{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T23:49:56Z","timestamp":1790552996239,"version":"4.1.0"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319493398","type":"print"},{"value":"9783319493404","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-49340-4_2","type":"book-chapter","created":{"date-parts":[[2017,2,25]],"date-time":"2017-02-25T08:23:30Z","timestamp":1488011010000},"page":"31-63","source":"Crossref","is-referenced-by-count":11,"title":["Big Data Programming Models"],"prefix":"10.1007","author":[{"given":"Dongyao","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sherif","family":"Sakr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liming","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,2,26]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"A. Alexandrov, R. Bergmann, S. Ewen, J.-C. Freytag, F. Hueske, A. Heise, O. Kao, M. Leich, U. Leser, V. Markl, F. Naumann, M. Peters, A. Rheinl\u00e4nder, M.J. Sax, S. Schelter, M. H\u00f6ger, K. Tzoumas, D. Warneke, The stratosphere platform for big data analytics, VLDB J. 23(6) (2014)","DOI":"10.1007\/s00778-014-0357-y"},{"key":"2_CR2","unstructured":"Apache. Apache crunch (2016). https:\/\/crunch.apache.org\/ . Accessed 17 Mar 2016"},{"key":"2_CR3","unstructured":"Apache. Apache drill (2016). https:\/\/drill.apache.org\/ . Accessed 17 Mar 2016"},{"key":"2_CR4","unstructured":"Apache. Apache giraph (2016). https:\/\/giraph.apache.org\/ . Accessed 17 Mar 2016"},{"key":"2_CR5","unstructured":"Apache. Apache hama (2016). https:\/\/hama.apache.org\/ . Accessed 17 Mar 2016"},{"key":"2_CR6","unstructured":"Apache. Apache orc (2016). https:\/\/orc.apache.org\/ . Accessed 17 Mar 2016"},{"key":"2_CR7","unstructured":"Apache. Avro (2016). https:\/\/avro.apache.org\/ . Accessed 17 Mar 2016"},{"key":"2_CR8","unstructured":"Apache. Hadoop (2016). http:\/\/hadoop.apache.org\/ . Accessed 17 Mar 2016"},{"key":"2_CR9","unstructured":"Apache. Mahout: Scalable machine learning and data mining (2016). https:\/\/mahout.apache.org\/ . Accessed 17 Mar 2016"},{"key":"2_CR10","unstructured":"Apache. Parquet (2016). https:\/\/parquet.apache.org\/ . Accessed 17 Mar 2016"},{"key":"2_CR11","unstructured":"Apache. Spark r (2016). https:\/\/spark.apache.org\/docs\/1.6.0\/sparkr.html . Accessed 17 Mar 2016"},{"key":"2_CR12","unstructured":"Apache Storm. Trident (2016). http:\/\/storm.apache.org\/documentation\/Trident-tutorial.html . Accessed 17 Mar 2016"},{"key":"2_CR13","unstructured":"M. Armbrust, R.S. Xin, C. Lian, Y. Huai, D. Liu, J.K. Bradley, X. Meng, T. Kaftan, M.J. Franklin, A. Ghodsi, M. Zaharia, Spark SQL: relational data processing in spark, in SIGMOD (2015), pp. 1383\u20131394"},{"key":"2_CR14","unstructured":"AsterixDB. Asterix query language (aql) (2016). https:\/\/asterixdb.ics.uci.edu\/documentation\/aql\/manual.html . Accessed 17 Mar 2016"},{"key":"2_CR15","unstructured":"Azure Microsoft. Microsoft azure: Cloud computing platform and services (2016). https:\/\/azure.microsoft.com . Accessed 27 Feb 2016"},{"issue":"3","key":"2_CR16","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1007\/s10586-015-0472-6","volume":"18","author":"O Batarfi","year":"2015","unstructured":"O. Batarfi, R. El Shawi, A.G. Fayoumi, R. Nouri, S.-M.-R. Beheshti, A. Barnawi, S. Sakr, Large scale graph processing systems: survey and an experimental evaluation. Clust. Comput. 18(3), 1189\u20131213 (2015)","journal-title":"Clust. Comput."},{"key":"2_CR17","volume-title":"S: An Interactive Environment for Data Analysis and Graphics","author":"RA Becker","year":"1984","unstructured":"R.A. Becker, J.M. Chambers, S: An Interactive Environment for Data Analysis and Graphics (CRC Press, New York, 1984)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"K.S. Beyer, V. Ercegovac, R. Gemulla, A. Balmin, M. Eltabakh, C.