{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T01:10:02Z","timestamp":1716772202963},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2014,5,26]],"date-time":"2014-05-26T00:00:00Z","timestamp":1401062400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front. Comput. Sci."],"published-print":{"date-parts":[[2014,8]]},"DOI":"10.1007\/s11704-014-3050-9","type":"journal-article","created":{"date-parts":[[2014,5,26]],"date-time":"2014-05-26T14:26:53Z","timestamp":1401114413000},"page":"581-595","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Clustering-based topical Web crawling using CFu-tree guided by link-context"],"prefix":"10.1007","volume":"8","author":[{"given":"Lu","family":"Liu","sequence":"first","affiliation":[]},{"given":"Tao","family":"Peng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,5,26]]},"reference":[{"key":"3050_CR1","volume-title":"Morgan & Claypool Publishers","author":"Y Sun","year":"2012","unstructured":"Sun Y, Han J. Mining heterogeneous information networks: principles and methodologies. Morgan & Claypool Publishers, 2012"},{"key":"3050_CR2","first-page":"41","volume":"752","author":"A McCallum","year":"1998","unstructured":"McCallum A, Nigam K. A comparison of event models for Na\u00efve Bayes text classification. In: Proceedings of the AAAI-98 Workshop on Learning for Text Categorization, 1998, 752: 41\u201348","journal-title":"Proceedings of the AAAI-98 Workshop on Learning for Text Categorization"},{"key":"3050_CR3","first-page":"80","volume-title":"Proceedings of Knowledge Discovery and Data Mining (KDD\u2019 98)","author":"B Liu","year":"1998","unstructured":"Liu B, Hsu W, Ma Y. Integrating classification and association rule mining. In: Proceedings of Knowledge Discovery and Data Mining (KDD\u2019 98), 1998, 80\u201386"},{"key":"3050_CR4","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1145\/130385.130401","volume":"5","author":"B Boser","year":"1992","unstructured":"Boser B, Guyon I, Vapnik V. A training algorithm for optimal margin classifiers. In: Proceedings of the 5th Annual Workshop on Computational Learning Theory, 1992, 5: 144\u2013152","journal-title":"Proceedings of the 5th Annual Workshop on Computational Learning Theory"},{"issue":"8","key":"3050_CR5","doi-asserted-by":"crossref","first-page":"890","DOI":"10.1093\/comjnl\/bxn049","volume":"52","author":"C Chou","year":"2009","unstructured":"Chou C, Lee C, Chen Y. GA-based keyword selection for the design of an intelligent Web document search system. Computer Journal, 2009, 52(8): 890\u2013901","journal-title":"Computer Journal"},{"issue":"1","key":"3050_CR6","first-page":"525","volume":"400","author":"M Steinbach","year":"2000","unstructured":"Steinbach M, Karypis G, Kumar V. A comparison of document clustering techniques. In: Proceedings of KDD Workshop on Text Mining, 2000, 400(1): 525\u2013526","journal-title":"Proceedings of KDD Workshop on Text Mining"},{"issue":"3","key":"3050_CR7","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"A Jain","year":"1999","unstructured":"Jain A, Murty M, Flyn P. Data clustering: a review. ACM Computing Surveys, 1999, 31(3): 264\u2013323","journal-title":"ACM Computing Surveys"},{"key":"3050_CR8","first-page":"59","volume-title":"Proceedings of SIAM International Conference on Data Mining (SDM\u2019 03)","author":"B Fung","year":"2003","unstructured":"Fung B, Wang K, Ester M. Hierarchical document clustering using frequent itemsets. In: Proceedings of SIAM International Conference on Data Mining (SDM\u2019 03), 2003, 59\u201370"},{"issue":"6","key":"3050_CR9","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.1002\/asi.21323","volume":"61","author":"T Fu","year":"2010","unstructured":"Fu T, Abbasi A, Chen H. A focused crawler for dark Web forums. Journal of the American Society for Information Science and Technology, 2010, 61(6): 1213\u20131231","journal-title":"Journal of the American Society for Information Science and Technology"},{"key":"3050_CR10","doi-asserted-by":"crossref","first-page":"1190","DOI":"10.1145\/1062745.1062933","volume-title":"Proceedings of Special Interest Tracks and Posters of the 14th International Conference on World Wide Web","author":"J Li","year":"2005","unstructured":"Li J, Furuse K, Yamaguchi K. Focused crawling by exploiting anchor text using decision tree. In: Proceedings of Special Interest Tracks and Posters of the 14th International Conference on World Wide Web. New York: ACM, 2005, 1190\u20131191"},{"issue":"3","key":"3050_CR11","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.1467-8640.2012.00411.x","volume":"28","author":"H Liu","year":"2012","unstructured":"Liu H, Milios E. Probabilistic models for