{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:39:14Z","timestamp":1757313554104,"version":"3.37.3"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2018,9,1]],"date-time":"2018-09-01T00:00:00Z","timestamp":1535760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100006280","name":"Ministerio de Ciencia y Tecnolog\u00eda","doi-asserted-by":"publisher","award":["TIN2013-46928-C3-1-R"],"award-info":[{"award-number":["TIN2013-46928-C3-1-R"]}],"id":[{"id":"10.13039\/501100006280","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Spanish Ministry of Economy and Competitiveness","award":["TIN2016-76956-C3-1-R"],"award-info":[{"award-number":["TIN2016-76956-C3-1-R"]}]},{"name":"POLOLAS","award":["TIN2016-76956-C3-2-R"],"award-info":[{"award-number":["TIN2016-76956-C3-2-R"]}]},{"name":"Principality of Asturias","award":["GRUPIN14-007"],"award-info":[{"award-number":["GRUPIN14-007"]}]},{"name":"Severo Ochoa Predoctoral","award":["BP16215"],"award-info":[{"award-number":["BP16215"]}]},{"name":"Italian MIUR"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Rel."],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/tr.2018.2802047","type":"journal-article","created":{"date-parts":[[2018,3,19]],"date-time":"2018-03-19T22:06:26Z","timestamp":1521497186000},"page":"717-732","source":"Crossref","is-referenced-by-count":14,"title":["Automatic Testing of Design Faults in MapReduce Applications"],"prefix":"10.1109","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7544-3901","authenticated-orcid":false,"given":"Jesus","family":"Moran","sequence":"first","affiliation":[]},{"given":"Antonia","family":"Bertolino","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5592-9683","authenticated-orcid":false,"given":"Claudio","family":"de la Riva","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1091-934X","authenticated-orcid":false,"given":"Javier","family":"Tuya","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"year":"2013","journal-title":"29119-1 2013 - ISO\/IEC\/IEEE International Standard for Software and Systems Engineering—Software Testing—Part 1 Concepts and Definitions","first-page":"1","key":"ref73"},{"doi-asserted-by":"publisher","key":"ref72","DOI":"10.1109\/TSE.2014.2372785"},{"key":"ref71","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/B978-0-12-800160-8.00003-6","article-title":"Automated\n test oracles: State of the art, taxonomies, and trends","volume":"95","author":"oliveira","year":"2015","journal-title":"Adv Comput"},{"doi-asserted-by":"publisher","key":"ref70","DOI":"10.1145\/1985793.1985847"},{"key":"ref76","doi-asserted-by":"crossref","first-page":"1278","DOI":"10.1109\/TSE.1987.232881","article-title":"Comparing the effectiveness of software testing strategies","volume":"se 13","author":"selby","year":"1987","journal-title":"IEEE Trans Softw Eng"},{"key":"ref77","first-page":"1","article-title":"Spectrum-based\n software fault localization: A survey of techniques, advances, and challenges","author":"de souza","year":"2016","journal-title":"arxiv1607 04347"},{"doi-asserted-by":"publisher","key":"ref74","DOI":"10.1016\/j.jss.2010.11.920"},{"key":"ref39","first-page":"165","article-title":"Overview on performance testing approach in big data","volume":"5","author":"nagdive","year":"2014","journal-title":"International Journal of Advanced Research in Computer Science"},{"doi-asserted-by":"publisher","key":"ref75","DOI":"10.1109\/TSE.2016.2532875"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/ICInfA.2014.6932625"},{"key":"ref78","first-page":"249","article-title":"Supervised machine learning: A review of classification techniques","volume":"31","author":"kotsiantis","year":"2007","journal-title":"Informatica"},{"doi-asserted-by":"publisher","key":"ref79","DOI":"10.1109\/32.6156"},{"year":"0","article-title":"Open Ankus: Data mining and machine learning based on MapReduce","key":"ref33"},{"key":"ref32","first-page":"1","volume":"7","author":"lin","year":"2010","journal-title":"Data-intensive Text Processing with MapReduce"},{"year":"0","article-title":"Average temperature per year","key":"ref31"},{"year":"0","article-title":"Average temperature per year","key":"ref30"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.5120\/13892-1835"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/ICCCNT.2013.6726822"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/FOSE.2007.25"},{"key":"ref34","first-page":"117","article-title":"Software