{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T05:10:03Z","timestamp":1744521003910,"version":"3.40.4"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2012,10,16]],"date-time":"2012-10-16T00:00:00Z","timestamp":1350345600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2013,9]]},"DOI":"10.1007\/s10115-012-0564-z","type":"journal-article","created":{"date-parts":[[2012,10,17]],"date-time":"2012-10-17T15:36:32Z","timestamp":1350488192000},"page":"693-729","source":"Crossref","is-referenced-by-count":1,"title":["Query directed clustering"],"prefix":"10.1007","volume":"36","author":[{"given":"Daniel","family":"Crabtree","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoying","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Andreae","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,10,16]]},"reference":[{"key":"564_CR1","doi-asserted-by":"crossref","unstructured":"Allan J (2005), Hard track overview in trec 2005 high accuracy retrieval from documents. In: The 14th Text REtrieval conference (TREC\u201905)","DOI":"10.21236\/ADA439446"},{"key":"564_CR2","doi-asserted-by":"crossref","unstructured":"Anastasiu DC, Gao BJ, Buttler D (2011) A framework for personalized and collaborative clustering of search results. In: Proceedings of the 20th ACM international conference on Information and, knowledge management, CIKM\u201911, pp 573\u2013582","DOI":"10.1145\/2063576.2063662"},{"key":"564_CR3","unstructured":"Asirvatham AP, Ravi KK (2001) Web page classification based on document structure"},{"key":"564_CR4","unstructured":"Back J, Oppenheim C (2001) A model of cognitive load for IR: implications for user relevance feedback interaction. Inf Res 6(2). http:\/\/InformationR.net\/ir\/6-2\/ws2.html"},{"key":"564_CR5","doi-asserted-by":"crossref","unstructured":"Balachandran V, Deepak P, Khemani D (2012) Interpretable and reconfigurable clustering of document datasets by deriving word-based rules. Knowl Inf Syst 32(3):475\u2013503","DOI":"10.1007\/s10115-011-0446-9"},{"key":"564_CR6","unstructured":"Berkhin P (2002) Survey of clustering data mining techniques. Technical report, Accrue Software, San Jose, CA"},{"issue":"3","key":"564_CR7","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/S0167-9236(99)00055-X","volume":"27","author":"D Boley","year":"1999","unstructured":"Boley D, Gini M, Gross R, Han E-H, Karypis G, Kumar V, Mobasher B, Moore J, Hastings K (1999) Partitioning-based clustering for web document categorization. Decis Support Syst (Special issue on WITS \u201997) 27(3):329\u2013341","journal-title":"Decis Support Syst (Special issue on WITS \u201997)"},{"key":"564_CR8","doi-asserted-by":"crossref","unstructured":"Carpineto C, Romano G (2010) Optimal meta search results clustering. In: Proceedings of the 33rd international ACM SIGIR conference on Research and development in, information retrieval. SIGIR\u201910, pp 170\u2013177","DOI":"10.1145\/1835449.1835480"},{"key":"564_CR9","volume-title":"Mining the web\u2014discovering knowledge from hypertext data","author":"S Chakrabarti","year":"2003","unstructured":"Chakrabarti S (2003) Mining the web\u2014discovering knowledge from hypertext data. Morgan Kaufmann, Los Altos, CA"},{"key":"564_CR10","doi-asserted-by":"crossref","unstructured":"Chen H, Dumais S (2000) Bringing order to the web: automatically categorizing search results. In: The SIGCHI conference on human factors in computing systems, pp 145\u2013152","DOI":"10.1145\/332040.332418"},{"issue":"3","key":"564_CR11","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1109\/TKDE.2007.48","volume":"19","author":"RL Cilibrasi","year":"2007","unstructured":"Cilibrasi RL, Vitanyi PM (2007) The google similarity distance. IEEE Trans Knowl Data Eng 19(3):370\u2013 383","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"564_CR12","unstructured":"Cilibrasi R, Vitanyi PMB (2004) Automatic meaning discovery using google. www.cwi.nl\/paulv\/papers\/amdug.pdf"},{"key":"564_CR13","unstructured":"Cock MD, Cornelis C (2005) Fuzzy rough set based web query expansion. In: International workshop on rough sets and soft computing in intelligent agent and web technologies, pp 9\u201316"},{"key":"564_CR14","doi-asserted-by":"crossref","unstructured":"Crabtree