{"id":"https://openalex.org/W2079861318","doi":"https://doi.org/10.1145/2567664","title":"Capturing and structuring data mined from the web","display_name":"Capturing and structuring data mined from the web","publication_year":2014,"publication_date":"2014-02-26","ids":{"openalex":"https://openalex.org/W2079861318","doi":"https://doi.org/10.1145/2567664","mag":"2079861318"},"language":"en","primary_location":{"id":"doi:10.1145/2567664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2567664","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2567664","source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications of the ACM","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2567664","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072151331","display_name":"Kate Matsudaira","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kate Matsudaira","raw_affiliation_strings":["Decide.com"],"affiliations":[{"raw_affiliation_string":"Decide.com","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5072151331"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7241,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86695421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"57","issue":"3","first_page":"10","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7294237613677979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6385075449943542},{"id":"https://openalex.org/keywords/publication","display_name":"Publication","score":0.6157839298248291},{"id":"https://openalex.org/keywords/dozen","display_name":"Dozen","score":0.5989739298820496},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.5909959077835083},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.45701199769973755},{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":0.42593634128570557},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.13602274656295776},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.12439918518066406},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.06401458382606506}],"concepts":[{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7294237613677979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6385075449943542},{"id":"https://openalex.org/C41458344","wikidata":"https://www.wikidata.org/wiki/Q732577","display_name":"Publication","level":2,"score":0.6157839298248291},{"id":"https://openalex.org/C185181809","wikidata":"https://www.wikidata.org/wiki/Q605704","display_name":"Dozen","level":2,"score":0.5989739298820496},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.5909959077835083},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.45701199769973755},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.42593634128570557},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.13602274656295776},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.12439918518066406},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.06401458382606506},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2567664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2567664","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2567664","source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications of the ACM","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/2567664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2567664","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2567664","source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications of the ACM","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2079861318.pdf","grobid_xml":"https://content.openalex.org/works/W2079861318.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2123482462","https://openalex.org/W2153704625","https://openalex.org/W2158049821"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4232622239","https://openalex.org/W4248098561","https://openalex.org/W305958151","https://openalex.org/W2782410293","https://openalex.org/W2724504120","https://openalex.org/W2089830040","https://openalex.org/W2809019971","https://openalex.org/W4230509584","https://openalex.org/W2793725298"],"abstract_inverted_index":{"The":[0],"Communications":[1,19],"Web":[2],"site,":[3],"http://cacm.acm.org,":[4],"features":[5],"more":[6],"than":[7],"a":[8],"dozen":[9],"bloggers":[10],"in":[11],"the":[12,46],"BLOG@CACM":[13],"community.":[14],"In":[15],"each":[16],"issue":[17],"of":[18],",":[20],"we'll":[21],"publish":[22],"selected":[23],"posts":[24],"or":[25],"excerpts":[26],".":[27],"twitter":[28],"Follow":[29],"us":[30],"on":[31],"Twitter":[32],"at":[33],"http://twitter.com/blogCACM":[34],"http://cacm.acm.org/blogs/blog-cacm":[35],"Kate":[36],"Matsudaira":[37],"considers":[38],"not":[39],"only":[40],"how":[41],"to":[42,50],"mine":[43],"data":[44],"from":[45],"Web,":[47],"but":[48],"what":[49],"do":[51],"with":[52],"it":[53],"once":[54],"you":[55],"have":[56],"it.":[57]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
