{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T02:16:26Z","timestamp":1775096186107,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2017,2,27]],"date-time":"2017-02-27T00:00:00Z","timestamp":1488153600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Scientometrics"],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1007\/s11192-017-2298-x","type":"journal-article","created":{"date-parts":[[2017,2,27]],"date-time":"2017-02-27T14:33:59Z","timestamp":1488206039000},"page":"1017-1031","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["Clustering articles based on semantic similarity"],"prefix":"10.1007","volume":"111","author":[{"given":"Shenghui","family":"Wang","sequence":"first","affiliation":[]},{"given":"Rob","family":"Koopman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,2,27]]},"reference":[{"issue":"4","key":"2298_CR1","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1016\/S0022-0000(03)00025-4","volume":"66","author":"D Achlioptas","year":"2003","unstructured":"Achlioptas, D. (2003). Database-friendly random projections: Johnson\u2013Lindenstrauss with binary coins. Journal of Computer and System Sciences, 66(4), 671\u2013687. doi:\n                        10.1016\/S0022-0000(03)00025-4\n                        \n                    .","journal-title":"Journal of Computer and System Sciences"},{"key":"2298_CR2","unstructured":"B\u00e9jar, J. (2013). K-means vs mini batch k-means: A comparison. Tech. rep., Universitat Polit\u00e8cnica de Catalunya. \n                        http:\/\/upcommons.upc.edu\/bitstream\/handle\/2117\/23414\/R13-8.pdf\n                        \n                    ."},{"key":"2298_CR3","doi-asserted-by":"publisher","first-page":"P10008","DOI":"10.1088\/1742-5468\/2008\/10\/P10008","volume":"10","author":"VD Blondel","year":"2008","unstructured":"Blondel, V. D., Guillaume, J. L., Lambiotte, R., & Lefebvre, E. (2008). Fast unfolding of communities in large networks. Journal of Statistical Mechanics: Theory and Experiment, 10, P10008. (12pp).","journal-title":"Journal of Statistical Mechanics: Theory and Experiment"},{"issue":"3","key":"2298_CR4","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s11192-005-0255-6","volume":"64","author":"KW Boyack","year":"2005","unstructured":"Boyack, K. W., Klavans, R., & B\u00f6rner, K. (2005). Mapping the backbone of science. Scientometrics, 64(3), 351\u2013374.","journal-title":"Scientometrics"},{"issue":"9","key":"2298_CR5","doi-asserted-by":"publisher","first-page":"1759","DOI":"10.1002\/asi.22896","volume":"64","author":"KW Boyack","year":"2013","unstructured":"Boyack, K. W., Small, H., & Klavans, R. (2013). Improving the accuracy of co-citation clustering using full text. Journal of the American Society for Information Science and Technology, 64(9), 1759\u20131767. doi:\n                        10.1002\/asi.22896\n                        \n                    .","journal-title":"Journal of the American Society for Information Science and Technology"},{"issue":"1\u20132","key":"2298_CR6","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/BF02019160","volume":"18","author":"E Bruckner","year":"1990","unstructured":"Bruckner, E., Ebeling, W., & Scharnhorst, A. (1990). The application of evolution models in scientometrics. Scientometrics, 18(1\u20132), 21\u201341. doi:\n                        10.1007\/BF02019160\n                        \n                    .","journal-title":"Scientometrics"},{"key":"2298_CR7","unstructured":"Firth, J.R. (1957). A synopsis of linguistic theory 1930\u20131955. Studies in Linguistic Analysis pp. 1\u201332."},{"issue":"6","key":"2298_CR8","doi-asserted-by":"publisher","first-page":"17531806","DOI":"10.1002\/j.1538-7305.1983.tb03513.x","volume":"62","author":"GW Furnas","year":"1983","unstructured":"Furnas, G. W., Landauer, T. K., Gomez, L. M., & Dumais, S. T. (1983). Statistical semantics: Analysis of the potential performance of keyword information systems. Bell System Technical Journal, 62(6), 17531806. doi:\n                        10.1002\/j.1538-7305.1983.tb03513.x\n                        \n                    .","journal-title":"Bell System Technical Journal"},{"key":"2298_CR9","volume-title":"Citation indexing\u2014Its theory and application in science, technology and humanities","author":"E Garfield","year":"1983","unstructured":"Garfield, E. (1983). Citation indexing\u2014Its theory and application in science, technology and humanities. Philadelphia: ISI Press."