focused Web crawling. Computational Intelligence, 2012, 28(3): 289\u2013328","journal-title":"Computational Intelligence"},{"key":"3050_CR12","first-page":"850","volume-title":"Proceedings of IEEE International Conference on Systems Man and Cyvernetics Conference","author":"H Hao","year":"2011","unstructured":"Hao H, Mu C, Yin X, Li S, Wang Z. An improved topic relevance algorithm for focused crawling. In: Proceedings of IEEE International Conference on Systems Man and Cyvernetics Conference, 2011, 850\u2013855"},{"issue":"1","key":"3050_CR13","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1109\/TKDE.2006.12","volume":"18","author":"G Pant","year":"2006","unstructured":"Pant G, Srinivasan P. Link contexts in classifier-guided topical crawlers. IEEE Transactions on Knowledge and Data Engineering, 2006, 18(1): 107\u2013122","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"2","key":"3050_CR14","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1016\/j.asoc.2009.08.017","volume":"10","author":"H Zhang","year":"2010","unstructured":"Zhang H, Lu J. SCTWC: an online semi-supervised clustering approach to topical Web crawlers. Applied Soft Computing, 2010, 10(2): 490\u2013495","journal-title":"Applied Soft Computing"},{"issue":"3\u20134","key":"3050_CR15","first-page":"203","volume":"12","author":"Y Liu","year":"2013","unstructured":"Liu Y, Agah A. Topical crawling on the Web through local sitesearchers. Journal of Web Engineering, 2013, 12(3\u20134): 203\u2013214","journal-title":"Journal of Web Engineering"},{"key":"3050_CR16","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1145\/1963192.1963249","volume-title":"Proceedings of the 20th International Conference Companion on World Wide Web","author":"A Rangrej","year":"2011","unstructured":"Rangrej A, Kulkarni S, Tendulkar A. Comparative study of clustering techniques for short text documents. In: Proceedings of the 20th International Conference Companion on World Wide Web. New York: ACM, 2011, 111\u2013112"},{"key":"3050_CR17","doi-asserted-by":"crossref","first-page":"804","DOI":"10.1109\/ICDM.2011.59","volume-title":"Proceedings 2011 IEEE 11th International Conference on Data Mining","author":"X Wang","year":"2011","unstructured":"Wang X, Tang J, Liu H. Document clustering via matrix representation. In: Proceedings 2011 IEEE 11th International Conference on Data Mining, 2011, 804\u2013813"},{"issue":"9","key":"3050_CR18","doi-asserted-by":"crossref","first-page":"1853","DOI":"10.1002\/asi.21363","volume":"61","author":"R Cota","year":"2010","unstructured":"Cota R, Ferreira A, Nascimento C, Goncalves M, Laender A. An unsupervised heuristic-based hierarchical method for name disambiguation in bibliographic citations. Journal of the American Society for Information Science and Technology, 2010, 61(9): 1853\u20131870","journal-title":"Journal of the American Society for Information Science and Technology"},{"issue":"3","key":"3050_CR19","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1093\/comjnl\/bxr024","volume":"55","author":"G Spanakis","year":"2012","unstructured":"Spanakis G, Siolas G, Stafylopatis A. Exploiting wikipedia knowledge for conceptual hierarchical clustering of documents. Computer Journal, 2012, 55(3): 299\u2013312","journal-title":"Computer Journal"},{"key":"3050_CR20","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.knosys.2012.06.015","volume":"36","author":"C Bouras","year":"2012","unstructured":"Bouras C, Tsogkas V. A clustering technique for news articles using WordNet. Knowledge-Based Systems, 2012, 36: 115\u2013128","journal-title":"Knowledge-Based Systems"},{"issue":"3","key":"3050_CR21","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1007\/s10844-012-0211-x","volume":"39","author":"J Li","year":"2012","unstructured":"Li J, Zhao Y, Liu B. Exploiting semantic resources for large scale text categorization. Journal of Intelligent Information Systems, 2012, 39(3): 763\u2013788","journal-title":"Journal of Intelligent Information Systems"},{"issue":"4","key":"3050_CR22","volume":"3","year":"2012","unstructured":"Trivedi A, Rai, P, Daume H, Duvall, S. Leveraging social bookmarks from partially tagged corpus for improved Web page clustering. ACM Transactions on Intelligent Systems and Technology, 2012, 3(4), Article 67","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"issue":"6","key":"3050_CR23","first-page":"1234","volume":"63","author":"M Wu","year":"2012","unstructured":"Wu M, Hawking D, Turpin A, Scholer F. Using anchor text for homepage and topic distillation search tasks. Journal of the American Society for Information Science and Technology, 2012, 63(6): 1234\u20131255","journal-title":"Journal of the