testing: A research travelogue (2000–2014)","author":"orso","year":"0","journal-title":"Proc Future Softw Eng"},{"doi-asserted-by":"publisher","key":"ref60","DOI":"10.1109\/32.62448"},{"doi-asserted-by":"publisher","key":"ref62","DOI":"10.1109\/TSE.2011.121"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.1109\/TSE.1984.5010257"},{"doi-asserted-by":"publisher","key":"ref63","DOI":"10.1109\/32.815325"},{"year":"0","article-title":"Apache MRUnit: Java library that helps developers unit test Apache Hadoop map reduce job","key":"ref28"},{"year":"2015","journal-title":"ISO\/IEC\/IEEE International Standard for Software and Systems Engineering—Software Testing—Part 4 Test Techniques","first-page":"1","key":"ref64"},{"key":"ref27","first-page":"1","article-title":"Metamorphic\n testing: A new approach for generating next test cases","author":"chen","year":"1998"},{"doi-asserted-by":"publisher","key":"ref65","DOI":"10.1109\/AICCSA.2001.934001"},{"doi-asserted-by":"publisher","key":"ref66","DOI":"10.1109\/CMPASS.1994.318466"},{"key":"ref29","first-page":"4","article-title":"Parallel programming must be\n deterministic by default","volume":"22","author":"bocchino","year":"0","journal-title":"Proc 1st USENIX Conf Hot Topics Parallelism"},{"doi-asserted-by":"publisher","key":"ref67","DOI":"10.1109\/SEW.2002.1199454"},{"key":"ref68","first-page":"16","article-title":"Reducing time to market with combinatorial design method testing","author":"huller","year":"0","journal-title":"Proc Int Council Syst Eng Conf"},{"doi-asserted-by":"publisher","key":"ref69","DOI":"10.1093\/comjnl\/25.4.465"},{"year":"2015","journal-title":"Xerox","article-title":"Big data in Western Europe today","key":"ref2"},{"year":"2014","journal-title":"Preliminary report","article-title":"ISO\/IEC JTC 1-Big Data","key":"ref1"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CCGRID.2010.112"},{"key":"ref22","first-page":"44","article-title":"Nondeterminism in mapreduce considered\n harmful? An empirical study on non-commutative aggregators in MapReduce programs","author":"xiao","year":"0","journal-title":"Proc Companion Proc 36th Int Conf Softw Eng ICSE Companion 2014"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.14778\/2536206.2536213"},{"key":"ref24","article-title":"Classificação de defeitos para programas MapReduce: Resultados de\n um estudo Empírico","author":"camargo","year":"0","journal-title":"Proc 7th Brazilian Workshop on Systematic and Automated Software Testing"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/FiCloud.2014.67"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.25046\/aj020111"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/W-FiCloud.2016.45"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1145\/2804322.2804326"},{"year":"2011","author":"de mattos","article-title":"Test data generation for testing MapReduce systems","key":"ref51"},{"year":"2010","author":"murphy","article-title":"Empirical evaluation of approaches to testing applications without test oracles","key":"ref94"},{"doi-asserted-by":"publisher","key":"ref93","DOI":"10.1109\/QSIC.2007.4385527"},{"key":"ref92","first-page":"654","article-title":"Are mutants a valid substitute for real faults in software testing?","author":"just","year":"0","journal-title":"Proc 2nd ACM SIGSOFT Symp on Foundations of Software Engineering"},{"key":"ref91","first-page":"402","article-title":"Is\n mutation an appropriate tool for testing experiments?","author":"andrews","year":"0","journal-title":"Proc 27th Int l Conf Software Eng"},{"key":"ref90","first-page":"354","article-title":"Threats to the validity of mutation-based\n test assessment","author":"papadakis","year":"0","journal-title":"Proc 25th Int Symp Softw Test Anal"},{"doi-asserted-by":"publisher","key":"ref59","DOI":"10.1145\/1883612.1883618"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1002\/stvr.319"},{"year":"1979","author":"glenford","journal-title":"The Art of Software Testing","key":"ref57"},{"key":"ref56","article-title":"Random testing","author":"hamlet","year":"1994","journal-title":"Encyclopedia of Software Engineering"},{"year":"0","article-title":"JUnit: A simple framework to write repeatable tests","key":"ref55"},{"year":"0","article-title":"Minicluster: Apache hadoop cluster in memory for testing","key":"ref54"},{"year":"0","article-title":"Herriot: Large-scale automated test