D, Andreae P, Gao X (2006) Query directed web page clustering. In: The 2006 IEEE\/WIC\/ACM international conference on web, intelligence (WI\u201906), pp 202\u2013210","DOI":"10.1109\/WI.2006.142"},{"key":"564_CR15","doi-asserted-by":"crossref","unstructured":"Crabtree D, Andreae P, Gao X (2007) Qc4\u2014a clustering evaluation method. In: The 2007 Pacific-Asia conference on knowledge discovery and data mining (PAKDD\u201907), pp 59\u201370","DOI":"10.1007\/978-3-540-71701-0_9"},{"key":"564_CR16","doi-asserted-by":"crossref","unstructured":"Crabtree D, Gao X, Andreae P (2005a) Improving web clustering by cluster selection. In: The 2005 IEEE\/WIC\/ACM International Conference on Web, Intelligence (WI\u201905), pp 172\u2013178","DOI":"10.1109\/WI.2005.75"},{"key":"564_CR17","doi-asserted-by":"crossref","unstructured":"Crabtree D, Gao X, Andreae P (2005b) Standardized evaluation method for web clustering results. In: The 2005 IEEE\/WIC\/ACM international conference on web, intelligence (WI\u201905), pp 280\u2013283","DOI":"10.1109\/WI.2005.138"},{"key":"564_CR18","doi-asserted-by":"crossref","unstructured":"Cui H, Wen J-R, Nie J-Y, Ma W-Y (2002) Probabilistic query expansion using query logs. In: The 11th international conference on, world wide web (WWW\u201902), pp 325\u2013332","DOI":"10.1145\/511446.511489"},{"key":"564_CR19","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1007\/s10115-010-0367-z","volume":"28","author":"A Farahat","year":"2011","unstructured":"Farahat A, Kamel M (2011) Statistical semantics for enhancing document clustering. Knowl Inf Syst 28:365\u2013393","journal-title":"Knowl Inf Syst"},{"key":"564_CR20","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1007\/s10115-010-0370-4","volume":"28","author":"S Fodeh","year":"2011","unstructured":"Fodeh S, Punch B, Tan P-N (2011) On ontology-driven document clustering using core semantic features. Knowl Inf Syst 28:395\u2013421","journal-title":"Knowl Inf Syst"},{"key":"564_CR21","doi-asserted-by":"crossref","unstructured":"Fung BC, Wang K, Ester M (2003) Hierarchical document clustering using frequent itemsets. In: The SIAM international conference on data mining","DOI":"10.1137\/1.9781611972733.6"},{"key":"564_CR22","unstructured":"Gelgi F, Davulcu H, Vadrevu S (2007) Term ranking for clustering web search results. In: The 10th international workshop on the web and databases (WebDB\u201907)"},{"key":"564_CR23","unstructured":"Goo (2007) Google.com: www.google.com"},{"issue":"2\u20133","key":"564_CR24","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1023\/A:1012801612483","volume":"17","author":"M Halkidi","year":"2001","unstructured":"Halkidi M, Batistakis Y, Vazirgiannis M (2001) On clustering validation techniques. J Intell Inf Syst 17(2\u20133):107\u2013145","journal-title":"J Intell Inf Syst"},{"key":"564_CR25","unstructured":"Hawking D, Craswell N (2005) Very large scale retrieval and web search. In: TREC: experiment and evaluation in information retrieval, MIT Press, pp 199\u2013231"},{"issue":"1","key":"564_CR26","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1023\/A:1011468107287","volume":"4","author":"D Hawking","year":"2001","unstructured":"Hawking D, Craswell N, Bailey P, Griffiths K (2001) Measuring search engine quality. Inf Retr 4(1):33\u201359","journal-title":"Inf Retr"},{"issue":"3","key":"564_CR27","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"AK Jain","year":"1999","unstructured":"Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv CSUR 31(3):264\u2013323","journal-title":"ACM Comput Surv CSUR"},{"issue":"8","key":"564_CR28","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/MC.2007.289","volume":"40","author":"T Joachims","year":"2007","unstructured":"Joachims T, Radlinski F (2007) Search engines that learn from implicit feedback. Computer 40(8):34\u201340","journal-title":"Computer"},{"key":"564_CR29","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1007\/s10115-011-0412-6","volume":"31","author":"A Kalogeratos","year":"2012","unstructured":"Kalogeratos A, Likas A (2012) Text document clustering using global term context vectors. Knowl Inf Syst 31:455\u2013474","journal-title":"Knowl