{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:07:13Z","timestamp":1755839233112,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["1640864"],"award-info":[{"award-number":["1640864"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,26]]},"DOI":"10.1145\/3459637.3482427","type":"proceedings-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T15:31:19Z","timestamp":1636990279000},"page":"2527-2536","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["DSDD"],"prefix":"10.1145","author":[{"given":"Haoxiang","family":"Zhang","sequence":"first","affiliation":[{"name":"New York University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A\u00e9cio","family":"Santos","sequence":"additional","affiliation":[{"name":"New York University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juliana","family":"Freire","sequence":"additional","affiliation":[{"name":"New York University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5220\/0005030500140021"},{"volume-title":"ACHE Focused Crawler. https:\/\/github.com\/ViDA-NYU\/ache. (accessed","year":"2021","author":"ACHE.","key":"e_1_3_2_1_2_1"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1645953.1646283"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_20"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"volume-title":"World Bank Open Data. https:\/\/data.worldbank.org. (accessed","year":"2021","author":"Bank World","key":"e_1_3_2_1_6_1"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1462148.1462151"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242632"},{"volume-title":"Variations of the similarity function of textrank for automated summarization. arXiv preprint arXiv:1602.03606","year":"2016","author":"Barrios Federico","key":"e_1_3_2_1_9_1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313685"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476346"},{"volume-title":"Encyclopedia of Database Systems, Ling Liu and M. Tamer \u00d6zsu (Eds.)","author":"Chakrabarti Soumen","key":"e_1_3_2_1_12_1"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(99)00042-0"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511466"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(99)00052-3"},{"volume-title":"NYC Open Data. https:\/\/data.cityofnewyork.us. (accessed","year":"2021","author":"City New York","key":"e_1_3_2_1_16_1"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/2968618.2968805"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1363686.1363953"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3313077"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/645926.671854"},{"key":"e_1_3_2_1_21_1","unstructured":"DISCO 2021 (accessed May 2 2021). The DISCO system. https:\/\/github.com\/kienpt\/site_discovery_public.  DISCO 2021 (accessed May 2 2021). The DISCO system. https:\/\/github.com\/kienpt\/site_discovery_public."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2234472"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/1316689.1316725"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-016-0207-1"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/11551362_33"},{"volume-title":"Advanced SEO, Dataset. https:\/\/developers.google.com\/search\/docs\/advanced\/structured-data\/dataset. (accessed","year":"2021","author":"Google","key":"e_1_3_2_1_26_1"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1099554.1099649"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3201064.3201085"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1718487.1718535"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(99)00040-7"},{"volume-title":"Parallel Crawling for Detection and Removal of DUST Using DUSTER. In International Conference on Computing Communication Control and Automation (ICCUBEA). IEEE, 1--5.","year":"2018","author":"Langhi Jyoti G","key":"e_1_3_2_1_31_1"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/2787930"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/1394399"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/2842497.2842502"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1031114.1031117"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2661902"},{"key":"e_1_3_2_1_37_1","unstructured":"Tsuyoshi Murata. 2001. Finding Related Web Pages Based on Connectivity Information from a Search Engine. In WWW Posters.  Tsuyoshi Murata. 2001. Finding Related Web Pages Based on Connectivity Information from a Search Engine. In WWW Posters."},{"volume-title":"NASA Open Data Portal. https:\/\/data.nasa.gov. (accessed","year":"2021","author":"NASA","key":"e_1_3_2_1_38_1"},{"volume-title":"City of Chicago | Data Portal. https:\/\/data.cityofchicago.org\/. (accessed","year":"2021","author":"Chicago City","key":"e_1_3_2_1_39_1"},{"key":"e_1_3_2_1_40_1","unstructured":"Gautam Pant Padmini Srinivasan Filippo Menczer etal 2002. Exploration versus Exploitation in Topic Driven Crawlers.. In WebDyn@ WWW. 88--97.  Gautam Pant Padmini Srinivasan Filippo Menczer et al. 2002. Exploration versus Exploitation in Topic Driven Crawlers.. In WebDyn@ WWW. 88--97."},{"volume-title":"A survey on data pricing: from economics to data science","year":"2020","author":"Pei Jian","key":"e_1_3_2_1_41_1"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159724"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313709"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/505248.506010"},{"volume-title":"Ethiopia country brief. https:\/\/www.wfp.org\/countries\/ethiopia. (accessed","year":"2021","author":"United Nations World Food Programme. [n.d.].","key":"e_1_3_2_1_45_1"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1183614.1183650"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390443"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1459352.1459357"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/2831360.2831372"},{"volume-title":"2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE, 1374--1379","year":"2018","author":"Rajalakshmi R","key":"e_1_3_2_1_50_1"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/1823431"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872518.2889291"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCES.2015.7393043"},{"volume-title":"Michael Biwer, and Patrick Zimmer.","year":"2003","author":"Sizov Sergej","key":"e_1_3_2_1_54_1"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/645529.658281"},{"volume-title":"The Socrata Open Data API. https:\/\/dev.socrata.com. (accessed","year":"2021","key":"e_1_3_2_1_56_1"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148223"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1080\/07421222.1996.11518099"},{"volume-title":"Proceedings of the International Conference on Data Mining (ICDM). Citeseer, 24--29","year":"2005","author":"Werner Lars","key":"e_1_3_2_1_59_1"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2017.08.008"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389726"},{"volume-title":"Find Open Data. https:\/\/github.com\/findopendata\/findopendata. (accessed","year":"2021","author":"Zhu Erkang","key":"e_1_3_2_1_62_1"}],"event":{"name":"CIKM '21: The 30th ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Virtual Event Queensland Australia","acronym":"CIKM '21"},"container-title":["Proceedings of the 30th ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482427","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3459637.3482427","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3459637.3482427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:23Z","timestamp":1750191143000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482427"}},"subtitle":["Domain-Specific Dataset Discovery on the Web"],"short-title":[],"issued":{"date-parts":[[2021,10,26]]},"references-count":62,"alternative-id":["10.1145\/3459637.3482427","10.1145\/3459637"],"URL":"https:\/\/doi.org\/10.1145\/3459637.3482427","relation":{},"subject":[],"published":{"date-parts":[[2021,10,26]]},"assertion":[{"value":"2021-10-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}