American Society for Information Science and Technology"},{"issue":"1","key":"3050_CR24","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/S0169-7552(98)00038-5","volume":"30","author":"M Hersovici","year":"1998","unstructured":"Hersovici M, Jacovi M, Maarek Y, Pellegb D, Shtalhaima M, Ura S. The shark-search algorithm. an application: tailored Web site mapping. Computer Networks and ISDN Systems, 1998, 30(1): 317\u2013326","journal-title":"Computer Networks and ISDN Systems"},{"issue":"1","key":"3050_CR25","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/S0169-7552(98)00087-7","volume":"30","author":"S Chakrabarti","year":"1998","unstructured":"Chakrabarti S, Dom B, Gibson D, Kleinberg J, Raghavan P, Rajagopalan S. Automatic resource list compilation by analyzing hyperlink structure and associated text. Computer Networks and ISDN Systems, 1998, 30(1): 65\u201374","journal-title":"Computer Networks and ISDN Systems"},{"key":"3050_CR26","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1145\/882082.882094","volume-title":"Proceedings of 8th ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery","author":"G Pant","year":"2003","unstructured":"Pant G. Deriving link-context from HTML tag tree. In: Proceedings of 8th ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery, 2003, 49\u201355"},{"issue":"5","key":"3050_CR27","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1109\/TPAMI.2011.191","volume":"34","author":"G Qi","year":"2012","unstructured":"Qi G, Aggarwal C, Tian Q, Ji H, Huang T. Exploring context and content links in social media: a latent space method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(5): 850\u2013862","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"3050_CR28","first-page":"105","volume":"99","author":"G Attardi","year":"1999","unstructured":"Attardi G, Gull\u0131\u2019 A, Sebastiani F. Automatic Web page categorization by link and context analysis. In: Proceedings of the 1st European Symposium on Telematics, Hypermedia, and Artificial Intelligence, 1999, 99: 105\u2013109","journal-title":"Proceedings of the 1st European Symposium on Telematics, Hypermedia, and Artificial Intelligence"},{"issue":"1\u20137","key":"3050_CR29","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/S0169-7552(98)00110-X","volume":"30","author":"S Brin","year":"1998","unstructured":"Brin S, Page L. The anatomy of a large-scale hypertextual Web search engine. Computer Networks and ISDN Systems, 1998, 30(1\u20137): 107\u2013117","journal-title":"Computer Networks and ISDN Systems"},{"key":"3050_CR30","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1145\/996350.996384","volume-title":"Proceedings of 4th ACM\/IEEE-CS Joint Conference Digital Libraries","author":"G Pant","year":"2004","unstructured":"Pant G, Tsioutsiouliklis K, Johnson J, Giles C. Panorama: extending digital libraries with topical crawlers. In: Proceedings of 4th ACM\/IEEE-CS Joint Conference Digital Libraries, 2004, 142\u2013150"},{"issue":"1","key":"3050_CR31","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1002\/cpe.1211","volume":"20","author":"T Peng","year":"2008","unstructured":"Peng T, Zhang C, Zuo W. Tunneling enhanced by Web page content bloc partition for focused crawling. Concurrency and Computation: Practice and Experience, 2008, 20(1): 61\u201374","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"3050_CR32","first-page":"1190","volume-title":"Proceedings of 14th International Conference on World Wide Web","author":"J Li","year":"2005","unstructured":"Li J, Furuse K, Yamaguchi K. Focused crawling by exploiting anchor text using decision tree. In: Proceedings of 14th International Conference on World Wide Web, 2005, 1190\u20131191"},{"key":"3050_CR33","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1007\/11579427_84","volume":"3789","author":"H Yu","year":"2005","unstructured":"Yu H, Zuo W, Peng T. A new PU learning algorithm for text classification. Lecture Notes in Computer Science, 2005, 3789: 824\u2013832","journal-title":"Lecture Notes in Computer Science"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-014-3050-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11704-014-3050-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-014-3050-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:37:39Z","timestamp":1716770259000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11704-014-3050-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5,26]]},"references-count":33,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2014,8]]}},"alternative-id":["3050"],"URL":"https:\/\/doi.org\/10.1007\/s11704-014-3050-9","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,5,26]]}}}