Inf Syst"},{"key":"564_CR30","doi-asserted-by":"crossref","unstructured":"Kummamuru K, Lotlikar R, Roy S, Singal K, Krishnapuram R (2004) A hierarchical monothetic document clustering algorithm for summarization and browsing search results. In The 13th international conference on, world wide web (WWW\u201904), pp 658\u2013665","DOI":"10.1145\/988672.988762"},{"key":"564_CR31","unstructured":"Mam (2007) Maamma.com: www.mamma.com"},{"key":"564_CR32","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval","author":"CD Manning","year":"2008","unstructured":"Manning CD, Raghavan P, Schtze H (2008) Introduction to information retrieval. Cambridge University Press, Cambridge"},{"issue":"14","key":"564_CR33","doi-asserted-by":"crossref","first-page":"1261","DOI":"10.1002\/asi.20081","volume":"55","author":"F Menczer","year":"2004","unstructured":"Menczer F (2004) Lexical and semantic clustering by web links. J Am Soc Inf Sci Technol 55(14):1261\u20131269","journal-title":"J Am Soc Inf Sci Technol"},{"key":"564_CR34","doi-asserted-by":"crossref","unstructured":"Murayama N, Saito S, Okumura M (2004) Are web pages characterized by color?. In: The 13th international conference on world wide web\u2014alternate track papers and posters (WWW\u201904), pp 248\u2013249","DOI":"10.1145\/1013367.1013419"},{"key":"564_CR35","doi-asserted-by":"crossref","unstructured":"Osi\u0144ski S, Stefanowski J, Weiss D (2004) Lingo: aearch results clustering algorithm based on singular value decomposition. In: The international IIS: intelligent information processing and web mining conference, advances in soft computing, Springer, pp 359\u2013368","DOI":"10.1007\/978-3-540-39985-8_37"},{"key":"564_CR36","doi-asserted-by":"crossref","unstructured":"Osi\u0144ski S, Weiss D (2004) Conceptual clustering using lingo algorithm: evaluation on open directory project data. In: The international IIS: intelligent information processing and web mining conference, advances in soft computing, Springer, pp 369\u2013378","DOI":"10.1007\/978-3-540-39985-8_38"},{"issue":"3","key":"564_CR37","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/MIS.2005.38","volume":"20","author":"S Osinski","year":"2005","unstructured":"Osinski S, Weiss D (2005) A concept-driven algorithm for clustering search results. IEEE Intell Syst 20(3):48\u201354","journal-title":"IEEE Intell Syst"},{"issue":"2","key":"564_CR38","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1017\/S0269888903000638","volume":"19","author":"I Ruthven","year":"2003","unstructured":"Ruthven I, Lalmas M (2003) A survey on the use of relevance feedback for information access systems. Knowl Eng Rev 19(2):95\u2013145","journal-title":"Knowl Eng Rev"},{"key":"564_CR39","unstructured":"Shipeng Y, Cai D, Wen J, Ma W (2003) Improving pseudo-relevance feedback in web information retrieval using web page segmentation. In: The 12th international world wide web conference, pp 11\u201318"},{"issue":"8","key":"564_CR40","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MC.2007.259","volume":"40","author":"B Smyth","year":"2007","unstructured":"Smyth B (2007) A community-based approach to personalizing web search. Computer 40(8):42\u201350","journal-title":"Computer"},{"key":"564_CR41","unstructured":"Spink A, Koshman S, Park M, Field C, Jansen BJ (2005) Multitasking web search on vivisimo.com. In: International conference on information technology: coding and computing (ITCC\u201905). Vol II, pp 486\u2013490"},{"key":"564_CR42","unstructured":"Steinbach M, Karypis G, Kumar V (2000) A comparison of document clustering techniques. In: KDD workshop on text mining"},{"key":"564_CR43","unstructured":"Strehl A (2002) Relationship-based clustering and cluster ensembles for high-dimensional data mining, PhD thesis, Faculty of the Graduate School of The University of Texas at Austin"},{"key":"564_CR44","unstructured":"Strehl A, Ghosh J, Mooney R (2000) Impact of similarity measures on web-page clustering. In: The 17th national conference on artificial intelligence: workshop of artificial intelligence for web, search (AAAI\u201900), pp 58\u201364"},{"key":"564_CR45","unstructured":"Su Z, Yang Q, Zhang H, Xu X, Hu Y (2001) Correlation-based