{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T05:26:23Z","timestamp":1769837183646,"version":"3.49.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031238031","type":"print"},{"value":"9783031238048","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-23804-8_25","type":"book-chapter","created":{"date-parts":[[2023,2,25]],"date-time":"2023-02-25T12:02:40Z","timestamp":1677326560000},"page":"314-328","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SMGKM: An Efficient Incremental Algorithm for\u00a0Clustering Document Collections"],"prefix":"10.1007","author":[{"given":"Adil","family":"Bagirov","sequence":"first","affiliation":[]},{"given":"Sattar","family":"Seifollahi","sequence":"additional","affiliation":[]},{"given":"Massimo","family":"Piccardi","sequence":"additional","affiliation":[]},{"given":"Ehsan","family":"Zare Borzeshi","sequence":"additional","affiliation":[]},{"given":"Bernie","family":"Kruger","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,26]]},"reference":[{"key":"25_CR1","unstructured":"Arthur, D., Vassilvitskii, S.: $$k$$-means++: the advantages of careful seeding. In: Gabow, H. (ed.) Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms [SODA 2007], Philadelphia, pp. 1027\u20131035 (2007)"},{"issue":"10","key":"25_CR2","doi-asserted-by":"publisher","first-page":"3192","DOI":"10.1016\/j.patcog.2008.04.004","volume":"41","author":"AM Bagirov","year":"2008","unstructured":"Bagirov, A.M.: Modified global $$k$$-means algorithm for minimum sum-of-squares clustering problems. Pattern Recogn. 41(10), 3192\u20133199 (2008)","journal-title":"Pattern Recogn."},{"issue":"4","key":"25_CR3","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1016\/j.patcog.2010.10.018","volume":"44","author":"AM Bagirov","year":"2011","unstructured":"Bagirov, A.M., Ugon, J., Webb, D.: Fast modified global $$k$$-means algorithm for incremental cluster construction. Pattern Recogn. 44(4), 866\u2013876 (2011)","journal-title":"Pattern Recogn."},{"key":"25_CR4","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.ins.2013.05.023","volume":"245","author":"L Bai","year":"2013","unstructured":"Bai, L., Liang, J., Sui, C., Dang, C.: Fast global $$k$$-means clustering based on local geometrical information. Inf. Sci. 245, 168\u2013180 (2013)","journal-title":"Inf. Sci."},{"key":"25_CR5","first-page":"1345","volume":"6","author":"A Banerjee","year":"2005","unstructured":"Banerjee, A., Dhillon, I.S., Ghosh, J., Sra, S.: Clustering on the unit hypersphere using Von Mises-Fisher distributions. J. Mach. Learn. Res. 6, 1345\u20131382 (2005)","journal-title":"J. Mach. Learn. Res."},{"issue":"106","key":"25_CR6","first-page":"168","volume":"16","author":"D Blei","year":"2004","unstructured":"Blei, D., Griffiths, T., Jordan, M.I., Tenenbaum, J.: Hierarchical topic models and the nested chinese restaurant process. Adv. Neural. Inf. Process. Syst. 16(106), 168\u2013180 (2004)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Buckley, C., Lewit, A.F.: Optimizations of inverted vector searches. In: SIGIR 1985, pp. 97\u2013110 (1985)","DOI":"10.1145\/253495.253515"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Dhillon, S., Fan, J., Guan, Y.: Efficient clustering of very large document collections. In: Data Mining for Scientific and Engineering Applications. Kluwer Academic Publishers, Oxford (2001)","DOI":"10.1007\/978-1-4615-1733-7_20"},{"key":"25_CR9","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.ins.2014.08.062","volume":"292","author":"U Erra","year":"2015","unstructured":"Erra, U., Senatore, S., Minnella, F., Caggianese, G.: Approximate TF-IDF based on topic extraction from massive message stream using the GPU. Inf. Sci. 292, 143\u2013161 (2015)","journal-title":"Inf. Sci."},{"key":"25_CR10","unstructured":"Harman, D.: Overview of the first text retrieval conference (TREC-1). In: Proceedings of the First Text Retrieval Conference (TREC-1), pp. 1\u201320. DIANE Publishing (1979)"},{"key":"25_CR11","doi-asserted-by":"publisher","first-page":"100","DOI":"10.2307\/2346830","volume":"28","author":"JA Hartigan","year":"1979","unstructured":"Hartigan, J.A., Wong, M.A.: A $$k$$-means clustering algorithm. Appl. Stat. 28, 100\u2013108 (1979)","journal-title":"Appl. Stat."},{"issue":"3","key":"25_CR12","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"AK Jain","year":"1999","unstructured":"Jain, A.K., Murty, M.N., Flynn, P.J.: Data clustering: a review. ACM Comput. Surv. 31(3), 264\u2013323 (1999)","journal-title":"ACM Comput. Surv."},{"key":"25_CR13","unstructured":"Kogan, J.: Introduction to Clustering Large and High-dimensional Data. Cambridge University Press, Cambridge (2007)"},{"key":"25_CR14","unstructured":"Kowalski, G.: Information Retrieval Systems - Theory and Implementation. Kluwer Academic Publishers, Dordrecht (1997)"},{"issue":"5","key":"25_CR15","doi-asserted-by":"publisher","first-page":"1954","DOI":"10.1016\/j.patcog.2009.11.021","volume":"43","author":"JZC Lai","year":"2010","unstructured":"Lai, J.Z.C., Huang, T.