{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:58:46Z","timestamp":1774875526077,"version":"3.50.1"},"reference-count":80,"publisher":"Emerald","issue":"3","license":[{"start":{"date-parts":[[1984,3,1]],"date-time":"1984-03-01T00:00:00Z","timestamp":446947200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1984,3,1]]},"abstract":"<jats:p>This paper considers the classifications produced by application of the single linkage, complete linkage, group average and Ward clustering methods to the Keen and Cranfield document test collections. Experiments were carried out to study the structure of the hierarchies produced by the different methods, the extent to which the methods distort the input similarity matrices during the generation of a classification, and the retrieval effectiveness obtainable in cluster based retrieval. The results would suggest that the single linkage method, which has been used extensively in previous work on document clustering, is not the most effective procedure of those tested, although it should be emphasized that the experiments have used only small document test collections.<\/jats:p>","DOI":"10.1108\/eb026764","type":"journal-article","created":{"date-parts":[[2008,1,19]],"date-time":"2008-01-19T07:45:42Z","timestamp":1200728742000},"page":"175-205","source":"Crossref","is-referenced-by-count":72,"title":["HIERARCHIC AGGLOMERATIVE CLUSTERING METHODS FOR AUTOMATIC DOCUMENT CLASSIFICATION"],"prefix":"10.1108","volume":"40","author":[{"given":"ALAN","family":"GRIFFITHS","sequence":"first","affiliation":[]},{"given":"LESLEY A.","family":"ROBINSON","sequence":"additional","affiliation":[]},{"given":"PETER","family":"WILLETT","sequence":"additional","affiliation":[]}],"member":"140","reference":[{"key":"p_1","doi-asserted-by":"publisher","DOI":"10.2307\/2344237"},{"key":"p_2","volume-title":"Mathematical taxonomy","author":"JARDINE N.","year":"1971"},{"key":"p_3","volume-title":"Numerical taxonomy","author":"SNEATH P. H.","year":"1973"},{"key":"p_4","volume-title":"Clustering algorithms","author":"HARTIGAN J. A.","year":"1975"},{"key":"p_5","doi-asserted-by":"publisher","DOI":"10.1016\/S0065-2458(08)60034-0"},{"key":"p_6","volume-title":"Cluster analysis algorithms","author":"SPATH H.","year":"1980"},{"key":"p_8","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-9883-7_4"},{"key":"p_9","first-page":"75","volume":"14","author":"VAN RIJSBERGEN C. J","year":"1978","journal-title":"Drexel Library Quarterly"},{"key":"p_10","volume-title":"Introduction to modem information retrieval","author":"SALTON G.","year":"1983"},{"key":"p_11","volume-title":"The SMART System","author":"SALTON G.","year":"1971"},{"key":"p_12","unstructured":"LITOFSKY, B. Utility of automatic classification systemsfor information storage and retrieval. Ph.D. thesis,University of Pennsylvania, 1969."},{"key":"p_13","first-page":"31","volume":"2","author":"DATTOLA R. T","year":"1969","journal-title":"Journal of Library Automation"},{"key":"p_14","unstructured":"MURRAY, D. M. Document retrieval based on clustered files. Ph.D. thesis,Cornell University, 1972."},{"key":"p_15","unstructured":"WILLIAMSON, R. E. Real-time document retrieval. Ph.D. thesis,Cornell University, 1974."},{"key":"p_16","first-page":"607","volume":"24","author":"YU C. T","year":"1974","journal-title":"Journal oftheAmerican Societyfor Information Science"},{"key":"p_17","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(75)90031-X"},{"key":"p_18","doi-asserted-by":"publisher","DOI":"10.1177\/016555158000200503"},{"key":"p_19","doi-asserted-by":"publisher","DOI":"10.1145\/1013228.511767"},{"key":"p_20","first-page":"275","volume":"1","author":"MURTAGH F","year":"1982","journal-title":"Information Technology: Research and Development"},{"key":"p_21","doi-asserted-by":"publisher","DOI":"10.1177\/016555158300600204"},{"key":"p_22","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0271(71)90051-9"},{"key":"p_23","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(75)90006-0"},{"key":"p_24","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4379(80)90010-1"},{"key":"p_25","doi-asserted-by":"publisher","DOI":"10.1002\/asi.4630280606"},{"key":"p_26","doi-asserted-by":"publisher","DOI":"10.1002\/asi.4630310411"},{"key":"p_27","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(81)90026-1"},{"key":"p_28","first-page":"189","volume":"1","author":"NOREAULT T.","year":"1982","journal-title":"Information Technology: Research and Development"},{"key":"p_29","first-page":"30","volume":"16","author":"SIBSON R.","year":"1973","journal-title":"ComputerJournal"},{"key":"p_30","first-page":"93","volume":"16","author":"ROHLF F","year":"1973","journal-title":"J. Algorithm 76. Hierarchical clustering using the minimum spanning tree. ComputerJournal"},{"key":"p_31","first-page":"364","volume":"20","author":"DEFAYS D","year":"1977","journal-title":"ComputerJournal"},{"key":"p_32","doi-asserted-by":"publisher","DOI":"10.1002\/asi.4630350303"},{"key":"p_33","first-page":"354","volume":"26","author":"MURTAGH F","year":"1983","journal-title":"ComputerJournal"},{"key":"p_34","first-page":"373","volume":"9","author":"LANCE