{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T04:19:49Z","timestamp":1745986789369,"version":"3.40.4"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,1,15]],"date-time":"2013-01-15T00:00:00Z","timestamp":1358208000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2014,1]]},"DOI":"10.1007\/s11280-012-0197-x","type":"journal-article","created":{"date-parts":[[2013,1,14]],"date-time":"2013-01-14T08:42:10Z","timestamp":1358152930000},"page":"105-126","source":"Crossref","is-referenced-by-count":10,"title":["Clustering web documents using hierarchical representation with multi-granularity"],"prefix":"10.1007","volume":"17","author":[{"given":"Faliang","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shichao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghua","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xindong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,1,15]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Beil, F., Ester, M., Xu, X.: Frequent term-based text clustering. In: Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2002), pp. 436\u2013442. Edmonton, Alberta, Canada (2002)","key":"197_CR1","DOI":"10.1145\/775047.775110"},{"key":"197_CR2","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)","journal-title":"J. Mach. Learn. Res."},{"issue":"5\u20136","key":"197_CR3","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1007\/s11280-011-0124-6","volume":"14","author":"E Bruno","year":"2011","unstructured":"Bruno, E., Faessel, N., Glotin, H., Maitre, J.L., Scholl, M.: Indexing and querying segmented web pages: the blockweb model. World Wide Web 14(5\u20136), 623\u2013649 (2011)","journal-title":"World Wide Web"},{"issue":"3","key":"197_CR4","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1007\/s10115-010-0364-2","volume":"28","author":"C-L Chen","year":"2011","unstructured":"Chen, C.-L., Tseng, F.S.C., Liang, T.: An integration of fuzzy association rules and WordNet for document clustering. Knowl. Inf. Syst. 28(3), 687\u2013708 (2011)","journal-title":"Knowl. Inf. Syst."},{"issue":"2","key":"197_CR5","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/s10115-010-0307-y","volume":"27","author":"J Cui","year":"2011","unstructured":"Cui, J., Liu, H., He, J., Li, P., Du, X., Wang, P.: Tagclus: a random walk-based method for tag clustering. Knowl. Inf. Syst. 27(2), 193\u2013225 (2011)","journal-title":"Knowl. Inf. Syst."},{"doi-asserted-by":"crossref","unstructured":"Derrick, C.: TinyLex: static n-gram index pruning with perfect recall. In: Proceedings of the 17th Conference on Information and Knowledge Management (CIKM 2008), pp. 409\u2013418. Napa Valley, California, USA (2008)","key":"197_CR6","DOI":"10.1145\/1458082.1458138"},{"issue":"2","key":"197_CR7","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1007\/s10115-010-0367-z","volume":"28","author":"AK Farahat","year":"2011","unstructured":"Farahat, A.K., Kamel, M.S.: Statistical semantics for enhancing document clustering. Knowl. Inf. Syst. 28(2), 365\u2013393 (2011)","journal-title":"Knowl. Inf. Syst."},{"issue":"2","key":"197_CR8","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.: On ontology-driven document clustering using core semantic features. Knowl. Inf. Syst. 28(2), 395\u2013421 (2011)","journal-title":"Knowl. Inf. Syst."},{"key":"197_CR9","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1023\/A:1007617005950","volume":"42","author":"T Hofmann","year":"2001","unstructured":"Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Mach. Learn. 42, 177\u2013196 (2001)","journal-title":"Mach. Learn."