{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T14:41:06Z","timestamp":1704206466676},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"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":["Inf Retrieval"],"published-print":{"date-parts":[[2006,1]]},"DOI":"10.1007\/s10791-005-5720-6","type":"journal-article","created":{"date-parts":[[2006,2,10]],"date-time":"2006-02-10T07:08:28Z","timestamp":1139555308000},"page":"33-53","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Hierarchical clustering of a Finnish newspaper article collection with graded relevance assessments"],"prefix":"10.1007","volume":"9","author":[{"given":"Tuomo","family":"Korenius","sequence":"first","affiliation":[]},{"given":"Jorma","family":"Laurikkala","sequence":"additional","affiliation":[]},{"given":"Martti","family":"Juhola","sequence":"additional","affiliation":[]},{"given":"Kalervo","family":"J\u00e4rvelin","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"3-4","key":"5720_CR1","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1023\/A:1011942104443","volume":"4","author":"R Alkula","year":"2001","unstructured":"Alkula R (2001) From plain character strings to meaningful words: Producing better full text databases for inflectional and compounding languages with morphological analysis software. Information Retrieval, 4(3-4):195\u2013208.","journal-title":"Information Retrieval"},{"key":"5720_CR2","volume-title":"Modern Information Retrieval","author":"R Baeza-Yates","year":"1999","unstructured":"Baeza-Yates R and Ribeiro-Neto B (1999) Modern Information Retrieval. ACM Press\/Addison-Wesley, New York."},{"key":"5720_CR3","volume-title":"Finding Out About","author":"RK Belew","year":"2000","unstructured":"Belew RK (2000) Finding Out About. Cambridge University Press, Cambridge."},{"issue":"4","key":"5720_CR4","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1023\/A:1009740529316","volume":"2","author":"D Boley","year":"1998","unstructured":"Boley D (1998) Principal direction divisive partitioning. Data Mining and Knowledge Discovery, 2(4):325\u2013344.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"5720_CR5","first-page":"318","volume-title":"Proceedings of the 15th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"DR Cutting","year":"1992","unstructured":"Cutting DR, Karger DR, Pedersen JO and Tukey JW (1992) Scatter\/Gather: A cluster-based approach to browsing large document collections. In Belkin N, Ingwersen P and Pejtersen AM, (eds.), Proceedings of the 15th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, pp. 318\u2013329."},{"issue":"3","key":"5720_CR6","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1093\/comjnl\/32.3.220","volume":"32","author":"A El-Hamdouchi","year":"1989","unstructured":"El-Hamdouchi A and Willett P (1989) Comparison of hierachic agglomerative clustering methods for document retrieval. The Computer Journal, 32(3):220\u2013227.","journal-title":"The Computer Journal"},{"key":"5720_CR7","volume-title":"Cluster Analysis","author":"BS Everitt","year":"2001","unstructured":"Everitt BS, Landau S and Leese M (2001) Cluster Analysis, 4th edn. Arnold, London.","edition":"4th edn."},{"key":"5720_CR8","volume-title":"Matrix Analysis","author":"RA Horn","year":"1990","unstructured":"Horn RA and Johnson CR (1990) Matrix Analysis, 4th edn. Cambridge University Press, Cambridge.","edition":"4th edn."},{"key":"5720_CR9","volume-title":"Algorithms for Clustering Data","author":"AK Jain","year":"1988","unstructured":"Jain AK and Dubes RC (1988) Algorithms for Clustering Data. Prentice-Hall, New Jersey."},{"key":"5720_CR10","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-1904-8","volume-title":"Principal Component Analysis","author":"IT Jolliffe","year":"1986","unstructured":"Jolliffe IT (1986) Principal Component Analysis. Springer-Verlag, New York."},{"key":"5720_CR11","first-page":"41","volume-title":"Proceedings of the 23th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"K J\u00e4rvelin","year":"2000","unstructured":"J\u00e4rvelin K and Kek\u00e4l\u00e4inen J (2000) IR evaluation methods for retrieving highly relevant documents. In Belkin N, Ingwersen P and Leong MK, (eds.), Proceedings of the 23th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, pp. 41\u201348."},{"key":"5720_CR12","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316801","volume-title":"Finding Groups in Data","author":"L Kaufman","year":"1990","unstructured":"Kaufman L and Rousseeuw PJ (1990) Finding Groups in Data. Wiley, New York."},{"issue":"4","key":"5720_CR13","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1016\/0306-4573(92)90006-L","volume":"28","author":"EM Keen","year":"1992","unstructured":"Keen EM (1992) Presenting results of experimental retrieval comparisons. Information Processing & Management, 28(4):491\u2013501.","journal-title":"Information Processing & Management"},{"key":"5720_CR14","unstructured":"Kek\u00e4l\u00e4inen J (1999) The Effects of Query Complexity, Expansion and Structure on Retrieval Performance in Probabilistic Text Retrieval. Ph.D. Thesis, University of Tampere. Acta Universitatis Tamperensis, Vol. 678. URL: http:\/\/www.info.uta.fi\/tutkimus\/fire\/archive\/QCES.pdf"},{"issue":"13","key":"5720_CR15","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1002\/asi.10137","volume":"53","author":"J Kek\u00e4l\u00e4inen","year":"2002","unstructured":"Kek\u00e4l\u00e4inen J and J\u00e4rvelin K (2002) Using graded relevance assessments in IR evaluation. Journal of the American Society for Information Science and Technology, 53(13):1120\u20131129.","journal-title":"Journal of the American Society for Information Science and Technology"},{"key":"5720_CR16","unstructured":"Korenius T, Laurikkala J and Juhola M (2004) On applying the principal components analysis and cosine similarity for information retrieval. Manuscript available by a request from the authors."