{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:14:01Z","timestamp":1750306441690,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,9,25]],"date-time":"2015-09-25T00:00:00Z","timestamp":1443139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,9,25]]},"DOI":"10.1145\/2818567.2818653","type":"proceedings-article","created":{"date-parts":[[2023,1,14]],"date-time":"2023-01-14T01:46:54Z","timestamp":1673660814000},"page":"256-260","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Effect of Corpus Size Selection on Performance of Map-Reduce Based Distributed K-Means for Big Textual Data Clustering"],"prefix":"10.1145","author":[{"given":"Shwet","family":"Ketu","sequence":"first","affiliation":[{"name":"Indian Institute of Information Technology, Allahabad, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bakshi Rohit","family":"Prasad","sequence":"additional","affiliation":[{"name":"Indian Institute of Information Technology, Allahabad, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sonali","family":"Agarwal","sequence":"additional","affiliation":[{"name":"Indian Institute of Information Technology, Allahabad, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2015,9,25]]},"reference":[{"issue":"3","key":"e_1_3_2_1_1_1","first-page":"267","article-title":"A survey of clustering algorithms for big data: Taxonomy and empirical analysis. Emerging Topics in Computing","volume":"2","author":"Fahad A.","year":"2014","journal-title":"IEEE Transactions on"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1536616.1536632"},{"key":"e_1_3_2_1_3_1","unstructured":"Zikopoulos P. and Eaton C. 2011. Understanding big data: Analytics for enterprise class hadoop and streaming data. McGraw-Hill Osborne Media.   Zikopoulos P. and Eaton C. 2011. Understanding big data: Analytics for enterprise class hadoop and streaming data. McGraw-Hill Osborne Media."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Prasad B. R. and Agarwal S. 2014. Handling Big Data Stream Analytics using SAMOA Framework-A Practical Experience. International Journal of Database Theory & Application 7(4).  Prasad B. R. and Agarwal S. 2014. Handling Big Data Stream Analytics using SAMOA Framework-A Practical Experience. International Journal of Database Theory & Application 7(4).","DOI":"10.14257\/ijdta.2014.7.4.15"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/HICSS.2013.645"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRTIT.2013.6844173"},{"issue":"08","key":"e_1_3_2_1_7_1","article-title":"Emblematic Fuzzy C-means Clustering for Demographic Dataset","volume":"5","author":"Arya R.","year":"2014","journal-title":"International Journal of Computer Science & Engineering Technology (IJCSET)"},{"key":"e_1_3_2_1_8_1","unstructured":"Mayer-Sch\u00f6nberger V. & Cukier K. 2013. Big data: A revolution that will transform how we live work and think. Houghton Mifflin Harcourt.  Mayer-Sch\u00f6nberger V. & Cukier K. 2013. Big data: A revolution that will transform how we live work and think. Houghton Mifflin Harcourt."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Aggarwal C. C. & Reddy C. K. (Eds.). 2013. Data clustering: algorithms and applications. CRC Press.   Aggarwal C. C. & Reddy C. K. (Eds.). 2013. Data clustering: algorithms and applications. CRC Press.","DOI":"10.1201\/b15410"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Chen H. Chiang R. H. & Storey V. C. 2012. Business Intelligence and Analytics: From Big Data to Big Impact. MIS quarterly 36(4) 1165--1188.   Chen H. Chiang R. H. & Storey V. C. 2012. Business Intelligence and Analytics: From Big Data to Big Impact. MIS quarterly 36(4) 1165--1188.","DOI":"10.2307\/41703503"},{"key":"e_1_3_2_1_11_1","unstructured":"Hadoop: Open source implementation of MapReduce http:\/\/lucene.apache.org\/Hadoop  Hadoop: Open source implementation of MapReduce http:\/\/lucene.apache.org\/Hadoop"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2007.346181"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/1324616.1324684"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10665-1_71"},{"volume-title":"Communication Software and Networks (ICCSN), 2011 IEEE 3rd International Conference on (pp. 44--46)","year":"2011","author":"Wang J.","key":"e_1_3_2_1_15_1"},{"volume-title":"International Journal of Engineering Research and Technology (Vol. 2, No. 2 (February-2013))","author":"Sujatha M. S.","key":"e_1_3_2_1_16_1"},{"key":"e_1_3_2_1_17_1","unstructured":"Yadav Krishna R. & Singh P. 2014. MapReduce programming paradigm solving big-data problems by using data-clustering algorithm. International Journal of Advanced Research in Computer Engineering & Technology (IJARCET) 3(1).  Yadav Krishna R. & Singh P. 2014. MapReduce programming paradigm solving big-data problems by using data-clustering algorithm. International Journal of Advanced Research in Computer Engineering & Technology (IJARCET) 3(1)."},{"volume-title":"2014 International Conference on (pp. 136--140)","year":"2014","author":"Chadha A.","key":"e_1_3_2_1_18_1"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.14257\/ijast.2014.62.04"},{"volume-title":"Computer Science & Education (ICCSE), 2014 9th International Conference on (pp. 263--266)","year":"2014","author":"Lin K.","key":"e_1_3_2_1_20_1"},{"key":"e_1_3_2_1_21_1","unstructured":"Dataset : http:\/\/wiki.dbpedia.org\/Datasets  Dataset : http:\/\/wiki.dbpedia.org\/Datasets"},{"key":"e_1_3_2_1_22_1","unstructured":"Dataset : https:\/\/www.cs.cmu.edu\/~.\/enron\/  Dataset : https:\/\/www.cs.cmu.edu\/~.\/enron\/"},{"key":"e_1_3_2_1_23_1","unstructured":"Dataset : http:\/\/wiki.dbpedia.org\/Downloads2014  Dataset : http:\/\/wiki.dbpedia.org\/Downloads2014"}],"event":{"name":"ICCCT '15: Sixth International Conference on Computer and Communication Technology 2015","acronym":"ICCCT '15","location":"Allahabad India"},"container-title":["Proceedings of the Sixth International Conference on Computer and Communication Technology 2015"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2818567.2818653","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2818567.2818653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:42:48Z","timestamp":1750225368000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2818567.2818653"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9,25]]},"references-count":23,"alternative-id":["10.1145\/2818567.2818653","10.1145\/2818567"],"URL":"https:\/\/doi.org\/10.1145\/2818567.2818653","relation":{},"subject":[],"published":{"date-parts":[[2015,9,25]]},"assertion":[{"value":"2015-09-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}