{"id":"https://openalex.org/W2210898515","doi":"https://doi.org/10.1109/gscit.2015.7353328","title":"Detecting spam webpages through topic and semantics analysis","display_name":"Detecting spam webpages through topic and semantics analysis","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W2210898515","doi":"https://doi.org/10.1109/gscit.2015.7353328","mag":"2210898515"},"language":"en","primary_location":{"id":"doi:10.1109/gscit.2015.7353328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gscit.2015.7353328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Global Summit on Computer &amp; Information Technology (GSCIT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5031875407","display_name":"Jing Wan","orcid":"https://orcid.org/0000-0002-4232-7883"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wan","raw_affiliation_strings":["Beijing University of Chemical Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026706844","display_name":"Mufan Liu","orcid":"https://orcid.org/0009-0005-3092-7848"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mufan Liu","raw_affiliation_strings":["Beijing University of Chemical Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076571597","display_name":"Junkai Yi","orcid":"https://orcid.org/0000-0003-3629-1957"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junkai Yi","raw_affiliation_strings":["Beijing University of Chemical Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036230867","display_name":"Xuechao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuechao Zhang","raw_affiliation_strings":["Beijing Technology and Business University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Technology and Business University, Beijing, China","institution_ids":["https://openalex.org/I179026463"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8688,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.72836894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","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/T11644","display_name":"Spam and Phishing Detection","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9991999864578247,"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/web-page","display_name":"Web page","score":0.8282047510147095},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7990195155143738},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6981905698776245},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6536567211151123},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4828360676765442},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45718806982040405},{"id":"https://openalex.org/keywords/semantic-analysis","display_name":"Semantic analysis (machine learning)","score":0.45556119084358215},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41765278577804565}],"concepts":[{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8282047510147095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990195155143738},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6981905698776245},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6536567211151123},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4828360676765442},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45718806982040405},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.45556119084358215},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41765278577804565},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gscit.2015.7353328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gscit.2015.7353328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Global Summit on Computer &amp; Information Technology (GSCIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1845137714","https://openalex.org/W1854214752","https://openalex.org/W1880262756","https://openalex.org/W1970801611","https://openalex.org/W1982889956","https://openalex.org/W1984160751","https://openalex.org/W1987365175","https://openalex.org/W2012422639","https://openalex.org/W2014454002","https://openalex.org/W2030035054","https://openalex.org/W2066055909","https://openalex.org/W2068696370","https://openalex.org/W2091846785","https://openalex.org/W2097496246","https://openalex.org/W2128272588","https://openalex.org/W2138323616","https://openalex.org/W2166812892","https://openalex.org/W2169270715","https://openalex.org/W2603834791","https://openalex.org/W4213009331","https://openalex.org/W4231510805","https://openalex.org/W4253997682","https://openalex.org/W6639055396","https://openalex.org/W6639619044","https://openalex.org/W6685179926","https://openalex.org/W6736255257"],"related_works":["https://openalex.org/W2065457896","https://openalex.org/W3173234801","https://openalex.org/W2167984027","https://openalex.org/W3021302227","https://openalex.org/W10630519","https://openalex.org/W1919377569","https://openalex.org/W3144288563","https://openalex.org/W3123907821","https://openalex.org/W2611741382","https://openalex.org/W2786691313"],"abstract_inverted_index":{"Spam":[0],"web":[1,41],"pages":[2],"have":[3],"posed":[4],"great":[5],"challenges":[6],"to":[7,33,117],"the":[8,18,23,28,40,50,73,90,93,96,101,113,118,127,134,141],"development":[9,24],"of":[10,25,75,78,92,120,129],"search":[11],"engines.":[12],"The":[13,35,137],"content":[14,29,44],"spam":[15,30,45,61],"is":[16,31],"among":[17],"commonly":[19],"used.":[20],"Along":[21],"with":[22,72,95,133],"Internet":[26],"technologies,":[27],"difficult":[32],"detect.":[34],"current":[36],"detection":[37,63],"methods":[38],"for":[39,126],"page":[42],"using":[43],"technique":[46],"primarily":[47],"rely":[48],"on":[49,66],"statistical":[51,135],"features,":[52,79],"which":[53],"has":[54],"obvious":[55],"limitations.":[56],"In":[57],"this":[58],"article,":[59],"a":[60,146],"webpage":[62,97],"method":[64,143],"based":[65],"topic":[67,102,114],"and":[68,82,110],"semantics":[69,81],"was":[70,86,105],"proposed,":[71],"use":[74],"two":[76],"categories":[77],"namely,":[80],"statistics.":[83],"Topic":[84],"modeling":[85],"first":[87],"performed":[88],"over":[89],"contents":[91,98],"webpage,":[94],"mapped":[99],"into":[100],"space.":[103],"This":[104],"followed":[106],"by":[107,131],"semantic":[108],"analysis":[109],"calculation":[111],"in":[112],"space":[115],"according":[116],"distribution":[119],"topics.":[121],"Semantic":[122],"features":[123],"were":[124],"extracted":[125],"classification":[128],"webpages":[130],"combining":[132],"features.":[136],"results":[138],"verified":[139],"that":[140],"proposed":[142],"can":[144],"achieve":[145],"better":[147],"effect.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