},{"doi-asserted-by":"crossref","unstructured":"Hossain, M.S., Angryk, R.A.: GDClust: a graph-based document clustering technique. In: Proceedings of the Seventh IEEE International Conference on Data Mining. (ICDM Workshops 2007), pp. 417\u2013422. Omaha, Nebraska, USA (2007)","key":"197_CR10","DOI":"10.1109\/ICDMW.2007.104"},{"unstructured":"Hotho, A., Maedche, A., Staab, S.: Ontology-based text document clustering. KI 16(4), 48\u201354 (2002)","key":"197_CR11"},{"doi-asserted-by":"crossref","unstructured":"Hotho, A., Staab, S., Stumme, G.: Ontologies improve text document clustering. In: Proceedings of the Third IEEE International Conference on Data Mining (ICDM\u201903), pp. 541\u2013544. Melbourne, Florida, USA (2003)","key":"197_CR12","DOI":"10.1109\/ICDM.2003.1250972"},{"unstructured":"http:\/\/www.cs.cmu.edu\/afs\/cs.cmu.edu\/project\/theo-20\/www\/data\/webkb-data.gtar.gz","key":"197_CR13"},{"unstructured":"http:\/\/www.cs.cmu.edu\/afs\/cs\/project\/theo-20\/www\/data\/bootstrappingIE\/7sectors.tar.gz","key":"197_CR14"},{"doi-asserted-by":"crossref","unstructured":"Huang, F., Xie, G., Yao, Z., Cai, S.: Clustering transactions based on weighting maximal frequent itemsets. In: Proceedings of the 3rd International Conference on Intelligent System and Knowledge Engineering (ISKE 2008), pp. 262\u2013266. Xiamen, China (2008)","key":"197_CR15","DOI":"10.1109\/ISKE.2008.4730938"},{"doi-asserted-by":"crossref","unstructured":"Huang, F., Zhang, S.: Clustering web documents based on knowledge granularity. In: Proceedings of the Eighth Asia Pacific Web Conference (APWeb\u201906), pp. 85\u201396. Harbin, China (2006)","key":"197_CR16","DOI":"10.1007\/11610113_9"},{"unstructured":"Jing, L., Zhou, L., Ng, M., Huang, Z.: Ontology-based distance measure for text clustering. In: Proceedings of SIAM SDM Workshop on Text Mining, Bethesda, Maryland, USA (2003)","key":"197_CR17"},{"doi-asserted-by":"crossref","unstructured":"Keller, M., Bengio, S.: A neural network for text representation. In: Proceedings of the International Conference on Artificial Neural Networks (ICANN\u201905), pp. 667\u2013672. Warsaw, Poland (2005)","key":"197_CR18","DOI":"10.1007\/11550907_106"},{"issue":"1","key":"197_CR19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11280-007-0018-9","volume":"11","author":"S Khy","year":"2008","unstructured":"Khy, S., Ishikawa, Y., Kitagawa, H.: A novelty-based clustering method for on-line documents. World Wide Web 11(1), 1\u201337 (2008)","journal-title":"World Wide Web"},{"unstructured":"Kryszkiewicz, M.: Properties of in complete information systems in the framework of rough sets. In: Polkowski, L., Skowron, A., (eds.) Rough Set in Knowledge Discovery 1: Methodology and Applications, Studies in Fuzziness and Soft Computing 18, pp. 422-450. Physica Verlag (1998)","key":"197_CR20"},{"unstructured":"Lang, N.C.: A Tolerance Rough Set Approach to Clustering Web Search Results. Warsaw University, Pisa, Italy (2003)","key":"197_CR21"},{"issue":"2","key":"197_CR22","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/s11280-011-0117-5","volume":"14","author":"C Leung","year":"2011","unstructured":"Leung, C., Chan, S., Chung, F., Ngai, G.: A probabilistic rating inference framework for mining user preferences from reviews. World Wide Web 14(2), 187\u2013215 (2011)","journal-title":"World Wide Web"},{"issue":"1","key":"197_CR23","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/j.datak.2007.08.001","volume":"64","author":"Y Li","year":"2008","unstructured":"Li, Y., Chung, S.M., Holt, J.D.: Text document clustering based on frequent word meaning sequences. Data Knowl. Eng. 64(1), 381\u2013404 (2008)","journal-title":"Data Knowl. Eng."