{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:12:04Z","timestamp":1761581524055,"version":"3.41.0"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/bigdata.2016.7841068","type":"proceedings-article","created":{"date-parts":[[2017,2,7]],"date-time":"2017-02-07T21:46:59Z","timestamp":1486504019000},"page":"3928-3935","source":"Crossref","is-referenced-by-count":11,"title":["Large-scale text processing pipeline with Apache Spark"],"prefix":"10.1109","author":[{"given":"A.","family":"Svyatkovskiy","sequence":"first","affiliation":[]},{"given":"K.","family":"Imai","sequence":"additional","affiliation":[]},{"given":"M.","family":"Kroeger","sequence":"additional","affiliation":[]},{"given":"Y.","family":"Shiraito","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/poq\/nft027"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6210.2012.02610.x"},{"key":"ref12","first-page":"10","article-title":"Spark: Cluster computing with working sets","author":"zaharia","year":"0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139058452"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742797"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2960414.2960416"},{"article-title":"histogrammar-scala: 1.0.0","year":"2016","author":"pivarski","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-010-9144-6"},{"article-title":"Dimension independent matrix square using mapreduce","year":"2013","author":"zadeh","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2307\/1956539"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2307\/1954434"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/1532673X01293001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2307\/1963526"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/1532440014561868"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-5907.2006.00185.x"},{"year":"0","key":"ref2","article-title":"LexisNexis StateNet"},{"key":"ref1","first-page":"1532440015608761","article-title":"Four ways we can improve policy diffusion research","author":"gilardi","year":"2015","journal-title":"Statistics Politics and Policy"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1353\/book52432","author":"mossberger","year":"2000","journal-title":"The Politics of Ideas and the Spread of Enterprise Zones"}],"event":{"name":"2016 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2016,12,5]]},"location":"Washington DC,USA","end":{"date-parts":[[2016,12,8]]}},"container-title":["2016 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7818133\/7840573\/07841068.pdf?arnumber=7841068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T03:02:59Z","timestamp":1749956579000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7841068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/bigdata.2016.7841068","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}