{"id":"https://openalex.org/W2036101886","doi":"https://doi.org/10.5430/air.v2n1p44","title":"Exploiting web scraping in a collaborative filtering- based approach to web advertising","display_name":"Exploiting web scraping in a collaborative filtering- based approach to web advertising","publication_year":2012,"publication_date":"2012-11-20","ids":{"openalex":"https://openalex.org/W2036101886","doi":"https://doi.org/10.5430/air.v2n1p44","mag":"2036101886"},"language":"en","primary_location":{"id":"doi:10.5430/air.v2n1p44","is_oa":true,"landing_page_url":"https://doi.org/10.5430/air.v2n1p44","pdf_url":"http://www.sciedu.ca/journal/index.php/air/article/download/1390/1115","source":{"id":"https://openalex.org/S4210167461","display_name":"Artificial Intelligence Research","issn_l":"1927-6974","issn":["1927-6974","1927-6982"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320842","host_organization_name":"Sciedu Press","host_organization_lineage":["https://openalex.org/P4310320842"],"host_organization_lineage_names":["Sciedu Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"http://www.sciedu.ca/journal/index.php/air/article/download/1390/1115","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072647170","display_name":"Eloisa Vargiu","orcid":"https://orcid.org/0000-0002-3840-628X"},"institutions":[{"id":"https://openalex.org/I4210150449","display_name":"Barcelona Digital Centro Tecnol\u00f3gico","ror":"https://ror.org/04v2q5t19","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210150449"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Eloisa Vargiu","raw_affiliation_strings":["Barcelona Digital Technological Centre"],"affiliations":[{"raw_affiliation_string":"Barcelona Digital Technological Centre","institution_ids":["https://openalex.org/I4210150449"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075429407","display_name":"Mirko Urru","orcid":null},"institutions":[{"id":"https://openalex.org/I172446870","display_name":"University of Cagliari","ror":"https://ror.org/003109y17","country_code":"IT","type":"education","lineage":["https://openalex.org/I172446870"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mirko Urru","raw_affiliation_strings":["Dipartimento di Matematica e Informatica, Universit\u00e0 di Cagliari","Dipartimento di Matematica e Informatica, Universit\u00e0 di Cagliari,"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, Universit\u00e0 di Cagliari","institution_ids":["https://openalex.org/I172446870"]},{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, Universit\u00e0 di Cagliari,","institution_ids":["https://openalex.org/I172446870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072647170"],"corresponding_institution_ids":["https://openalex.org/I4210150449"],"apc_list":null,"apc_paid":null,"fwci":4.9739,"has_fulltext":true,"cited_by_count":132,"citation_normalized_percentile":{"value":0.95077588,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"2","issue":"1","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":0.9998000264167786,"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":0.9998000264167786,"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/T11478","display_name":"Caching and Content Delivery","score":0.9943000078201294,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.993399977684021,"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":0.754905104637146},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7226686477661133},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.689642071723938},{"id":"https://openalex.org/keywords/scraper-site","display_name":"Scraper site","score":0.6518573760986328},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.5519692897796631},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4962204098701477},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.4946756064891815},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.4901479184627533},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.48246222734451294},{"id":"https://openalex.org/keywords/web-analytics","display_name":"Web analytics","score":0.4769398272037506},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.435800701379776},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4348782002925873},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.43444302678108215},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.35217350721359253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754905104637146},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7226686477661133},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.689642071723938},{"id":"https://openalex.org/C78500136","wikidata":"https://www.wikidata.org/wiki/Q477840","display_name":"Scraper site","level":2,"score":0.6518573760986328},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.5519692897796631},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4962204098701477},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.4946756064891815},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.4901479184627533},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.48246222734451294},{"id":"https://openalex.org/C516187249","wikidata":"https://www.wikidata.org/wiki/Q10719477","display_name":"Web