{"id":"https://openalex.org/W2005266950","doi":"https://doi.org/10.1007/s11280-013-0269-6","title":"Entropy-based automated wrapper generation for weblog data extraction","display_name":"Entropy-based automated wrapper generation for weblog data extraction","publication_year":2013,"publication_date":"2013-11-20","ids":{"openalex":"https://openalex.org/W2005266950","doi":"https://doi.org/10.1007/s11280-013-0269-6","mag":"2005266950"},"language":"en","primary_location":{"id":"doi:10.1007/s11280-013-0269-6","doi":"https://doi.org/10.1007/s11280-013-0269-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11280-013-0269-6","pdf_url":null,"source":{"id":"https://openalex.org/S129236917","display_name":"World Wide Web","issn_l":"1386-145X","issn":["1386-145X","1573-1413"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-b","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Wide Web","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://durham-repository.worktribe.com/file/1354582/1/Accepted%20Journal%20Article","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031364513","display_name":"George Gkotsis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"George Gkotsis","raw_affiliation_strings":["Department of Computer Science, University of Warwick, Coventry, CV4 7AL, UK","Department of Computer Science, University of Warwick Coventry, UK, CV4 7AL#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Warwick, Coventry, CV4 7AL, UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"Department of Computer Science, University of Warwick Coventry, UK, CV4 7AL#TAB#","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068475403","display_name":"Karen Stepanyan","orcid":"https://orcid.org/0000-0003-4823-3041","observed_orcids":["https://orcid.org/0000-0003-4823-3041"]},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Karen Stepanyan","raw_affiliation_strings":["Department of Computer Science, University of Warwick, Coventry, CV4 7AL, UK","Department of Computer Science, University of Warwick Coventry, UK, CV4 7AL#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Warwick, Coventry, CV4 7AL, UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"Department of Computer Science, University of Warwick Coventry, UK, CV4 7AL#TAB#","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034125179","display_name":"Alexandra Ioana Cristea","orcid":"https://orcid.org/0000-0002-1454-8822","observed_orcids":["https://orcid.org/0000-0002-1454-8822"]},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexandra I. Cristea","raw_affiliation_strings":["Department of Computer Science, University of Warwick, Coventry, CV4 7AL, UK","Department of Computer Science, University of Warwick Coventry, UK, CV4 7AL#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Warwick, Coventry, CV4 7AL, UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"Department of Computer Science, University of Warwick Coventry, UK, CV4 7AL#TAB#","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012585972","display_name":"Mike S. Joy","orcid":"https://orcid.org/0000-0001-9826-5928","observed_orcids":["https://orcid.org/0000-0001-9826-5928","https://orcid.org/0009-0008-0159-6754"]},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mike Joy","raw_affiliation_strings":["Department of Computer Science, University of Warwick, Coventry, CV4 7AL, UK","Department of Computer Science, University of Warwick Coventry, UK, CV4 7AL#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Warwick, Coventry, CV4 7AL, UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"Department of Computer Science, University of Warwick Coventry, UK, CV4 7AL#TAB#","institution_ids":["https://openalex.org/I39555362"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031364513"],"corresponding_institution_ids":["https://openalex.org/I39555362"],"apc_list":{"value":3290,"currency":"USD","value_usd":3290},"apc_paid":null,"fwci":1.2376,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83881642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"17","issue":"4","first_page":"827","last_page":"846"},"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/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"}},{"id":"https://openalex.org/T14435","display_name":"Information Retrieval and Data Mining","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/blogs","display_name":"blogs","score":0.8130000233650208},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.9129999876022339},{"id":"https://openalex.org/keywords/web-feeds","display_name":"web feeds","score":0.9739999771118164},{"id":"https://openalex.org/keywords/html-parsing","display_name":"HTML parsing","score":0.7239999771118164},{"id":"https://openalex.org/keywords/blogosphere","display_name":"blogosphere","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.876860499382019},{"id":"https://openalex.org/C2779661781","wikidata":"https://www.wikidata.org/wiki/Q374132","display_name":"Blogosphere","level":3,"score":0.6667570471763611},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6297248005867004},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5509931445121765},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5213474035263062},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5202420949935913},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5192378163337708},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5162134766578674},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.49674469232559204},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.46750175952911377},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4435858428478241},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4221544861793518},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4115681052207947},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3469266891479492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2730945944786072},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20308423042297363},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.1955178678035736},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s11280-013-0269-6","doi":"https://doi.org/10.1007/s11280-013-0269-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11280-013-0269-6","pdf_url":null,"source":{"id":"https://openalex.org/S129236917","display_name":"World Wide Web","issn_l":"1386-145X","issn":["1386-145X","1573-1413"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-b","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Wide Web","raw_type":"journal-article"},{"id":"pmh:oai:dro.dur.ac.uk.OAI2:25728","doi":null,"is_oa":false,"landing_page_url":"http://dro.dur.ac.uk/25728/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"World Wide Web, 2013, Vol.17(4), pp.827-846 [Peer Reviewed Journal]","raw_type":"Article"},{"id":"pmh:oai:https://durham-repository.worktribe.com/:1354582","doi":null,"is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/1354582","pdf_url":"https://durham-repository.worktribe.com/file/1354582/1/Accepted%20Journal%20Article","source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:oai:wrap.warwick.ac.uk:61827","doi":null,"is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11280-013-0269-6","pdf_url":"https://wrap.warwick.ac.uk/id/eprint/61827/7/WRAP_gkotsis_stepanyan_cristea_joy_wwwj_2013_final.pdf","source":{"id":"https://openalex.org/S4306400665","display_name":"Warwick Research Archive Portal (University of Warwick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I39555362","host_organization_name":"University of Warwick","host_organization_lineage":["https://openalex.org/I39555362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:https://durham-repository.worktribe.com/:1354582","doi":null,"is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/1354582","pdf_url":"https://durham-repository.worktribe.com/file/1354582/1/Accepted%20Journal%20Article","source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2651749869","display_name":"BlogForever","funder_award_id":"269963","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2005266950.pdf","grobid_xml":"https://content.openalex.org/works/W2005266950.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W11750719","https://openalex.org/W91707408","https://openalex.org/W197497516","https://openalex.org/W1515087027","https://openalex.org/W1542149162","https://openalex.org/W1553448964","https://openalex.org/W1570448133","https://openalex.org/W1616576116","https://openalex.org/W1927338256","https://openalex.org/W2005646337","https://openalex.org/W2104086170","https://openalex.org/W2120101509","https://openalex.org/W2120402301","https://openalex.org/W2135397824","https://openalex.org/W2135479443","https://openalex.org/W2140327372","https://openalex.org/W2143309843","https://openalex.org/W2148210463","https://openalex.org/W2149706766","https://openalex.org/W2156279557","https://openalex.org/W2157140910","https://openalex.org/W2166994378","https://openalex.org/W2319012534","https://openalex.org/W2548007011","https://openalex.org/W2966207845","https://openalex.org/W3006373977","https://openalex.org/W3123518987","https://openalex.org/W4230980612","https://openalex.org/W4232002262","https://openalex.org/W4246154067"],"related_works":["https://openalex.org/W2157140910","https://openalex.org/W1583739829","https://openalex.org/W1592414845","https://openalex.org/W1494002846","https://openalex.org/W2367505665","https://openalex.org/W1556829891","https://openalex.org/W2151928232","https://openalex.org/W100708882","https://openalex.org/W7048121818","https://openalex.org/W2080132606"],"abstract_inverted_index":null,"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}
