{"id":"https://openalex.org/W1816783716","doi":"https://doi.org/10.1145/2740908.2742750","title":"Probabilistic Deduplication of Anonymous Web Traffic","display_name":"Probabilistic Deduplication of Anonymous Web Traffic","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W1816783716","doi":"https://doi.org/10.1145/2740908.2742750","mag":"1816783716"},"language":"en","primary_location":{"id":"doi:10.1145/2740908.2742750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2742750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th 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/A5042165238","display_name":"Rishiraj Saha Roy","orcid":"https://orcid.org/0000-0002-5774-5658"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rishiraj Saha Roy","raw_affiliation_strings":["Adobe Research Big Data Intelligence Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Adobe Research Big Data Intelligence Lab, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056964468","display_name":"Ritwik Sinha","orcid":"https://orcid.org/0000-0002-0344-1368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ritwik Sinha","raw_affiliation_strings":["Adobe Research Big Data Intelligence Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Adobe Research Big Data Intelligence Lab, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004920788","display_name":"Niyati Chhaya","orcid":"https://orcid.org/0000-0002-3586-7240"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niyati Chhaya","raw_affiliation_strings":["Adobe Research Big Data Intelligence Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Adobe Research Big Data Intelligence Lab, Bangalore, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101067322","display_name":"Shiv Saini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiv Saini","raw_affiliation_strings":["Adobe Research Big Data Intelligence Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Adobe Research Big Data Intelligence Lab, Bangalore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042165238"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8629,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81656968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9998999834060669,"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/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/T12034","display_name":"Digital and Cyber Forensics","score":0.9986000061035156,"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":0.7889810800552368},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.7836328744888306},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6863351464271545},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.5745075941085815},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.527347207069397},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5202592611312866},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.466835618019104},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4263139069080353},{"id":"https://openalex.org/keywords/visitor-pattern","display_name":"Visitor pattern","score":0.41590118408203125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4102022051811218},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3853776156902313},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3149811029434204},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2872313857078552},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18608427047729492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1641518473625183},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.09902405738830566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7889810800552368},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.7836328744888306},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6863351464271545},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.5745075941085815},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.527347207069397},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5202592611312866},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.466835618019104},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4263139069080353},{"id":"https://openalex.org/C48947383","wikidata":"https://www.wikidata.org/wiki/Q830719","display_name":"Visitor pattern","level":2,"score":0.41590118408203125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4102022051811218},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3853776156902313},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3149811029434204},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2872313857078552},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18608427047729492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1641518473625183},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.09902405738830566},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2740908.2742750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2742750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","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":2,"referenced_works":["https://openalex.org/W1525967479","https://openalex.org/W2105783544"],"related_works":["https://openalex.org/W4254879869","https://openalex.org/W3022576529","https://openalex.org/W2628526247","https://openalex.org/W2596401011","https://openalex.org/W4401519790","https://openalex.org/W2913569734","https://openalex.org/W2702570413","https://openalex.org/W3127229356","https://openalex.org/W2901284887","https://openalex.org/W2000801317"],"abstract_inverted_index":{"Cookies":[0],"and":[1,52,75],"log":[2],"in-based":[3],"authentication":[4],"often":[5],"provide":[6],"incomplete":[7],"data":[8],"for":[9,32,66],"stitching":[10],"website":[11],"visitors":[12],"across":[13],"multiple":[14],"sources,":[15],"necessitating":[16],"probabilistic":[17],"deduplication.":[18],"We":[19,37],"address":[20],"this":[21],"challenge":[22],"by":[23,42],"formulating":[24],"the":[25,63,84,91,101],"problem":[26],"as":[27],"a":[28],"binary":[29],"classification":[30],"task":[31],"pairs":[33],"of":[34,94],"anonymous":[35],"visitors.":[36],"compute":[38],"visitor":[39],"proximity":[40],"vectors":[41],"converting":[43],"categorical":[44],"variables":[45,61],"like":[46],"IP":[47],"addresses,":[48],"product":[49],"search":[50],"keywords":[51],"URLs":[53],"with":[54],"very":[55],"high":[56],"cardinalities":[57],"to":[58,83],"continuous":[59],"numeric":[60],"using":[62],"Jaccard":[64],"coefficient":[65],"each":[67],"attribute.":[68],"Our":[69],"method":[70],"achieves":[71],"about":[72],"90%":[73],"AUC":[74],"F-scores":[76],"in":[77,97],"identifying":[78],"whether":[79],"two":[80],"cookies":[81],"map":[82],"same":[85],"visitor,":[86],"while":[87],"providing":[88],"insights":[89],"on":[90],"relative":[92],"importance":[93],"available":[95],"features":[96],"Web":[98],"analytics":[99],"towards":[100],"deduplication":[102],"process.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