},{"issue":"2","key":"5720_CR17","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/BF02294245","volume":"50","author":"GW Milligan","year":"1985","unstructured":"Milligan GW and Cooper MC (1985) An examination of procedures for determining the number of clusters in a data set. Psychometrika, 50(2):159\u2013179.","journal-title":"Psychometrika"},{"key":"5720_CR18","volume-title":"Machine Learning","author":"TM Mitchell","year":"1997","unstructured":"Mitchell TM (1997) Machine Learning. McGraw-Hill, New York."},{"issue":"4","key":"5720_CR19","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1023\/A:1020443310743","volume":"5","author":"M Nilsson","year":"2002","unstructured":"Nilsson M (2002) Hierarchical clustering using non-greedy principal direction divisive partitioning. Information Retrieval, 5(4):311\u2013321.","journal-title":"Information Retrieval"},{"key":"5720_CR20","volume-title":"Nonparametric Statistics for Health Care Research: Statistics for Small Samples and Unusual Distributions","author":"MA Pett","year":"1997","unstructured":"Pett MA (1997) Nonparametric Statistics for Health Care Research: Statistics for Small Samples and Unusual Distributions. Sage Publications, Thousand Oaks, California."},{"key":"5720_CR21","first-page":"419","volume-title":"Information Retrieval: Data Structures and Algorithms","author":"E Rasmussen","year":"1992","unstructured":"Rasmussen E (1992) Clustering algorithms. In Frakes W and Baeza-Yates R, eds. Information Retrieval: Data Structures and Algorithms. Prentice-Hall, Upper Saddle River, New Jersey, pp. 419\u2013442."},{"key":"5720_CR22","doi-asserted-by":"crossref","DOI":"10.1002\/0471271357","volume-title":"Methods of Multivariate Analysis","author":"AC Rencher","year":"2002","unstructured":"Rencher AC (2002) Methods of Multivariate Analysis, 2nd edn. Wiley, New York.","edition":"2nd edn."},{"key":"5720_CR23","volume-title":"Introduction to Modern Information Retrieval","author":"G Salton","year":"1983","unstructured":"Salton G (1983) Introduction to Modern Information Retrieval. McGraw-Hill, New York."},{"key":"5720_CR24","volume-title":"Automatic Text Processing: The Transformation, Analysis, and Retrieval of Information by Computer","author":"G Salton","year":"1989","unstructured":"Salton G (1989) Automatic Text Processing: The Transformation, Analysis, and Retrieval of Information by Computer. Addison-Wesley, Reading, Massachusetts."},{"issue":"1","key":"5720_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/505282.505283","volume":"34","author":"F Sebastiani","year":"2002","unstructured":"Sebastiani F (2002) Machine learning in automated text categorization. ACM Computing Surveys, 34(1):1\u201347.","journal-title":"ACM Computing Surveys"},{"key":"5720_CR26","volume-title":"Applied Multivariate Techniques","author":"S Sharma","year":"1996","unstructured":"Sharma S (1996) Applied Multivariate Techniques. Wiley, New York."},{"key":"5720_CR27","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1145\/345508.345578","volume-title":"Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"N Slonim","year":"2000","unstructured":"Slonim N and Tishby N (2000) Document clustering using word clusters via the information bottleneck method. In Yannakoudakis E, Belkin NJ, Leong M-K and Ingwersen P, eds. Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, pp. 208\u2013215."},{"key":"5720_CR28","unstructured":"Sormunen E (2000) A Method for Measuring Wide Range Performance of Boolean Queries in Full-Text Databases. Ph.D. Thesis, University of Tampere. Acta Universitatis Tamperensis, Vol. 748. URL: http:\/\/acta.uta.fi\/pdf\/951-44-4732-8.pdf"},{"key":"5720_CR29","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1145\/564376.564433","volume-title":"Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"E Sormunen","year":"2002","unstructured":"Sormunen E (2002) Liberal relevance criteria of TREC - counting on negligible documents? In Beaulieu M, Baeza-Yates R, Myaeng SH, J\u00e4rvelin K, eds. Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, pp. 324\u2013330."},{"key":"5720_CR30","volume-title":"Statistics Toolbox User's Guide","author":"The Math Works Inc.","year":"2002","unstructured":"The Math Works Inc. (2002) Statistics Toolbox User's Guide, 4th edn. The Math Works Inc., Natick.","edition":"4th edn."},{"key":"5720_CR31","volume-title":"Information Retrieval","author":"CJ van Rijsbergen","year":"1980","unstructured":"van Rijsbergen CJ (1980) Information Retrieval, 2nd edn. Butterworths, London.","edition":"2nd edn."},{"key":"5720_CR32","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1145\/383952.383963","volume-title":"Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"E. Voorhees","year":"2001","unstructured":"Voorhees, E. (2001). Evaluation by Highly Relevant Documents. In Croft, WB, Harper, DJ, Kraft, DH & Zobel, J, eds. Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York. pp. 74\u201382."},{"issue":"5","key":"5720_CR33","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1016\/0306-4573(88)90027-1","volume":"24","author":"P Willett","year":"1988","unstructured":"Willett P (1988) Recent trends in hierarchic document clustering: A critical review. Information Processing & Management, 24(5):577\u2013597.","journal-title":"Information Processing & Management"}],"container-title":["Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-005-5720-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-005-5720-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-005-5720-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-005-5720-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T14:13:31Z","timestamp":1704204811000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-005-5720-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,1]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2006,1]]}},"alternative-id":["5720"],"URL":"https:\/\/doi.org\/10.1007\/s10791-005-5720-6","relation":{},"ISSN":["1386-4564","1573-7659"],"issn-type":[{"value":"1386-4564","type":"print"},{"value":"1573-7659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,1]]},"assertion":[{"value":"26 January 2004","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2004","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2004","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}