framework","key":"ref53"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1145\/2970276.2970325"},{"year":"0","article-title":"Institutions that are using Apache Hadoop for educational or production uses","key":"ref10"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.14569\/IJACSA.2015.060828"},{"key":"ref40","first-page":"65","article-title":"Big data: Testing approach to overcome quality challenges","volume":"11","author":"gudipati","year":"2013"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.5121\/ijcsit.2015.7410"},{"year":"0","article-title":"Apache Hadoop: Open-source software for reliable, scalable, distributed computing","key":"ref13"},{"year":"0","article-title":"Apache Flink: Scalable batch and stream data processing","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1007\/s00778-014-0357-y"},{"year":"0","key":"ref82"},{"year":"0","article-title":"Apache Spark: A fast and general engine for large-scale data processing","key":"ref16"},{"year":"0","article-title":"Movies analysis implemented in MapReduce","key":"ref81"},{"key":"ref17","first-page":"10","article-title":"Spark: Cluster computing with working sets","author":"zaharia","year":"0","journal-title":"Proc 2nd USENIX Conf Hot Topics Cloud Comput"},{"year":"0","article-title":"MapReduce algorithm of connected components in graphs","key":"ref84"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1093\/bioinformatics\/btp236"},{"key":"ref83","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-29044-2","author":"wohlin","year":"2012","journal-title":"Experimentation in Software Engineering"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/HPCSim.2011.5999917"},{"doi-asserted-by":"publisher","key":"ref80","DOI":"10.1007\/978-3-319-25747-1_17"},{"doi-asserted-by":"publisher","key":"ref89","DOI":"10.1145\/2001420.2001461"},{"year":"2015","author":"marr","article-title":"Where big data projects fail","key":"ref4"},{"year":"2014","journal-title":"Capgemini Consulting","article-title":"Big data survey","key":"ref3"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1038\/498255a","article-title":"Biology: The big challenges of big data","volume":"498","author":"marx","year":"2013","journal-title":"Nature"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/PRDC.2015.41"},{"year":"0","article-title":"Goldstein analysis implemented in MapReduce","key":"ref85"},{"year":"2015","journal-title":"Gartner","article-title":"How to take a first step to advanced analytics","key":"ref8"},{"year":"0","article-title":"Analysis of the New York restaurants based on MapReduce","key":"ref86"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/EmergiTech.2016.7737349"},{"doi-asserted-by":"publisher","key":"ref49","DOI":"10.1016\/j.comnet.2015.04.009"},{"year":"1979","author":"cook","journal-title":"Quasi-Experimentation Design and analysis issues for field settings","key":"ref87"},{"key":"ref88","doi-asserted-by":"crossref","DOI":"10.1201\/b19292","author":"malhotra","year":"2016","journal-title":"Empirical Research in Software Engineering Concepts Analysis and Applications"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1145\/1327452.1327492"},{"year":"0","article-title":"Anarchy Ape: Fault injection tool for Hadoop cluster from Yahoo anarchyape","key":"ref46"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1145\/2076021.2048082"},{"year":"0","article-title":"Hadoop injection framework","key":"ref48"},{"year":"0","article-title":"Chaosmonkey: Fault injector","key":"ref47"},{"key":"ref42","first-page":"131","article-title":"Commutativity of reducers","author":"chen","year":"0","journal-title":"Proc Int Conf Tools Algorithms Construction Anal Syst"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1145\/2025113.2025204"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1145\/2405186.2405191"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1145\/1807128.1807161"}],"container-title":["IEEE Transactions on Reliability"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/24\/8452065\/08318901.pdf?arnumber=8318901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T13:19:50Z","timestamp":1643203190000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8318901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":94,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tr.2018.2802047","relation":{},"ISSN":["0018-9529","1558-1721"],"issn-type":[{"type":"print","value":"0018-9529"},{"type":"electronic","value":"1558-1721"}],"subject":[],"published":{"date-parts":[[2018,9]]}}}