{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T10:40:05Z","timestamp":1749811205181,"version":"3.41.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/wincom.2016.7777212","type":"proceedings-article","created":{"date-parts":[[2016,12,8]],"date-time":"2016-12-08T21:34:10Z","timestamp":1481232850000},"page":"187-192","source":"Crossref","is-referenced-by-count":3,"title":["Information content measures of semantic similarity between documents based on Hadoop system"],"prefix":"10.1109","author":[{"given":"Marouane","family":"Birjali","sequence":"first","affiliation":[]},{"given":"Abderrahim","family":"Beni-Hssane","sequence":"additional","affiliation":[]},{"given":"Mohammed","family":"Erritali","sequence":"additional","affiliation":[]},{"given":"Youness","family":"Madani","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/1699571.1699616"},{"key":"ref11","article-title":"Identifying and Filtering Near Duplicate Documents","author":"broder","year":"2000","journal-title":"Computer Processing"},{"key":"ref12","first-page":"547","article-title":"Comparative de la Distribution Florale Dans Une Portion Des Alpes et Des Jura","volume":"37","author":"jaccard","year":"1901","journal-title":"Bulletin del la Socit Vaudoise des Sciences Naturelles"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1835449.1835562"},{"article-title":"Efficient Parallel Setsimilarity Joins","year":"0","author":"vernica","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICICA.2014.16"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2010.5496972"},{"key":"ref17","article-title":"Document Identification with MapReduce Framework","author":"yenumula b","year":"0","journal-title":"DATA ANALYTICS 2014 The Third International Conference on Data Analytics"},{"journal-title":"WordNet et son ecosysteme un ensemble de ressources linguistiques de large couverture","year":"0","author":"chaumartin","key":"ref18"},{"key":"ref19","article-title":"An Information-Theoretic Definition of similarity","author":"lin","year":"1998","journal-title":"Machine Learning Proceedings of the Fifteenth International Conference (ICML)"},{"article-title":"Modern Information Retrieval","year":"1999","author":"baeza-yates","key":"ref4"},{"key":"ref3","article-title":"La similarit&#x00E9;: une notion symbolique\/num&#x00E9;rique","author":"bisson","year":"2000","journal-title":"Apprentissag symbolique num&#x00E9;rique (tome 2) Editions CEPADUES"},{"article-title":"Duplicate data detection","year":"2004","author":"chowdhury","key":"ref6"},{"key":"ref5","first-page":"514","article-title":"Duplicate and Near Duplicate Documents Detection: A Review","volume":"32","author":"kumar","year":"2009","journal-title":"European Journal of Scientific Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/1225797.1225804"},{"key":"ref7","article-title":"Detecting Short Passages of Similar Text in Large Document Collections","author":"lyon","year":"2001","journal-title":"Proc EMNLP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CTS.2013.6567203"},{"key":"ref9","article-title":"Detecting Text Similarity over Short Passages: Exploring Linguistic Feature Cominations via Machine Learning","author":"hatzivassiloglou","year":"1999","journal-title":"Proc SIGDA"},{"journal-title":"Improving Decision Making in the World of Big Data","year":"0","key":"ref1"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1613\/jair.514","article-title":"Semantic similarity in a taxonomy: An information based measure and its application to problems of ambiguity in natural language","volume":"11","author":"resnik","year":"1999","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref22","article-title":"Using information content to evaluate semantic similarity in taxonomy","author":"resnik","year":"1995","journal-title":"Proceedings of 14th International Joint Conference on Artificial Intelligence"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1613\/jair.514","article-title":"Semantic similarity in a taxonomy: An information based measure and its application to problems of ambiguity in natural language","volume":"11","author":"resnik","year":"1999","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7287.003.0018","article-title":"Combining Local Context and WordNet Similarity for Word Sense Identification","author":"leacock","year":"1998","journal-title":"WordNet An Electronic Lexical Database"},{"key":"ref23","article-title":"Semantic similarity based on corpus statistics and lexical taxonomy","author":"jiang","year":"1997","journal-title":"Proceedings of International Conference on Research in Computational Linguistics"},{"article-title":"Modern Information Retrieval","year":"1999","author":"baeza-yates","key":"ref25"}],"event":{"name":"2016 International Conference on Wireless Networks and Mobile Communications (WINCOM)","start":{"date-parts":[[2016,10,26]]},"location":"Fez, Morocco","end":{"date-parts":[[2016,10,29]]}},"container-title":["2016 International Conference on Wireless Networks and Mobile Communications (WINCOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7764433\/7777180\/07777212.pdf?arnumber=7777212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T10:20:38Z","timestamp":1749810038000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7777212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/wincom.2016.7777212","relation":{},"subject":[],"published":{"date-parts":[[2016,10]]}}}