{"id":"https://openalex.org/W2008791266","doi":"https://doi.org/10.1145/2184512.2184609","title":"Automatic information extraction from the web","display_name":"Automatic information extraction from the web","publication_year":2012,"publication_date":"2012-03-29","ids":{"openalex":"https://openalex.org/W2008791266","doi":"https://doi.org/10.1145/2184512.2184609","mag":"2008791266"},"language":"en","primary_location":{"id":"doi:10.1145/2184512.2184609","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2184512.2184609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual Southeast Regional Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5065307353","display_name":"Neva Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I94658018","display_name":"University of Memphis","ror":"https://ror.org/01cq23130","country_code":"US","type":"education","lineage":["https://openalex.org/I94658018"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neva Smith","raw_affiliation_strings":["University of Memphis, Memphis, TN"],"affiliations":[{"raw_affiliation_string":"University of Memphis, Memphis, TN","institution_ids":["https://openalex.org/I94658018"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036026859","display_name":"King-Ip Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I94658018","display_name":"University of Memphis","ror":"https://ror.org/01cq23130","country_code":"US","type":"education","lineage":["https://openalex.org/I94658018"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"King-Ip Lin","raw_affiliation_strings":["University of Memphis, Memphis, TN"],"affiliations":[{"raw_affiliation_string":"University of Memphis, Memphis, TN","institution_ids":["https://openalex.org/I94658018"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065307353"],"corresponding_institution_ids":["https://openalex.org/I94658018"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15109806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9581999778747559,"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"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9487000107765198,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8678858280181885},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6045106649398804},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5890029668807983},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5010418891906738},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.46341389417648315},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.415600061416626},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4050005376338959},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35695505142211914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8678858280181885},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6045106649398804},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5890029668807983},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5010418891906738},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.46341389417648315},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.415600061416626},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4050005376338959},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35695505142211914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2184512.2184609","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2184512.2184609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual Southeast Regional Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2015551056","https://openalex.org/W2074295823","https://openalex.org/W2119577990","https://openalex.org/W2160196229"],"related_works":["https://openalex.org/W2611741382","https://openalex.org/W3135843367","https://openalex.org/W3112355890","https://openalex.org/W2613685774","https://openalex.org/W2003932708","https://openalex.org/W1967424056","https://openalex.org/W2284877871","https://openalex.org/W4220741973","https://openalex.org/W36911888","https://openalex.org/W4385731361"],"abstract_inverted_index":{"We":[0,50],"implemented":[1],"a":[2,15],"system":[3,17,22,38],"that":[4,69],"automatically":[5],"extract":[6],"information":[7,44],"from":[8],"web":[9],"pages":[10],"and":[11,59],"store":[12],"them":[13],"in":[14],"database":[16,31],"for":[18],"easy":[19],"processing.":[20],"Our":[21],"only":[23],"requires":[24],"to":[25,27,33,47,55],"user":[26],"provide":[28,66],"the":[29,52],"underlying":[30],"structure":[32],"work.":[34],"In":[35],"addition,":[36],"our":[37,57],"also":[39],"make":[40],"use":[41,51],"of":[42],"existing":[43],"we":[45],"extracted":[46],"improve":[48],"accuracy.":[49],"recipe":[53],"domain":[54],"illustrate":[56],"work,":[58],"initial":[60],"experiment":[61],"results":[62],"(of":[63],"70%":[64],"accuracy)":[65],"encouraging":[67],"signs":[68],"this":[70],"method":[71],"will":[72],"be":[73],"effective":[74],"on":[75],"other":[76],"domains.":[77]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
