{"id":"https://openalex.org/W2132605240","doi":"https://doi.org/10.1145/1135777.1135901","title":"Detecting semantic cloaking on the web","display_name":"Detecting semantic cloaking on the web","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2132605240","doi":"https://doi.org/10.1145/1135777.1135901","mag":"2132605240"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135901","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","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/A5034836937","display_name":"Baoning Wu","orcid":"https://orcid.org/0000-0002-9609-4325"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baoning Wu","raw_affiliation_strings":["Lehigh University, Bethlehem, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehigh University, Bethlehem, PA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042328810","display_name":"Brian D. Davison","orcid":"https://orcid.org/0000-0002-9326-3648"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian D. Davison","raw_affiliation_strings":["Lehigh University, Bethlehem, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehigh University, Bethlehem, PA","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I186143895"],"apc_list":null,"apc_paid":null,"fwci":12.0347,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.9805726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"819","last_page":"828"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9993000030517578,"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":0.9944999814033508,"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/cloaking","display_name":"Cloaking","score":0.9018085598945618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8103201985359192},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7897012829780579},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6160287261009216},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.605475127696991},{"id":"https://openalex.org/keywords/semantic-search","display_name":"Semantic search","score":0.600959062576294},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5488250851631165},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5309179425239563},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5305106043815613},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.48920607566833496},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.4616934061050415},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.43675389885902405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27169910073280334}],"concepts":[{"id":"https://openalex.org/C62973154","wikidata":"https://www.wikidata.org/wiki/Q868018","display_name":"Cloaking","level":3,"score":0.9018085598945618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103201985359192},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7897012829780579},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6160287261009216},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.605475127696991},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.600959062576294},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5488250851631165},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5309179425239563},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5305106043815613},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.48920607566833496},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.4616934061050415},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.43675389885902405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27169910073280334},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C49040817","wikidata":"https://www.wikidata.org/wiki/Q193091","display_name":"Optoelectronics","level":1,"score":0.0},{"id":"https://openalex.org/C110367647","wikidata":"https://www.wikidata.org/wiki/Q497166","display_name":"Metamaterial","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1135777.1135901","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.4440","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.4440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.lehigh.edu/~brian/pubs/2006/WWW/semantic-cloaking.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W38924359","https://openalex.org/W1504694836","https://openalex.org/W1555037502","https://openalex.org/W1566984846","https://openalex.org/W1570448133","https://openalex.org/W1574862351","https://openalex.org/W1764421085","https://openalex.org/W1845137714","https://openalex.org/W1967825155","https://openalex.org/W1982889956","https://openalex.org/W1987365175","https://openalex.org/W2005124845","https://openalex.org/W2023408138","https://openalex.org/W2047221353","https://openalex.org/W2050028965","https://openalex.org/W2053049304","https://openalex.org/W2066636486","https://openalex.org/W2079672501","https://openalex.org/W2089199911","https://openalex.org/W2112400959","https://openalex.org/W2116196348","https://openalex.org/W2116584611","https://openalex.org/W2125055259","https://openalex.org/W2138621811","https://openalex.org/W2139148100","https://openalex.org/W2139731740","https://openalex.org/W2156632103","https://openalex.org/W2157748587","https://openalex.org/W2169270715","https://openalex.org/W2169557227","https://openalex.org/W2170344111","https://openalex.org/W2170602716","https://openalex.org/W2401383085","https://openalex.org/W2966207845","https://openalex.org/W4240407914","https://openalex.org/W4285719527","https://openalex.org/W6601535493","https://openalex.org/W6683392976","https://openalex.org/W6712844215"],"related_works":["https://openalex.org/W2389761961","https://openalex.org/W4254300012","https://openalex.org/W2113184419","https://openalex.org/W2963706618","https://openalex.org/W1999548128","https://openalex.org/W2102475112","https://openalex.org/W1582561301","https://openalex.org/W2888269900","https://openalex.org/W2296157284","https://openalex.org/W2365664923"],"abstract_inverted_index":{"By":[0],"supplying":[1],"different":[2,65],"versions":[3],"of":[4,26,43,67,92,133,138,158],"a":[5,14,73,77,84,89,100,128,131,136],"web":[6,74,78],"page":[7,70],"to":[8,12,18,33,58,104,144],"search":[9,28,45],"engines":[10],"and":[11,76,135,152],"browsers,":[13],"content":[15,22],"provider":[16],"attempts":[17],"cloak":[19],"the":[20,24,27,41,68,97,110,114,147],"real":[21],"from":[23,109,146],"view":[25],"engine.":[29],"Semantic":[30],"cloaking":[31,61,94,107],"refers":[32],"differences":[34],"in":[35],"meaning":[36],"between":[37],"pages":[38,62,108,160],"which":[39,87],"have":[40],"effect":[42],"deceiving":[44],"engine":[46],"ranking":[47],"algorithms.":[48],"In":[49,96],"this":[50],"paper,":[51],"we":[52,125],"propose":[53],"an":[54],"automated":[55],"two-step":[56],"method":[57],"detect":[59,105],"semantic":[60,93,106,162],"based":[63],"on":[64,118],"copies":[66],"same":[69],"downloaded":[71],"by":[72,113],"crawler":[75],"browser.":[79],"The":[80],"first":[81],"step":[82],"is":[83,102],"filtering":[85,115],"step,":[86,99],"generates":[88],"candidate":[90],"list":[91],"pages.":[95],"second":[98],"classifier":[101,129],"used":[103],"candidates":[111],"generated":[112],"step.":[116],"Experiments":[117],"manually":[119],"labeled":[120],"data":[121],"sets":[122],"show":[123],"that":[124,154],"can":[126],"generate":[127],"with":[130],"precision":[132],"93%":[134],"recall":[137],"85%.":[139],"We":[140],"apply":[141],"our":[142],"approach":[143],"links":[145],"dmoz":[148],"Open":[149],"Directory":[150],"Project":[151],"estimate":[153],"more":[155],"than":[156],"50,000":[157],"these":[159],"employ":[161],"cloaking.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":13}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