-J.: Fast global $$k$$-means clustering using cluster membership and inequality. Pattern Recogn. 43(5), 1954\u20131963 (2010)","journal-title":"Pattern Recogn."},{"key":"25_CR16","unstructured":"Lewis, D.D.: Reuters-21578 text categorization collection distribution 1.0 (1997). http:\/\/kdd.ics.uci.edu\/databases\/reuters21578\/reuters21578.html"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xiao, S., Lv, X., Shi, S.: Research on k-means text clustering algorithm based on semantic. In: Proceedings of 10th International Conference on Computing, Control and Industrial Engineering (CCIE 2010), vol. 1, pp. 124\u2013127 (2010)","DOI":"10.1109\/CCIE.2010.39"},{"key":"25_CR18","doi-asserted-by":"publisher","first-page":"530","DOI":"10.2174\/1874110X01408010530","volume":"8","author":"J Ma","year":"2014","unstructured":"Ma, J.: Improved k-means algorithm in text semantic clustering. Open Cybern. Syst. J. 8, 530\u2013534 (2014)","journal-title":"Open Cybern. Syst. J."},{"issue":"2","key":"25_CR19","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1023\/A:1009953814988","volume":"3","author":"A McCallum","year":"2000","unstructured":"McCallum, A., Nigam, K., Rennie, J., Seymore, K.: Automating the construction of internet portals with machine learning. Inf. Retrieval 3(2), 127\u2013163 (2000)","journal-title":"Inf. Retrieval"},{"issue":"4","key":"25_CR20","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1007\/s00521-014-1792-9","volume":"26","author":"C Qimin","year":"2015","unstructured":"Qimin, C., Qiao, G., Yongliang, W., Xianghua, W.: Text clustering using VSM with feature clusters. Neural Comput. Appl. 26(4), 995\u20131003 (2015)","journal-title":"Neural Comput. Appl."},{"key":"25_CR21","unstructured":"Rennie, J.: The 20 newsgroups data set (2008). http:\/\/qwone.com\/jason\/20Newsgroups, 1997"},{"key":"25_CR22","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/s10898-014-0171-5","volume":"61","author":"B Ordin","year":"2015","unstructured":"Ordin, B., Bagirov, A.M.: A heuristic algorithm for solving the minimum sum-of-squares clustering problems. J. Global Optim. 61, 341\u2013361 (2015)","journal-title":"J. Global Optim."},{"issue":"5","key":"25_CR23","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"S Salton","year":"1988","unstructured":"Salton, S., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24(5), 513\u2013523 (1988)","journal-title":"Inf. Process. Manag."},{"key":"25_CR24","volume-title":"Introduction to Modern Retrieval","author":"G Salton","year":"1983","unstructured":"Salton, G., McGill, M.J.: Introduction to Modern Retrieval. McGraw-Hill Book Company, New York (1983)"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Seifollahi, S., Bagirov, A., Layton, R., Gondal, I.: Optimization based clustering algorithms for authorship analysis of phishing emails. Neural Process. Lett. 1\u201315 (2017)","DOI":"10.1007\/s11063-017-9593-7"},{"key":"25_CR26","unstructured":"Van Rijsbergen, C.J.: Information Retrieval, 2nd edition. Buttersworth, London (1989)"},{"key":"25_CR27","unstructured":"WebKB: Available electronically at http:\/\/www.cs.cmu.edu\/~WebKB"},{"key":"25_CR28","first-page":"1","volume":"1","author":"J Yi","year":"2017","unstructured":"Yi, J., Zhang, Y., Zhao, X., Wan, J.: A novel text clustering approach using deep-learning vocabulary network. Math. Probl. Eng. 1, 1\u201313 (2017)","journal-title":"Math. Probl. Eng."},{"key":"25_CR29","doi-asserted-by":"publisher","first-page":"2758","DOI":"10.1016\/j.eswa.2010.08.066","volume":"38","author":"W Zhang","year":"2011","unstructured":"Zhang, W., Yoshida, T., Tang, X.: A comparative study of TF-IDF, LSI and multi-words for text classification. Expert Syst. Appl. 38, 2758\u20132765 (2011)","journal-title":"Expert Syst. Appl."}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-23804-8_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,25]],"date-time":"2023-02-25T12:05:52Z","timestamp":1677326752000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-23804-8_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031238031","9783031238048"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-23804-8_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"26 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICLing","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Linguistics and Intelligent Text Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 March 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 March 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicling2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cicling.org\/2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}