},{"key":"2298_CR10","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/BF02093621","volume":"37","author":"W Gl\u00e4nzel","year":"1996","unstructured":"Gl\u00e4nzel, W., & Czerwon, H. J. (1996). A new methodological approach to bibliographic coupling and its application to the national, regional and institutional level. Scientometrics, 37, 195\u2013221.","journal-title":"Scientometrics"},{"key":"2298_CR11","doi-asserted-by":"publisher","unstructured":"Gl\u00e4nzel, W., & Thijs, B. (2017). Using hybrid methods and \u2018core documents\u2019 for the representation of clusters and topics. the astronomy dataset. Scientometrics. doi:\n                        10.1007\/s11192-017-2301-6\n                        \n                    .","DOI":"10.1007\/s11192-017-2301-6"},{"key":"2298_CR12","doi-asserted-by":"publisher","unstructured":"Gl\u00e4ser, J., Gl\u00e4nzel, W., & Scharnhorst, A. (2017). Same data: different results? Towards a comparative approach to the identification of thematic structures in science. Scientometrics. doi:\n                        10.1007\/s11192-017-2296-z\n                        \n                    .","DOI":"10.1007\/s11192-017-2296-z"},{"issue":"23","key":"2298_CR13","first-page":"146162","volume":"10","author":"Z Harris","year":"1954","unstructured":"Harris, Z. (1954). Distributional structure. Word, 10(23), 146162.","journal-title":"Word"},{"key":"2298_CR14","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1090\/conm\/026\/737400","volume":"26","author":"W Johnson","year":"1984","unstructured":"Johnson, W., & Lindenstrauss, J. (1984). Extensions of Lipschitz mappings into a Hilbert space. Contemporary Mathematics, 26, 189\u2013206.","journal-title":"Contemporary Mathematics"},{"key":"2298_CR15","unstructured":"Koopman, R., Wang, S., & Scharnhorst, A. (2015) .Contextualization of topics\u2014browsing through terms, authors, journals and cluster allocations. In: Salah, A.A., Tonta, Y., Salah, A.A.A., Sugimoto, C.R., Al, U., (Eds.), Proceedings of ISSI 2015 Istanbul: 15th International Society of Scientometrics and Informetrics Conference, Istanbul, Turkey, 29 June to 3 July, 2015. Bogazi\u00e7i University Printhouse. \n                        http:\/\/www.issi2015.org\/files\/downloads\/all-papers\/1042.pdf\n                        \n                    ."},{"key":"2298_CR16","doi-asserted-by":"publisher","unstructured":"Koopman, R., Wang, S., & Scharnhorst, A. (2017). Contextualization of topics\u2014browsing through the universe of bibliographic information. In J. Gl\u00e4ser, A. Scharnhorst, & W. Gl\u00e4nzel (Eds.), Same  data\u2014different results? Towards a comparative approach to the identification of thematic structures in science, Special Issue of Scientometrics.","DOI":"10.1007\/s11192-017-2303-4"},{"key":"2298_CR17","doi-asserted-by":"publisher","unstructured":"Koopman, R., Wang, S., Scharnhorst, A., & Englebienne, G. (2015). Ariadne\u2019s thread: Interactive navigation in a world of networked information. In: Begole, B., Kim, J., Inkpen, K., Woo, W., (Eds.), Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems, Seoul, CHI 2015 Extended Abstracts, Republic of Korea, April 18\u201323, 2015, pp. 1833\u20131838. ACM doi:\n                        10.1145\/2702613.2732781\n                        \n                    .","DOI":"10.1145\/2702613.2732781"},{"issue":"4","key":"2298_CR18","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/0048-7333(89)90016-4","volume":"18","author":"L Leydesdorff","year":"1989","unstructured":"Leydesdorff, L. (1989). Words and co-words as indicators of intellectual organization. Research Policy, 18(4), 209\u2013223. doi:\n                        10.1016\/0048-7333(89)90016-4\n                        \n                    .","journal-title":"Research Policy"},{"issue":"2","key":"2298_CR19","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s11192-006-0096-y","volume":"67","author":"L Leydesdorff","year":"2006","unstructured":"Leydesdorff, L., & Hellsten, I. (2006). Measuring the meaning of words in contexts: An automated analysis of controversies about\u2019monarch butterflies\u201d,frankenfoods\u2019,and\u2019stem cells\u2019. Scientometrics, 67(2), 231\u2013258.","journal-title":"Scientometrics"},{"key":"2298_CR20","unstructured":"MacKay, D. (2003). Information Theory, Inference and Learning Algorithms, chap. Chapter 20. An Example Inference Task: Clustering, p. 284292. Cambridge University Press."},{"key":"2298_CR21","doi-asserted-by":"publisher","unstructured":"Newman, M. E. (2006). Modularity and community structure in networks. Proc Natl Acad Sci USA, 103(23), 8577\u20138582. doi:\n                        10.1073\/pnas.0601602103\n                        \n                    . \n                        http:\/\/www.ncbi.nlm.nih.gov\/sites\/entrez?cmd=retrieve&db=pubmed&list_uids=16723398&dopt=AbstractPlus\n                        \n                    .","DOI":"10.1073\/pnas.0601602103"},{"issue":"6","key":"2298_CR22","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/BF02025827","volume":"6","author":"A Rip","year":"1984","unstructured":"Rip, A., & Courtial, J. P. (1984). Co-word maps of biotechnology: An example of cognitive scientometrics. Scientometrics, 6(6), 381\u2013400.","journal-title":"Scientometrics"},{"issue":"1","key":"2298_CR23","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"P Rousseeuw","year":"1987","unstructured":"Rousseeuw, P. (1987). Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20(1), 53\u201365. doi:\n                        10.1016\/0377-0427(87)90125-7\n                        \n                    .","journal-title":"Journal of Computational and Applied Mathematics"},{"issue":"1","key":"2298_CR24","first-page":"3353","volume":"20","author":"M Sahlgren","year":"2008","unstructured":"Sahlgren, M. (2008). The distributional hypothesis. Rivista di Linguistica, 20(1), 3353.","journal-title":"Rivista di Linguistica"},{"key":"2298_CR25","unstructured":"Sculley, D. (2016). Web scale k-means clustering. In: Proceedings of the 19th International Conference on World Wide Web, p. 11771178. Raleigh, NC, USA."},{"key":"2298_CR26","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1002\/asi.4630240406","volume":"24","author":"H Small","year":"1973","unstructured":"Small, H. (1973). Co-citation in the scientific literature: A new measure of the relationship between two documents. Journal of the American Society for Information Science, 24, 265\u2013269.","journal-title":"Journal of the American Society for Information Science"},{"key":"2298_CR27","doi-asserted-by":"publisher","unstructured":"Sugimoto, C. R., & Weingart, S. (2015). The kaleidoscope of disciplinarity. Journal of Documentation, 71(4), 775\u2013794. doi:\n                        10.1108\/JD-06-2014-0082\n                        \n                    . \n                        http:\/\/www.scopus.com\/inward\/record.url?eid=2-s2.0-84933503812&partnerID=tZOtx3y1\n                        \n                    .","DOI":"10.1108\/JD-06-2014-0082"},{"key":"2298_CR28","doi-asserted-by":"publisher","unstructured":"Velden, T., Boyack, K., van Eck, N., Gl\u00e4nzel, W., Gl\u00e4ser, J., Havemann, F., Heinz, M., Koopman, R., Scharnhorst, A., Thijs, B., & Wang, S. (2017). Comparison of topic extraction approaches and their results. In J. Gl\u00e4ser, A. Scharnhorst, & W. Gl\u00e4nzel (Eds.), Same data\u2014different results? Towards a comparative approach to the identification of thematic structures in science, Special Issue of Scientometrics.","DOI":"10.1007\/s11192-017-2306-1"},{"key":"2298_CR29","first-page":"28372854","volume":"11","author":"NX Vinh","year":"2010","unstructured":"Vinh, N. X., Epps, J., & Bailey, J. (2010). Information theoretic measures for clusterings comparison: Variants, properties, normalization and correction for chance. Journal of Machine Learning Research, 11, 28372854.","journal-title":"Journal of Machine Learning Research"},{"key":"2298_CR30","first-page":"15","volume-title":"Machine translation of languages","author":"W Weaver","year":"1955","unstructured":"Weaver, W. (1955). Translation. In W. Locke & D. Booth (Eds.), Machine translation of languages (pp. 15\u201323). Cambridge, Massachusetts: MIT Press."},{"key":"2298_CR31","volume-title":"Data mining: Practical machine learning tools and techniques, third edition edn. The Morgan Kaufmann series in data management systems","author":"IH Witten","year":"2011","unstructured":"Witten, I. H., Frank, E., & Hall, M. A. (2011). Data mining: Practical machine learning tools and techniques, third edition edn. The Morgan Kaufmann series in data management systems. Burlington: Morgan Kaufmann."},{"key":"2298_CR32","doi-asserted-by":"publisher","unstructured":"Zhang, L., Liu, X., Janssens, F., Liang, L., & Gl\u00e4nzel, W. (2010). Subject clustering analysis based on ISI category classification. Journal of Informetrics, 4(2), 185\u2013193. doi:\n                        10.1016\/j.joi.2009.11.005\n                        \n                    . \n                        http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1751157709000832\n                        \n                    .","DOI":"10.1016\/j.joi.2009.11.005"},{"key":"2298_CR33","doi-asserted-by":"publisher","unstructured":"Zhang, L., Liu, X., Janssens, F., Liang, L., & Gl\u00e4nzel, W. (2010). Subject clustering analysis based on ISI category classification. Journal of Informetrics\n                    4(2), 185\u2013193. doi:\n                        10.1016\/j.joi.2009.11.005\n                        \n                    . \n                        http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1751157709000832\n                        \n                    . The ASIS&ISSI \u201dmetrics\u201d pre-conference seminar and the Global Alliance.","DOI":"10.1016\/j.joi.2009.11.005"}],"container-title":["Scientometrics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11192-017-2298-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11192-017-2298-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11192-017-2298-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,4,21]],"date-time":"2017-04-21T16:38:06Z","timestamp":1492792686000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11192-017-2298-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,27]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,5]]}},"alternative-id":["2298"],"URL":"https:\/\/doi.org\/10.1007\/s11192-017-2298-x","relation":{},"ISSN":["0138-9130","1588-2861"],"issn-type":[{"value":"0138-9130","type":"print"},{"value":"1588-2861","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,2,27]]}}}