_name":"Henzinger, Monika H","id":"540c9bbd-f2de-11ec-812d-d04a5be85630"},{"last_name":"Marian","full_name":"Marian, Ludmila","first_name":"Ludmila"},{"last_name":"Weber","first_name":"Ingmar","full_name":"Weber, Ingmar"}],"date_published":"2011-07-01T00:00:00Z","title":"A comprehensive study of features and algorithms for URL-based topic classification","publication_identifier":{"eissn":["1559-114X"],"issn":["1559-1131"]},"type":"journal_article","article_processing_charge":"No","volume":5,"date_created":"2022-07-27T13:48:11Z","day":"01","date_updated":"2024-11-06T12:07:30Z","abstract":[{"text":"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.","lang":"eng"}],"fulldoi":"https://doi.org/10.1145/1993053.1993057","language":[{"iso":"eng"}],"month":"07","status":"public","article_type":"original","article_number":"15","keyword":["Topic classification","URL","ODP"],"extern":"1","intvolume":"         5","issue":"3","publisher":"Association for Computing Machinery","quality_controlled":"1","doi":"10.1145/1993053.1993057","year":"2011","publication_status":"published","citation":{"ama":"Baykan E, Henzinger M, Marian L, Weber I. A comprehensive study of features and algorithms for URL-based topic classification. <i>ACM Transactions on the Web</i>. 2011;5(3). doi:<a href=\"https://doi.org/10.1145/1993053.1993057\">10.1145/1993053.1993057</a>","short":"E. Baykan, M. Henzinger, L. Marian, I. Weber, ACM Transactions on the Web 5 (2011).","ieee":"E. Baykan, M. Henzinger, L. Marian, and I. Weber, “A comprehensive study of features and algorithms for URL-based topic classification,” <i>ACM Transactions on the Web</i>, vol. 5, no. 3. Association for Computing Machinery, 2011.","apa":"Baykan, E., Henzinger, M., Marian, L., &#38; Weber, I. (2011). A comprehensive study of features and algorithms for URL-based topic classification. <i>ACM Transactions on the Web</i>. Association for Computing Machinery. <a href=\"https://doi.org/10.1145/1993053.1993057\">https://doi.org/10.1145/1993053.1993057</a>","ista":"Baykan E, Henzinger M, Marian L, Weber I. 2011. A comprehensive study of features and algorithms for URL-based topic classification. ACM Transactions on the Web. 5(3), 15.","mla":"Baykan, Eda, et al. “A Comprehensive Study of Features and Algorithms for URL-Based Topic Classification.” <i>ACM Transactions on the Web</i>, vol. 5, no. 3, 15, Association for Computing Machinery, 2011, doi:<a href=\"https://doi.org/10.1145/1993053.1993057\">10.1145/1993053.1993057</a>.","chicago":"Baykan, Eda, Monika Henzinger, Ludmila Marian, and Ingmar Weber. “A Comprehensive Study of Features and Algorithms for URL-Based Topic Classification.” <i>ACM Transactions on the Web</i>. Association for Computing Machinery, 2011. <a href=\"https://doi.org/10.1145/1993053.1993057\">https://doi.org/10.1145/1993053.1993057</a>."},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87"}]