{"id":"https://openalex.org/W2463059953","doi":"https://doi.org/10.1145/2911451.2914757","title":"Understanding Website Behavior based on User Agent","display_name":"Understanding Website Behavior based on User Agent","publication_year":2016,"publication_date":"2016-07-07","ids":{"openalex":"https://openalex.org/W2463059953","doi":"https://doi.org/10.1145/2911451.2914757","mag":"2463059953"},"language":"en","primary_location":{"id":"doi:10.1145/2911451.2914757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2911451.2914757","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2914757&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2914757&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043862809","display_name":"Kien Pham","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kien Pham","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101972578","display_name":"A\u00e9cio Santos","orcid":"https://orcid.org/0000-0002-5124-7770"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A\u00e9cio Santos","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006773757","display_name":"Juliana Freire","orcid":"https://orcid.org/0000-0003-3915-7075"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juliana Freire","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043862809"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":3.4529,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.93413567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1053","last_page":"1056"},"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":0.9995999932289124,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.9056482315063477},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8618065118789673},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8224630951881409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8154698014259338},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6753716468811035},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6531210541725159},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.608595609664917},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42741304636001587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15068107843399048},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14270246028900146}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9056482315063477},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8618065118789673},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8224630951881409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8154698014259338},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6753716468811035},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6531210541725159},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.608595609664917},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42741304636001587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15068107843399048},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14270246028900146},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2911451.2914757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2911451.2914757","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2914757&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2911451.2914757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2911451.2914757","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2914757&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2006955685","display_name":null,"funder_award_id":"CI-EN-1405927","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2890859391","display_name":"CI-EN: Enhancing and Supporting a Community-Based Data Analysis, Visualization, and Provenance Platform","funder_award_id":"1405927","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5033923906","display_name":null,"funder_award_id":"CI-EN-1405927,CNS-1229185","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G519871063","display_name":"MRI: Acquisition of an Infrastructure for Prototyping Next-Generation Algorithms for Large-Scale Visualization, Data Processing and Analysis","funder_award_id":"1229185","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7349255816","display_name":null,"funder_award_id":"FA8750-14-2-0236","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2463059953.pdf","grobid_xml":"https://content.openalex.org/works/W2463059953.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W38924359","https://openalex.org/W183174002","https://openalex.org/W1583640058","https://openalex.org/W2007089944","https://openalex.org/W2015452169","https://openalex.org/W2043780693","https://openalex.org/W2102475166","https://openalex.org/W2138393708","https://openalex.org/W2159710624","https://openalex.org/W6601535493"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W2137810919","https://openalex.org/W2089702591","https://openalex.org/W4255854114","https://openalex.org/W4385695127"],"abstract_inverted_index":{"Web":[0],"sites":[1],"have":[2],"adopted":[3],"a":[4,26,60],"variety":[5],"of":[6,67],"adversarial":[7,40,69],"techniques":[8,41],"to":[9,21,28,44,51,77],"prevent":[10],"web":[11,61],"crawlers":[12],"from":[13],"retrieving":[14],"their":[15],"content.":[16],"While":[17],"it":[18],"is":[19,34,42],"possible":[20],"simulate":[22],"users":[23],"behavior":[24],"using":[25],"browser":[27],"crawl":[29],"such":[30],"sites,":[31],"this":[32],"approach":[33],"not":[35],"scalable.":[36],"Therefore,":[37],"understanding":[38],"existing":[39],"important":[43],"design":[45],"crawling":[46],"strategies":[47],"that":[48],"can":[49],"adapt":[50],"retrieve":[52],"the":[53,65,68,73],"content":[54],"as":[55,57],"efficiently":[56],"possible.":[58],"Ideally,":[59],"crawler":[62],"should":[63],"detect":[64],"nature":[66],"policies":[70],"and":[71],"select":[72],"most":[74],"cost-effective":[75],"means":[76],"defeat":[78],"them.":[79]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
