{"id":"https://openalex.org/W158294556","doi":null,"title":"Information Extraction from the World Wide Web","display_name":"Information Extraction from the World Wide Web","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W158294556","mag":"158294556"},"language":"en","primary_location":{"id":"mag:158294556","doi":null,"is_oa":false,"landing_page_url":"https://www.isi.edu/integration/courses/csci548/Slides/McCallum_IE_tutorial.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107835063","display_name":"Andrew McCallum","orcid":"https://orcid.org/0000-0003-2843-6992","observed_orcids":["https://orcid.org/0000-0003-2843-6992"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew McCallum","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2843-6992","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051617344","display_name":"William W. Cohen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William W. Cohen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108828659","display_name":"Martin Baker","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Baker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.2177,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97342859,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":95},"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":0.9984999895095825,"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":0.9984999895095825,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0006000000284984708,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.00019999999494757503,"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/information-extraction","display_name":"information extraction","score":0.9929999709129333},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.9599999785423279},{"id":"https://openalex.org/keywords/web-mining","display_name":"web mining","score":0.6470000147819519},{"id":"https://openalex.org/keywords/web-scraping","display_name":"web scraping","score":0.4429999887943268}],"concepts":[{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5351285338401794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4965119957923889},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3208589255809784}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:158294556","doi":null,"is_oa":false,"landing_page_url":"https://www.isi.edu/integration/courses/csci548/Slides/McCallum_IE_tutorial.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W200042785","https://openalex.org/W1598003989","https://openalex.org/W1616576116","https://openalex.org/W1979960035","https://openalex.org/W2085099553","https://openalex.org/W2093559286","https://openalex.org/W2104884878","https://openalex.org/W2137096228","https://openalex.org/W2153072229","https://openalex.org/W2161290181","https://openalex.org/W2162340487","https://openalex.org/W2163915185","https://openalex.org/W2163918411","https://openalex.org/W2168808732","https://openalex.org/W2785349534"],"related_works":["https://openalex.org/W6884994139","https://openalex.org/W6903846437","https://openalex.org/W7095957730","https://openalex.org/W4385571731","https://openalex.org/W2302728551","https://openalex.org/W2338276930","https://openalex.org/W2587385920","https://openalex.org/W6903947809","https://openalex.org/W2288934155","https://openalex.org/W7097704274"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2016-06-24T00:00:00"}
