{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T09:25:25Z","timestamp":1768728325873,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,3,22]],"date-time":"2016-03-22T00:00:00Z","timestamp":1458604800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Hemera"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2017,1]]},"DOI":"10.1007\/s10115-016-0931-2","type":"journal-article","created":{"date-parts":[[2016,3,21]],"date-time":"2016-03-21T22:27:45Z","timestamp":1458599265000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A highly scalable parallel algorithm for maximally informative k-itemset mining"],"prefix":"10.1007","volume":"50","author":[{"given":"Saber","family":"Salah","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reza","family":"Akbarinia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florent","family":"Masseglia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,3,22]]},"reference":[{"key":"931_CR1","unstructured":"Agrawal R, Srikant R (1994) Fast algorithms for mining association rules in large databases. In: Proceedings of international conference on very large data bases (VLDB), pp\u00a0487\u2013499"},{"key":"931_CR2","unstructured":"Amazon (n.d.) , http:\/\/snap.stanford.edu\/data\/web-Amazon-links.html"},{"key":"931_CR3","volume-title":"Mining of massive datasets","author":"R Anand","year":"2012","unstructured":"Anand R (2012) Mining of massive datasets. Cambridge University Press, New York"},{"key":"931_CR4","doi-asserted-by":"crossref","unstructured":"Berberich K, Bedathur S (2013) Computing n-gram statistics in mapreduce. In: Proceedings of the 16th international conference on extending database technology (EDBT), pp\u00a0101\u2013112","DOI":"10.1145\/2452376.2452389"},{"key":"931_CR5","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-84800-046-9","volume-title":"Survey of text mining II clustering, classification, and retrieval","author":"M Berry","year":"2008","unstructured":"Berry M (2008) Survey of text mining II clustering, classification, and retrieval. Springer, New York"},{"issue":"4","key":"931_CR6","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/2094114.2094129","volume":"40","author":"C Bizer","year":"2011","unstructured":"Bizer C, Boncz PA, Brodie ML, Erling O (2011) The meaningful use of big data: four perspectives\u2014four challenges. SIGMOD Rec 40(4):56\u201360","journal-title":"SIGMOD Rec"},{"issue":"2","key":"931_CR7","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1145\/253262.253327","volume":"26","author":"S Brin","year":"1997","unstructured":"Brin S, Motwani R, Silverstein C (1997) Beyond market baskets: generalizing association rules to correlations. SIGMOD Rec 26(2):265\u2013276. doi: 10.1145\/253262.253327","journal-title":"SIGMOD Rec"},{"issue":"1","key":"931_CR8","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.compeleceng.2013.11.024","volume":"40","author":"G Chandrashekar","year":"2014","unstructured":"Chandrashekar G, Sahin F (2014) A survey on feature selection methods. Comput Elect Eng 40(1):16\u201328","journal-title":"Comput Elect Eng"},{"key":"931_CR9","doi-asserted-by":"crossref","DOI":"10.1002\/0471200611","volume-title":"Elements of information theory","author":"TM Cover","year":"1991","unstructured":"Cover TM, Thomas JA (1991) Elements of information theory. Wiley-Interscience, New York"},{"issue":"1","key":"931_CR10","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean J, Ghemawat S (2008) Mapreduce: simplified data processing on large clusters. Commun ACM 51(1):107\u2013113","journal-title":"Commun ACM"},{"key":"931_CR11","unstructured":"English Wikipedia Articles (2014) http:\/\/dumps.wikimedia.org\/enwiki\/latest"},{"key":"931_CR12","doi-asserted-by":"crossref","unstructured":"Hastie T (2009) The elements of statistical learning: data mining, inference, and prediction. Springer, New York. ISBN: 978-0387848570","DOI":"10.1007\/978-0-387-84858-7"},{"key":"931_CR13","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-7970-4","volume-title":"Entropy and information theory","author":"R Gray","year":"2011","unstructured":"Gray R (2011) Entropy and information theory. Springer, New York"},{"key":"931_CR14","unstructured":"Grid5000 (n.d.) https:\/\/www.grid5000.fr\/mediawiki\/index.php\/Grid5000:Home"},{"key":"931_CR15","first-page":"1157","volume":"3","author":"I Guyon","year":"2003","unstructured":"Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157\u20131182","journal-title":"J Mach Learn Res"},{"key":"931_CR16","unstructured":"Hadoop (2014) http:\/\/hadoop.apache.org"},{"key":"931_CR17","volume-title":"Data mining: concepts and techniques","author":"J Han","year":"2012","unstructured":"Han J (2012) Data mining: concepts and techniques. Elsevier\/Morgan Kaufmann, Boston"},{"issue":"2","key":"931_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/335191.335372","volume":"29","author":"J Han","year":"2000","unstructured":"Han J, Pei J, Yin Y (2000) Mining frequent patterns without candidate generation. SIGMOD Rec 29(2):1\u201312. doi: 10.1145\/335191.335372","journal-title":"SIGMOD Rec"},{"key":"931_CR19","doi-asserted-by":"crossref","unstructured":"Heikinheimo H, Hinkkanen E, Mannila H, Mielik\u00e4inen