-C. Kanne, F. Ozcan, E.J. Shekita, Jaql: a scripting language for large scale semistructured data analysis, in Proceedings of VLDB Conference (2011)","DOI":"10.14778\/3402755.3402761"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"C. Chambers, A. Raniwala, F. Perry, S. Adams, R.R. Henry, R. Bradshaw, N. Weizenbaum, FlumeJava: easy, efficient data-parallel pipelines, in PLDI (2010)","DOI":"10.1145\/1806596.1806638"},{"key":"2_CR20","unstructured":"W. Clinger, J. Rees, Ieee standard for the scheme programming language, in Institute for Electrical and Electronic Engineers (1991), pp. 1178\u20131990"},{"key":"2_CR21","unstructured":"Cloudera. Apache impala (2016). http:\/\/impala.io\/ . Accessed 17 Mar 2016"},{"key":"2_CR22","volume-title":"Introduction to Algorithms","author":"TH Cormen","year":"2009","unstructured":"T.H. Cormen, Introduction to Algorithms (MIT press, New York, 2009)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"S. Das, Y. Sismanis, K.S. Beyer, R. Gemulla, P.J. Haas, J. McPherson, Ricardo: integrating r and hadoop, in Proceedings of the 2010 ACM SIGMOD International Conference on Management of data (ACM, 2010), pp. 987\u2013998","DOI":"10.1145\/1807167.1807275"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"J. Dean, S. Ghemawat, MapReduce: simplified data processing on large clusters. Commun. ACM 51(1) (2008)","DOI":"10.1145\/1327452.1327492"},{"key":"2_CR25","unstructured":"Facebook. Presto (2016), https:\/\/prestodb.io\/ . Accessed 17 Mar 2016"},{"key":"2_CR26","unstructured":"L. George, HBase: The Definitive Guide (O\u2019Reilly Media, Inc., 2011)"},{"key":"2_CR27","unstructured":"Google. Cloud sql - mysql relational database (2016). https:\/\/cloud.google.com\/sql\/ . Accessed 27 Feb 2016"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"S. Guha, R. Hafen, J. Rounds, J. Xia, J. Li, B. Xi, W.S. Cleveland, Large complex data: divide and recombine (d&r) with rhipe. Stat 1(1), 53\u201367 (2012)","DOI":"10.1002\/sta4.7"},{"key":"2_CR29","unstructured":"C. Hewitt, P. Bishop, R. Steiger, A universal modular actor formalism for artificial intelligence, in Proceedings of the 3rd International Joint Conference on Artificial Intelligence (Morgan Kaufmann Publishers Inc., 1973), pp. 235\u2013245"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"S. Hong, H. Chafi, E. Sedlar, K. Olukotun, Green-marl: a dsl for easy and efficient graph analysis, in ACM SIGARCH Computer Architecture News, vol. 40 (ACM, 2012), pp. 349\u2013362","DOI":"10.1145\/2150976.2151013"},{"key":"2_CR31","unstructured":"Inc Concurrent. Cascading - application platform for enterprise big data (2016). http:\/\/www.cascading.org\/ . Accessed 17 Mar 2016"},{"issue":"3","key":"2_CR32","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1080\/10618600.1996.10474713","volume":"5","author":"R Ihaka","year":"1996","unstructured":"R. Ihaka, R. Gentleman, R: a language for data analysis and graphics. J. Comput. Graph. Stat. 5(3), 299\u2013314 (1996)","journal-title":"J. Comput. Graph. Stat."},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"M. Isard, M. Budiu, Y. Yu, A. Birrell, D. Fetterly, Dryad: distributed data-parallel programs from sequential building blocks, in ACM SIGOPS Operating Systems Review, vol. 41 (ACM, 2007), pp. 59\u201372","DOI":"10.1145\/1272996.1273005"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"M. Islam, A.K. Huang, M. Battisha, M. Chiang, S. Srinivasan, C. Peters, A. Neumann, A. Abdelnur, Oozie: towards a scalable workflow management system for hadoop, in SIGMOD Workshops (2012)","DOI":"10.1145\/2443416.2443420"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"W.M. Johnston, J.R.\u00a0Hanna, R.J. Millar, Advances in dataflow programming languages. ACM Comput. Surv. (CSUR) 36(1), 1\u201334 (2004)","DOI":"10.1145\/1013208.1013209"},{"issue":"2","key":"2_CR36","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1145\/1773912.1773922","volume":"44","author":"A Lakshman","year":"2010","unstructured":"A. Lakshman, P. Malik, Cassandra: a decentralized structured storage system. ACM SIGOPS Oper. Syst. Rev. 44(2), 35\u201340 (2010)","journal-title":"ACM SIGOPS Oper. Syst. Rev."},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"G. Malewicz, M.H. Austern, A.J.C. Bik, J.C. Dehnert, I. Horn, N. Leiser, G. Czajkowski, Pregel: a system for large-scale graph processing, in SIGMOD Conference (2010)","DOI":"10.1145\/1807167.1807184"},{"key":"2_CR38","unstructured":"X. Meng, J. Bradley, B. Yavuz, E. Sparks, S. Venkataraman, D. Liu, J. Freeman, D.B.