},{"unstructured":"Liu, N., Zhang, B., Yan, J., et al.: Text representation: from vector to tensor. In: Proceedings of the 5th IEEE International Conference on Data Mining (ICDM 2005), pp. 725\u2013728. Houston, Texas, USA (2005)","key":"197_CR24"},{"issue":"3","key":"197_CR25","doi-asserted-by":"crossref","first-page":"784","DOI":"10.1109\/TSMCA.2011.2172205","volume":"42","author":"J Ma","year":"2012","unstructured":"Ma, J., Xu, W., Sun, Y.-h., et al.: An ontology-based text-mining method to cluster proposals for research project selection. IEEE Trans. Syst. Man Cybern. Syst. Hum. 42(3), 784\u2013790 (2012)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst. Hum."},{"doi-asserted-by":"crossref","unstructured":"Parapar, J., Barreiro, A.: Evaluation of Text Clustering Algorithms with N-Gram-Based Document Fingerprints. ECIR, pp. 645\u2013653 (2009)","key":"197_CR26","DOI":"10.1007\/978-3-642-00958-7_61"},{"doi-asserted-by":"crossref","unstructured":"Park, S., An, D.U., Char, B.R., et al.: Document Clustering with Cluster Refinement and Non-negative Matrix Factorization. ICONIP. (2), 281\u2013288 (2009)","key":"197_CR27","DOI":"10.1007\/978-3-642-10684-2_31"},{"issue":"6","key":"197_CR28","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1587\/transinf.E94.D.1227","volume":"94","author":"S Park","year":"2011","unstructured":"Park, S., Lee, S.R.: Enhancing document clustering using condensing cluster terms and fuzzy association. IEICE Trans. Inf. Syst. 94(6), 1227\u20131234 (2011)","journal-title":"IEICE Trans. Inf. Syst."},{"doi-asserted-by":"crossref","unstructured":"Pawlak, Z.: Rough Sets, Theoretical Aspects of Reasoning about Data. Kluwer Academic Publishers, Dordrecht (1991)","key":"197_CR29","DOI":"10.1007\/978-94-011-3534-4_7"},{"doi-asserted-by":"crossref","unstructured":"Pawlak, Z.: Granularity of knowledge, indiscernibility and rough sets. In: Proceedings of IEEE International Conference on Fuzzy Systems, pp. 106\u2013110. Anchorage, Alaska (1998)","key":"197_CR30","DOI":"10.1109\/FUZZY.1998.687467"},{"issue":"11","key":"197_CR31","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1145\/361219.361220","volume":"18","author":"G Salton","year":"1975","unstructured":"Salton, G., Wong, A., Yang, C.S.: A vector space model for automatic indexing. Commun. ACM 18(11), 613\u2013620 (1975)","journal-title":"Commun. ACM"},{"doi-asserted-by":"crossref","unstructured":"Sedding, J., Kazakov, D.: WordNet-based text document clustering. In: Proceedings of COLING-2004 Workshop on Robust Methods in Analysis of Natural Language Data, pp. 104\u2013113. Geneva, Switzerland (2004)","key":"197_CR32","DOI":"10.3115\/1621445.1621458"},{"doi-asserted-by":"crossref","unstructured":"Siivola, V., Pellom, B.: Growing an n-gram language model. In: Proceedings of the 9th European Conference on Speech Communication and Technology (INTERSPEECH\u201905), pp. 1309\u20131312. Lisbon, Portugal (2005)","key":"197_CR33","DOI":"10.21437\/Interspeech.2005-24"},{"unstructured":"Steinbach, M., Karypis, G., Kumar, V.: A comparison of document clustering techniques. KDD-2000 Workshop on Text Mining, (2000)","key":"197_CR34"},{"issue":"17","key":"197_CR35","doi-asserted-by":"crossref","first-page":"1935","DOI":"10.1093\/bioinformatics\/btn318","volume":"24","author":"T Theodosiou","year":"2008","unstructured":"Theodosiou, T., Darzentas, N., Angelis, L., Ouzounis, C.A.: PuReD-MCL: a graph-based PubMed document clustering methodology. Bioinformatics 24(17), 1935\u20131941 (2008)","journal-title":"Bioinformatics"},{"key":"197_CR36","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1007\/s10115-010-0372-2","volume":"29","author":"FS