T, Sepp\u00e4nen JK (2007) Finding low-entropy sets and trees from binary data. In: Proceedings of ACM SIGKDD international conference on knowledge discovery and data mining (KDD), pp\u00a0350\u2013359","DOI":"10.1145\/1281192.1281232"},{"issue":"3","key":"931_CR20","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s10115-010-0356-2","volume":"29","author":"F Herrera","year":"2011","unstructured":"Herrera F, Carmona C, Gonz\u00e1lez P, del Jesus M (2011) An overview on subgroup discovery: foundations and applications. Knowl Inf Syst 29(3):495\u2013525. doi: 10.1007\/s10115-010-0356-2","journal-title":"Knowl Inf Syst"},{"key":"931_CR21","doi-asserted-by":"crossref","unstructured":"Knobbe AJ, Ho EKY (2006) Maximally informative k-itemsets and their efficient discovery. In: Proceedings of ACM SIGKDD international conference on knowledge discovery and data mining (KDD), pp\u00a0237\u2013244","DOI":"10.1145\/1150402.1150431"},{"key":"931_CR22","unstructured":"Kotsiantis SB (2007) Supervised machine learning: a review of classification techniques. In: Proceedings of international conference on emerging artificial intelligence applications in computer engineering, pp\u00a03\u201324"},{"key":"931_CR23","doi-asserted-by":"crossref","unstructured":"Li H, Wang Y, Zhang D, Zhang M, Chang EY (2008) Pfp: parallel fp-growth for query recommendation. In Proceedings of the ACM conference on recommender systems (RecSys), pp\u00a0107\u2013114","DOI":"10.1145\/1454008.1454027"},{"key":"931_CR24","doi-asserted-by":"crossref","unstructured":"Miliaraki I, Berberich K, Gemulla R, Zoupanos S (2013) Mind the gap: Large-scale frequent sequence mining. In: Proceedings of the 2013 ACM SIGMOD international conference on management of data (SIGMOD), pp\u00a0797\u2013808","DOI":"10.1145\/2463676.2465285"},{"key":"931_CR25","doi-asserted-by":"crossref","unstructured":"Moens S, Aksehirli E, Goethals B ( 2013) Frequent itemset mining for big data. In: IEEE international conference on big data, pp\u00a0111\u2013118","DOI":"10.1109\/BigData.2013.6691742"},{"key":"931_CR26","doi-asserted-by":"crossref","unstructured":"Riondato M, DeBrabant JA, Fonseca R, Upfal E (2012) Parma: a parallel randomized algorithm for approximate association rules mining in mapreduce. In: 21st ACM international conference on information and knowledge management (CIKM), pp\u00a085\u201394","DOI":"10.1145\/2396761.2396776"},{"key":"931_CR27","unstructured":"Savasere A, Omiecinski E, Navathe SB ( 1995) An efficient algorithm for mining association rules in large databases. In: Proceedings of international conference on very large data bases (VLDB), pp\u00a0432\u2013444"},{"key":"931_CR28","doi-asserted-by":"crossref","unstructured":"Tanbeer S, Ahmed C, Jeong B-S ( 2009) Parallel and distributed frequent pattern mining in large databases. In: 11th IEEE international conference on high performance computing and communications (HPCC), pp\u00a0407\u2013414","DOI":"10.1109\/HPCC.2009.37"},{"key":"931_CR29","doi-asserted-by":"publisher","unstructured":"Tatti N (2010) Probably the best itemsets. In: Proceedings of the 16th ACM SIGKDD international conference on knowledge discovery and data mining, Washington, DC, USA, July 25-28, 2010, pp\u00a0293\u2013302. doi: 10.1145\/1835804.1835843","DOI":"10.1145\/1835804.1835843"},{"key":"931_CR30","doi-asserted-by":"crossref","unstructured":"Teng W-G, Chen M-S, Yu PS ( 2003) A regression-based temporal pattern mining scheme for data streams. In: Proceedings of international conference on very large data bases (VLDB), pp\u00a093\u2013104","DOI":"10.1016\/B978-012722442-8\/50017-3"},{"key":"931_CR31","unstructured":"The ClueWeb09 Dataset (2009) http:\/\/www.lemurproject.org\/clueweb09.php\/"},{"key":"931_CR32","volume-title":"Hadoop: the definitive guide","author":"T White","year":"2012","unstructured":"White T (2012) Hadoop: the definitive guide. O\u2019Reilly, California"},{"key":"931_CR33","unstructured":"Zaharia M, Chowdhury M, Franklin MJ, Shenker S, Stoica I (2010) Spark: cluster computing with working sets. In: Proceedings of the 2nd USENIX conference on hot topics in cloud computing, p\u00a010"},{"key":"931_CR34","doi-asserted-by":"crossref","unstructured":"Zhang C, Masseglia F (2010) Discovering highly informative feature sets from data streams. In: Proceedings of the 21st international conference on database and expert systems applications: part I, DEXA\u201910, Springer, Berlin, pp\u00a091\u2013104. http:\/\/dl.acm.org\/citation.cfm?id=1881867.1881877","DOI":"10.1007\/978-3-642-15364-8_7"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-016-0931-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-016-0931-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-016-0931-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-016-0931-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T06:11:20Z","timestamp":1559110280000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-016-0931-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,22]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,1]]}},"alternative-id":["931"],"URL":"https:\/\/doi.org\/10.1007\/s10115-016-0931-2","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,3,22]]}}}