{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:22:48Z","timestamp":1755998568712,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,7,25]],"date-time":"2020-07-25T00:00:00Z","timestamp":1595635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Australian Research Council (ARC), Discovery Project (DP)","award":["DP190102141"],"award-info":[{"award-number":["DP190102141"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,7,25]]},"DOI":"10.1145\/3397271.3401059","type":"proceedings-article","created":{"date-parts":[[2020,7,25]],"date-time":"2020-07-25T07:50:08Z","timestamp":1595663408000},"page":"269-278","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["On Understanding Data Worker Interaction Behaviors"],"prefix":"10.1145","author":[{"given":"Lei","family":"Han","sequence":"first","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwa","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gianluca","family":"Demartini","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marta","family":"Indulska","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shazia","family":"Sadiq","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,7,25]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2015.17"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772697"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077257.3077272"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1736359"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295750.3298926"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1518705"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.14778\/3115404.3115414"},{"volume-title":"Exploratory data mining and data cleaning","author":"Dasu Tamraparni","key":"e_1_3_2_2_8_1","unstructured":"Tamraparni Dasu and Theodore Johnson . 2003. Exploratory data mining and data cleaning . Vol. 479 . John Wiley & Sons . Tamraparni Dasu and Theodore Johnson. 2003. Exploratory data mining and data cleaning. Vol. 479. John Wiley & Sons."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025916"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2011.10.009"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047205"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979125"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979444"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.23187"},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings. 2004 International Symposium on Empirical Software Engineering, 2004. ISESE'04. IEEE, 83--92","author":"Kim Miryung","year":"2004","unstructured":"Miryung Kim , Lawrence Bergman , Tessa Lau , and David Notkin . 2004 . An ethnographic study of copy and paste programming practices in OOPL . In Proceedings. 2004 International Symposium on Empirical Software Engineering, 2004. ISESE'04. IEEE, 83--92 . Miryung Kim, Lawrence Bergman, Tessa Lau, and David Notkin. 2004. An ethnographic study of copy and paste programming practices in OOPL. In Proceedings. 2004 International Symposium on Empirical Software Engineering, 2004. ISESE'04. IEEE, 83--92."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2006.116"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2835776.2835833"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210170"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2786805.2786871"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295750.3298922"},{"key":"e_1_3_2_2_21_1","volume-title":"On a test of whether one of two random variables is stochastically larger than the other. The annals of mathematical statistics","author":"Mann Henry B","year":"1947","unstructured":"Henry B Mann and Donald R Whitney . 1947. On a test of whether one of two random variables is stochastically larger than the other. The annals of mathematical statistics ( 1947 ), 50--60. Henry B Mann and Donald R Whitney. 1947. On a test of whether one of two random variables is stochastically larger than the other. The annals of mathematical statistics (1947), 50--60."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133001"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC.2015.12"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300356"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2015.39"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2466418"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1988842.1988847"},{"key":"e_1_3_2_2_28_1","volume-title":"Proceedings of the first instructional conference on machine learning","volume":"242","author":"Juan","unstructured":"Juan Ramos et almbox. 2003. Using tf-idf to determine word relevance in document queries . In Proceedings of the first instructional conference on machine learning , Vol. 242 . 133--142. Juan Ramos et almbox. 2003. Using tf-idf to determine word relevance in document queries. In Proceedings of the first instructional conference on machine learning, Vol. 242. 133--142."},{"key":"e_1_3_2_2_29_1","first-page":"46","article-title":"Pattern-matching-the gestalt approach","volume":"13","author":"Ratcliff John W","year":"1988","unstructured":"John W Ratcliff and David E Metzener . 1988 . Pattern-matching-the gestalt approach . Dr Dobbs Journal , Vol. 13 , 7 (1988), 46 . John W Ratcliff and David E Metzener. 1988. Pattern-matching-the gestalt approach. Dr Dobbs Journal, Vol. 13, 7 (1988), 46.","journal-title":"Dr Dobbs Journal"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3186549.3186559"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2786805.2786855"},{"key":"e_1_3_2_2_32_1","volume-title":"Perry","author":"Saha Ripon K.","year":"2013","unstructured":"Ripon K. Saha , Chanchal K. Roy , Kevin A. Schneider , and Dewayne E . Perry . 2013 . Understanding the Evolution of Type-3 Clones : An Exploratory Study. In Proceedings of the 10th Working Conference on MSR. IEEE Press , 139--148. Ripon K. Saha, Chanchal K. Roy, Kevin A. Schneider, and Dewayne E. Perry. 2013. Understanding the Evolution of Type-3 Clones: An Exploratory Study. In Proceedings of the 10th Working Conference on MSR. IEEE Press, 139--148."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220057"},{"key":"e_1_3_2_2_34_1","volume-title":"Challenges and Visions","volume":"7","author":"Tay Y","year":"2011","unstructured":"Y Tay . 2011 . Data generation for application-specific benchmarking. VLDB , Challenges and Visions , Vol. 7 (2011). Y Tay. 2011. Data generation for application-specific benchmarking. VLDB, Challenges and Visions, Vol. 7 (2011)."},{"volume-title":"Creating a Data-Driven Enterprise with DataOps","author":"Thusoo Ashish","key":"e_1_3_2_2_35_1","unstructured":"Ashish Thusoo and Joydeep Sarma . 2017. Creating a Data-Driven Enterprise with DataOps . O'Reilly Media, Inc orporated. Ashish Thusoo and Joydeep Sarma. 2017. Creating a Data-Driven Enterprise with DataOps. O'Reilly Media, Incorporated."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00196"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-018-9634-5"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209990"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702593"}],"event":{"name":"SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Virtual Event China","acronym":"SIGIR '20"},"container-title":["Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397271.3401059","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3397271.3401059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:31:38Z","timestamp":1750195898000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397271.3401059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,25]]},"references-count":39,"alternative-id":["10.1145\/3397271.3401059","10.1145\/3397271"],"URL":"https:\/\/doi.org\/10.1145\/3397271.3401059","relation":{},"subject":[],"published":{"date-parts":[[2020,7,25]]},"assertion":[{"value":"2020-07-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}