G. N.","year":"1967","journal-title":"ComputerJournal"},{"key":"p_35","doi-asserted-by":"publisher","DOI":"10.1207\/s15327906mbr1403_6"},{"key":"p_36","volume-title":"STEVENS, M. E., GIULIANO, v","author":"DOYLE L. B.","year":"1965"},{"key":"p_37","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7161(82)02015-X"},{"key":"p_38","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(76)90045-5"},{"key":"p_39","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(79)90034-7"},{"key":"p_40","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.es.05.110174.000533"},{"key":"p_41","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0036348"},{"key":"p_42","first-page":"177","volume":"11","author":"JARDINE N.","year":"1968","journal-title":"ComputerJournal"},{"key":"p_43","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/58.1.91"},{"key":"p_44","doi-asserted-by":"publisher","DOI":"10.2307\/2528417"},{"key":"p_45","first-page":"162","volume":"14","author":"WILLIAMS W. T.","year":"1971","journal-title":"ComputerJournal"},{"key":"p_46","volume-title":"A consumer report on cluster analysis software: hierarchical methods","author":"ALDENDERFER M. S.","year":"1977"},{"key":"p_47","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1971.10482356"},{"key":"p_48","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"p_49","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(82)90002-4"},{"key":"p_50","doi-asserted-by":"publisher","DOI":"10.2307\/2529565"},{"key":"p_51","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.83.3.377"},{"key":"p_52","first-page":"359","volume":"20","author":"MOJENA R","year":"1977","journal-title":"ComputerJournal"},{"key":"p_53","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(80)90002-3"},{"key":"p_54","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(80)90001-1"},{"key":"p_55","volume":"393","author":"RAGHAVEN YU","year":"1981","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-3"},{"key":"p_56","doi-asserted-by":"publisher","DOI":"10.1207\/s15327906mbr1603_7"},{"key":"p_57","first-page":"265","volume":"13","author":"MEZZICH J. E","year":"1978","journal-title":"Biological Psychiatry"},{"key":"p_58","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1021\/ci00032a005","volume":"21","author":"ADAMSON G. W.","year":"1981","journal-title":"Journal of Chemical Information and Computer Sciences"},{"key":"p_59","doi-asserted-by":"publisher","DOI":"10.1016\/S0003-2670(01)95360-7"},{"key":"p_60","doi-asserted-by":"publisher","DOI":"10.1207\/s15327906mbr1803_4"},{"key":"p_61","doi-asserted-by":"publisher","DOI":"10.2307\/2529943"},{"key":"p_62","doi-asserted-by":"publisher","DOI":"10.1108\/eb026557"},{"key":"p_63","volume-title":"CLUSTAN 1C User Manual Program Library Unit","author":"WISHART D.","year":"1978"},{"key":"p_64","first-page":"138","volume":"10","author":"WILLETT","year":"1983","journal-title":"International Classification"},{"key":"p_65","doi-asserted-by":"publisher","DOI":"10.2307\/2412343"},{"key":"p_66","doi-asserted-by":"publisher","DOI":"10.2307\/2412378"},{"key":"p_67","doi-asserted-by":"publisher","DOI":"10.1016\/0022-5193(78)90137-6"},{"key":"p_68","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1983.10478008"},{"key":"p_69","volume-title":"Hierarchic structure in cluster analysis. Technical report. Department of Computer Science","author":"MURTAGH F.","year":"1983"},{"key":"p_71","volume-title":"dissertation","author":"ROBINSON L. A.","year":"1983"},{"key":"p_72","doi-asserted-by":"publisher","DOI":"10.2307\/1217208"},{"key":"p_73","doi-asserted-by":"publisher","DOI":"10.2307\/2412324"},{"key":"p_74","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(78)90038-9"},{"key":"p_75","unstructured":"CROFT, W. B. Organizing and searching largefiles of document descriptions. Ph.D. thesis,University of Cambridge, 1979."},{"key":"p_76","volume-title":"Numerical taxonomy.","author":"WISHART D.","year":"1969"},{"key":"p_77","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1973.223640"},{"key":"p_78","doi-asserted-by":"publisher","DOI":"10.1007\/BF00264289"},{"key":"p_79","doi-asserted-by":"publisher","DOI":"10.1145\/356631.356634"},{"key":"p_80","volume-title":"Information retrieval","author":"VAN RIJSBERGEN C. J.","year":"1979"},{"key":"p_81","volume-title":"Nonparametric statistics","author":"SIEGAL S.","year":"1956"},{"key":"p_82","volume-title":"Evaluation of clustering methods for automatic document classification","author":"GRIFFITHS A."}],"container-title":["Journal of Documentation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/eb026764\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/eb026764\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T23:11:10Z","timestamp":1753398670000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/jd\/article\/40\/3\/175-205\/198469"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1984,3,1]]},"references-count":80,"journal-issue":{"issue":"3","published-print":{"date-parts":[[1984,3,1]]}},"alternative-id":["10.1108\/eb026764"],"URL":"https:\/\/doi.org\/10.1108\/eb026764","relation":{},"ISSN":["0022-0418"],"issn-type":[{"value":"0022-0418","type":"print"}],"subject":[],"published":{"date-parts":[[1984,3,1]]}}}