Tsai","year":"2011","unstructured":"Tsai, F.S., Zhang, Y.: D2S: document-to-sentence framework for novelty detection. Knowl. Inf. Syst. (KAIS) 29, 419\u2013433 (2011)","journal-title":"Knowl. Inf. Syst. (KAIS)"},{"doi-asserted-by":"crossref","unstructured":"Varelas, G., Voutsakis, E., Raftopoulou, P., et al.: Semantic similarity methods in wordNet and their application to information retrieval on the web. In: Proceedings of Seventh ACM International Workshop on Web Information and Data Management (WIDM 2005), pp. 10\u201316. Bremen, Germany (2005)","key":"197_CR37","DOI":"10.1145\/1097047.1097051"},{"doi-asserted-by":"crossref","unstructured":"Wang, F., Li, P., K\u00f6nig, A.C.: Efficient Document Clustering via Online Nonnegative Matrix Factorizations. SDM, pp. 908\u2013919 (2011)","key":"197_CR38","DOI":"10.1137\/1.9781611972818.78"},{"key":"197_CR39","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1002\/1098-111X(200101)16:1<87::AID-INT7>3.0.CO;2-S","volume":"16","author":"YY Yao","year":"2001","unstructured":"Yao, Y.Y.: Information granulation and rough set approximation. Int. J. Intell. Syst. 16, 87\u2013104 (2001)","journal-title":"Int. J. Intell. Syst."},{"key":"197_CR40","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1007\/978-3-540-27794-1_11","volume":"1","author":"YY Yao","year":"2004","unstructured":"Yao, Y.Y.: A partition model of granular computing. LNCS Trans. Rough Sets 1, 232\u2013253 (2004)","journal-title":"LNCS Trans. Rough Sets"},{"doi-asserted-by":"crossref","unstructured":"Yao, Y.Y.: Granular computing for the design of information retrieval support systems. In: Wu, W., Xiong, H., Shekhar, S. (eds.) Information Retrieval and Clustering. Kluwer Academic Publishers 299 (2003)","key":"197_CR41","DOI":"10.1007\/978-1-4613-0227-8_10"},{"doi-asserted-by":"crossref","unstructured":"Yao,Y.Y.: Granular computing for data mining. In: Proceedings of SPIE Conference on Data Mining, Intrusion Detection, Information Assurance, and Data Networks Security, pp. 1\u201312. Orlando, FL, USA (2006)","key":"197_CR42","DOI":"10.1117\/12.669023"},{"key":"197_CR43","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/S0165-0114(97)00077-8","volume":"19","author":"LA Zadeh","year":"1997","unstructured":"Zadeh, L.A.: Towards a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy Set Syst. 19, 111\u2013127 (1997)","journal-title":"Fuzzy Set Syst."},{"key":"197_CR44","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s005000050030","volume":"2","author":"LA Zadeh","year":"1998","unstructured":"Zadeh, L.A.: Some reflections on soft computing, granular computing and their roles in the conception, design and utilization of information\/intelligent systems. Soft Comput. 2, 23\u201325 (1998)","journal-title":"Soft Comput."},{"unstructured":"Zheng W.: Architecture for Paragraphs (in Chinese). Fujian People\u2019s Press, Fuzhou, China (1984)","key":"197_CR45"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-012-0197-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11280-012-0197-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-012-0197-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T17:03:45Z","timestamp":1745946225000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11280-012-0197-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,1,15]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,1]]}},"alternative-id":["197"],"URL":"https:\/\/doi.org\/10.1007\/s11280-012-0197-x","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"type":"print","value":"1386-145X"},{"type":"electronic","value":"1573-1413"}],"subject":[],"published":{"date-parts":[[2013,1,15]]}}}