analytics","level":5,"score":0.4769398272037506},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.435800701379776},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4348782002925873},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.43444302678108215},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.35217350721359253},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5430/air.v2n1p44","is_oa":true,"landing_page_url":"https://doi.org/10.5430/air.v2n1p44","pdf_url":"http://www.sciedu.ca/journal/index.php/air/article/download/1390/1115","source":{"id":"https://openalex.org/S4210167461","display_name":"Artificial Intelligence Research","issn_l":"1927-6974","issn":["1927-6974","1927-6982"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320842","host_organization_name":"Sciedu Press","host_organization_lineage":["https://openalex.org/P4310320842"],"host_organization_lineage_names":["Sciedu Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5430/air.v2n1p44","is_oa":true,"landing_page_url":"https://doi.org/10.5430/air.v2n1p44","pdf_url":"http://www.sciedu.ca/journal/index.php/air/article/download/1390/1115","source":{"id":"https://openalex.org/S4210167461","display_name":"Artificial Intelligence Research","issn_l":"1927-6974","issn":["1927-6974","1927-6982"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320842","host_organization_name":"Sciedu Press","host_organization_lineage":["https://openalex.org/P4310320842"],"host_organization_lineage_names":["Sciedu Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2036101886.pdf","grobid_xml":"https://content.openalex.org/works/W2036101886.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W36037584","https://openalex.org/W56761911","https://openalex.org/W90045850","https://openalex.org/W108447284","https://openalex.org/W126199333","https://openalex.org/W153995565","https://openalex.org/W616073450","https://openalex.org/W1532325895","https://openalex.org/W1559548043","https://openalex.org/W1567479583","https://openalex.org/W1589355968","https://openalex.org/W1772070704","https://openalex.org/W1966553486","https://openalex.org/W1967766192","https://openalex.org/W1984349431","https://openalex.org/W2009892466","https://openalex.org/W2012852390","https://openalex.org/W2030144199","https://openalex.org/W2042281163","https://openalex.org/W2042616792","https://openalex.org/W2046325278","https://openalex.org/W2047221353","https://openalex.org/W2066590388","https://openalex.org/W2073448073","https://openalex.org/W2094005170","https://openalex.org/W2113843799","https://openalex.org/W2116030947","https://openalex.org/W2124591829","https://openalex.org/W2147859400","https://openalex.org/W2147896987","https://openalex.org/W2155106456","https://openalex.org/W2159094788","https://openalex.org/W2171960770","https://openalex.org/W2188998750","https://openalex.org/W2489568120","https://openalex.org/W2497145372","https://openalex.org/W2737184189","https://openalex.org/W3022307797","https://openalex.org/W4213009331","https://openalex.org/W4236322898","https://openalex.org/W4241676240","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2268201587","https://openalex.org/W3174726539","https://openalex.org/W2182629206","https://openalex.org/W2330648582","https://openalex.org/W2187544069","https://openalex.org/W2800499880","https://openalex.org/W141438787","https://openalex.org/W2332851378","https://openalex.org/W2356091546","https://openalex.org/W2547725155"],"abstract_inverted_index":{"Web":[0,25,41,77,87,98,111,115],"scraping":[1,83],"is":[2,27,128],"the":[3,73,86,104,120],"set":[4],"of":[5,17,23,33,64,75],"techniques":[6,70,84],"used":[7],"to":[8,28],"automatically":[9],"get":[10],"some":[11],"information":[12],"from":[13],"a":[14,24,76,95,109,125],"website":[15],"instead":[16],"manually":[18],"copying":[19],"it.":[20],"The":[21],"goal":[22],"scraper":[26],"look":[29],"for":[30,108],"certain":[31],"kinds":[32],"information,":[34],"extract,":[35],"and":[36,52],"aggregate":[37],"it":[38],"into":[39],"new":[40],"pages.":[42],"In":[43,58,79],"particular,":[44,80],"scrapers":[45],"are":[46],"focused":[47],"on":[48,68],"transforming":[49],"unstructured":[50],"data":[51],"save":[53],"them":[54],"in":[55,85,123],"structured":[56],"databases.":[57],"this":[59,91],"paper,":[60],"among":[61],"others":[62],"kind":[63],"scraping,":[65],"we":[66,81,93],"focus":[67],"those":[69],"that":[71],"extract":[72],"content":[74],"page.":[78],"adopt":[82],"advertising":[88,99],"field.":[89],"To":[90,117],"end,":[92],"propose":[94],"collaborative":[96],"filtering-based":[97],"system":[100,121],"aimed":[101],"at":[102],"finding":[103],"most":[105],"relevant":[106],"ads":[107],"generic":[110],"page":[112],"by":[113],"exploiting":[114],"scraping.":[116],"illustrate":[118],"how":[119],"works":[122],"practice,":[124],"case":[126],"study":[127],"presented.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}