\u00a0Tsai, M. Amde, S. Owen, et\u00a0al., Mllib: machine learning in apache spark (2015). arXiv preprint, arXiv:1505.06807"},{"key":"2_CR39","unstructured":"MongoDB Inc. Mongodb for giant ideas (2016). https:\/\/www.mongodb.org\/ . Accessed 27 Feb 2016"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"C. Olston, B. Reed, U. Srivastava, R. Kumar, A. Tomkins, Pig latin: a not-so-foreign language for data processing, in SIGMOD (2008)","DOI":"10.1145\/1376616.1376726"},{"key":"2_CR41","unstructured":"Swift OpenStack. Openstack swift - enterprise storage from swiftstack (2016). https:\/\/www.swiftstack.com\/openstack-swift\/ . Accessed 27 Feb 2016"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"S. Sakr, Big Data 2.0 Processing Systems (Springer, Berlin, 2016)","DOI":"10.1007\/978-3-319-38776-5"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"S. Sakr, M.M. Gaber (eds.) Large Scale and Big Data - Processing and Management (Auerbach Publications, 2014)","DOI":"10.1201\/b17112"},{"issue":"1","key":"2_CR44","first-page":"11","volume":"46","author":"Sherif Sakr","year":"2013","unstructured":"Sherif Sakr, Anna Liu, Ayman G. Fayoumi, The family of mapreduce and large-scale data processing systems. ACM Comput. Surv. 46(1), 11 (2013)","journal-title":"ACM Comput. Surv."},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"K. Shvachko, H. Kuang, S. Radia, R. Chansler, The hadoop distributed file system, in IEEE MSST (2010)","DOI":"10.1109\/MSST.2010.5496972"},{"key":"2_CR46","unstructured":"S3\u00a0Amazon. Amazon simple storage service (amazon s3) (2016). https:\/\/aws.amazon.com\/s3\/ . Accessed 27 Feb 2016"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"A. Thusoo, J.S. Sarma, N. Jain, Z. Shao, P. Chakka, S. Anthony, H. Liu, P. Wyckoff, R. Murthy, Hive: a warehousing solution over a map-reduce framework. Proc. VLDB Endow. 2(2), 1626\u20131629 (2009)","DOI":"10.14778\/1687553.1687609"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"A. Toshniwal, S. Taneja, A. Shukla, K. Ramasamy, J.M. Patel, S. Kulkarni, J. Jackson, K. Gade, M. Fu, J. Donham, et\u00a0al., Storm@ twitter, in Proceedings of the 2014 ACM SIGMOD international conference on Management of data (ACM, 2014), pp. 147\u2013156","DOI":"10.1145\/2588555.2595641"},{"key":"2_CR49","unstructured":"Typesafe. Akka (2016). http:\/\/akka.io\/ . Accessed 17 Mar 2016"},{"key":"2_CR50","unstructured":"Typesafe. Play framework - build modern & scalable web apps with java and scala (2016). https:\/\/www.playframework.com\/ . Accessed 17 Mar 2016"},{"issue":"8","key":"2_CR51","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1145\/79173.79181","volume":"33","author":"LG Valiant","year":"1990","unstructured":"L.G. Valiant, A bridging model for parallel computation. Commun. ACM 33(8), 103\u2013111 (1990)","journal-title":"Commun. ACM"},{"key":"2_CR52","unstructured":"Y. Yu, M. Isard, D. Fetterly, M. Budiu, \u00da. Erlingsson, P.K. Gunda, J. Currey, Dryadlinq: a system for general-purpose distributed data-parallel computing using a high-level language, in OSDI, vol.\u00a08 (2008), pp. 1\u201314"},{"key":"2_CR53","unstructured":"M. Zaharia, M. Chowdhury, M.J. Franklin, S. Shenker, I. Stoica, Spark: cluster computing with working sets, in HotCloud (2010)"},{"key":"2_CR54","unstructured":"M. Zaharia, M. Chowdhury, T. Das, A. Dave, J. Ma, M. McCauly, M.J. Franklin, S. Shenker, I. Stoica, Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing, in NSDI (2012)"}],"container-title":["Handbook of Big Data Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-49340-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,22]],"date-time":"2024-06-22T18:05:06Z","timestamp":1719079506000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-49340-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319493398","9783319493404"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-49340-4_2","relation":{},"subject":[],"published":{"date-parts":[[2017]]}}}