document clustering using web logs. In: The 34th annual Hawaii international conference on system sciences (HICSS-34) 5(34), p 5022"},{"key":"564_CR46","volume-title":"Information retrieval","author":"CJ Rijsbergen van","year":"1979","unstructured":"van Rijsbergen CJ (1979) Information retrieval, 2nd edn. Buterworths, London","edition":"2"},{"key":"564_CR47","doi-asserted-by":"crossref","unstructured":"Wang Y, Kitsuregawa M (2002) On combining link and contents information for web page clustering. In: The 13th international conference on database and expert systems applications (DEXA\u201902), pp 902\u2013913","DOI":"10.1007\/3-540-46146-9_89"},{"key":"564_CR48","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/s10115-009-0203-5","volume":"21","author":"W Woon","year":"2009","unstructured":"Woon W, Madnick S (2009) Asymmetric information distances for automated taxonomy construction. Knowl Inf Syst 21:91\u2013111","journal-title":"Knowl Inf Syst"},{"key":"564_CR49","doi-asserted-by":"crossref","unstructured":"Yu G, Huang R, Wang Z (2010) Document clustering via dirichlet process mixture model with feature selection. In: Proceedings of the 16th ACM SIGKDD international conference on knowledge discovery and data mining, KDD\u201910, pp 763\u2013772","DOI":"10.1145\/1835804.1835901"},{"key":"564_CR50","unstructured":"Zamir OE (1999) Clustering Web documents: a phrase-based method for grouping search engine results, PhD thesis, University of Washington"},{"key":"564_CR51","doi-asserted-by":"crossref","unstructured":"Zamir O, Etzioni O (1998) Web document clustering: a feasibility demonstration. In: The 21st annual international ACM SIGIR conference on research and development, in Information retrieval (SIGIR\u201998), pp 46\u201354","DOI":"10.1145\/290941.290956"},{"key":"564_CR52","unstructured":"Zeng H-J, He Q-C, Chen Z, Ma W-Y, Ma J (2004) Learning to cluster web search results. In: The 27th annual international ACM SIGIR conference on research and development in, information retrieval (SIGIR\u201904), pp 210\u2013217"},{"key":"564_CR53","doi-asserted-by":"crossref","unstructured":"Zhang J, Sun L, Lv Y, Zhang W (2005) Relevance feedback by exploring the different feedback source and collection structure. In: The 14th text REtrieval conference (TREC\u201905)","DOI":"10.6028\/NIST.SP.500-266.HARD-cas.zhang"},{"key":"564_CR54","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1007\/s10115-011-0389-1","volume":"30","author":"W Zhao","year":"2012","unstructured":"Zhao W, He Q, Ma H, Shi Z (2012) Effective semi-supervised document clustering via active learning with instance-level constraints. Knowl Inf Syst 30:569\u2013587","journal-title":"Knowl Inf Syst"},{"key":"564_CR55","unstructured":"Zhao Y, Karypis G (2001) Criterion functions for document clustering: experiments and analysis. Department of Computer Science, University of Minnesota, Minneapolis, MN, Technical report"},{"issue":"2","key":"564_CR56","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/s10618-005-0361-3","volume":"10","author":"Y Zhao","year":"2005","unstructured":"Zhao Y, Karypis G, Fayyad U (2005) Hierarchical clustering algorithms for document datasets. Data Min Knowl Discov 10(2):141\u2013168","journal-title":"Data Min Knowl Discov"},{"key":"564_CR57","unstructured":"Zu Eissen SM, Stein B, Potthast M (2005) The suffix tree document model revisited. In: The 5th international conference on, knowledge management (I-KNOW\u201905)"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-012-0564-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-012-0564-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-012-0564-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T04:42:42Z","timestamp":1744519362000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-012-0564-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,10,16]]},"references-count":57,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,9]]}},"alternative-id":["564"],"URL":"https:\/\/doi.org\/10.1007\/s10115-012-0564-z","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"type":"print","value":"0219-1377"},{"type":"electronic","value":"0219-3116"}],"subject":[],"published":{"date-parts":[[2012,10,16]]}}}