{"id":"https://openalex.org/W7219766513","doi":"https://doi.org/10.5281/zenodo.23143116","title":"WebRuleBench annotation study \u2014 data (v1.0)","display_name":"WebRuleBench annotation study \u2014 data (v1.0)","publication_year":2026,"publication_date":"2026-10-04","ids":{"openalex":"https://openalex.org/W7219766513","doi":"https://doi.org/10.5281/zenodo.23143116"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23143116","doi":"https://doi.org/10.5281/zenodo.23143116","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23143116","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23143116","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006050193","display_name":"Burak Sevinc","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sevin\u00e7, Burak","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7918-1278","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078816512","display_name":"Erdin\u00e7 Uzun","orcid":"https://orcid.org/0000-0003-4351-2244","observed_orcids":["https://orcid.org/0000-0003-4351-2244"]},"institutions":[{"id":"https://openalex.org/I125454184","display_name":"Tekirda\u011f Nam\u0131k Kemal University","ror":"https://ror.org/01a0mk874","country_code":"TR","type":"education","lineage":["https://openalex.org/I125454184"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Uzun, Erdin\u00e7","raw_affiliation_strings":["Tekirda\u011f Nam\u0131k Kemal University"],"raw_orcid":"https://orcid.org/0000-0003-4351-2244","affiliations":[{"raw_affiliation_string":"Tekirda\u011f Nam\u0131k Kemal University","institution_ids":["https://openalex.org/I125454184"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13910","display_name":"Computational and Text Analysis Methods","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/inter-annotator-agreement","display_name":"inter-annotator agreement","score":0.8240000009536743},{"id":"https://openalex.org/keywords/web-scraping","display_name":"web scraping","score":0.5600000023841858},{"id":"https://openalex.org/keywords/news-websites","display_name":"news websites","score":0.5379999876022339},{"id":"https://openalex.org/keywords/ground-truth-annotation","display_name":"ground truth annotation","score":0.5809999704360962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698000073432922},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6269999742507935},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.5913000106811523},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5131999850273132},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41119998693466187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.385699987411499},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.33809998631477356},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2985331491","wikidata":"https://www.wikidata.org/wiki/Q5227298","display_name":"Data format","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23143116","doi":"https://doi.org/10.5281/zenodo.23143116","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23143116","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.23143117","doi":"https://doi.org/10.5281/zenodo.23143117","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23143117","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23143116","doi":"https://doi.org/10.5281/zenodo.23143116","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23143116","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7219688401","https://openalex.org/W7065296734","https://openalex.org/W7162401835","https://openalex.org/W2123666189","https://openalex.org/W2315967650","https://openalex.org/W4394102597","https://openalex.org/W2396209226","https://openalex.org/W7101226318","https://openalex.org/W7142884435","https://openalex.org/W6992670551"],"abstract_inverted_index":{"Data":[0],"of":[1,31],"the":[2,8,35,40],"inter-annotator":[3],"agreement":[4,41],"study":[5],"reported":[6],"in":[7],"WebRuleBench":[9],"paper:":[10],"CSS":[11],"/":[12,14],"XPath":[13],"regex":[15],"extraction":[16],"rules":[17],"written":[18],"independently":[19],"by":[20],"three":[21],"annotators":[22],"for":[23],"one":[24],"article":[25],"layout":[26],"(\"Article":[27],"1\")":[28],"on":[29],"each":[30],"10":[32],"news":[33],"sites,":[34],"approved":[36],"ground":[37],"truth,":[38],"and":[39],"results.":[42]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-05T00:00:00"}
