{"id":"https://openalex.org/W4411550015","doi":"https://doi.org/10.1145/3701716.3715303","title":"Benchmarking Near-Duplicate Detection in the era of Pay-walled News","display_name":"Benchmarking Near-Duplicate Detection in the era of Pay-walled News","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4411550015","doi":"https://doi.org/10.1145/3701716.3715303"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3701716.3715303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","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/A5103509874","display_name":"Alok Kumar","orcid":"https://orcid.org/0009-0001-9602-7640"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Alok Kumar","raw_affiliation_strings":["TCS Research, Pune, Maharashtra, India"],"raw_orcid":"https://orcid.org/0009-0001-9602-7640","affiliations":[{"raw_affiliation_string":"TCS Research, Pune, Maharashtra, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117555407","display_name":"Siddharth Tumre","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Siddharth Tumre","raw_affiliation_strings":["TCS Research, Pune, Maharashtra, India"],"raw_orcid":"https://orcid.org/0009-0004-1438-6036","affiliations":[{"raw_affiliation_string":"TCS Research, Pune, Maharashtra, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103152027","display_name":"Sangameshwar Patil","orcid":"https://orcid.org/0000-0002-9452-1397"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sangameshwar Patil","raw_affiliation_strings":["TCS Research, Pune, Maharshtra, India"],"raw_orcid":"https://orcid.org/0000-0002-9452-1397","affiliations":[{"raw_affiliation_string":"TCS Research, Pune, Maharshtra, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"745","last_page":"748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9760000109672546,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9760000109672546,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9383999705314636,"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/T13718","display_name":"Media Influence and Politics","score":0.9017999768257141,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.9331489205360413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5280997157096863},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.21251854300498962},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.07332983613014221}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.9331489205360413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5280997157096863},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.21251854300498962},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.07332983613014221}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3715303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3701716.3715303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2012833704","https://openalex.org/W2124071479","https://openalex.org/W2145349611","https://openalex.org/W2148885851","https://openalex.org/W3022709647","https://openalex.org/W3081389081","https://openalex.org/W4247081456"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699"],"abstract_inverted_index":{"Redundancy":[0],"and":[1,24,39,69,84,114,181,225],"access":[2,98],"restriction":[3],"due":[4,240],"to":[5,99,111,116,241],"paywalls":[6,32],"are":[7,125,162],"emerging":[8],"as":[9,64,82,106],"key":[10],"challenges":[11,113,165],"faced":[12],"by":[13,119],"web-enabled":[14],"digital":[15],"news":[16,26,57,85,137,151,160,172,238],"ecosystem.":[17],"Over":[18],"the":[19,45,112,120,136,167,171,178,203,208,212],"past":[20],"few":[21],"years,":[22],"newspapers":[23],"other":[25,40],"sources":[27],"have":[28,43,72,154],"increasingly":[29],"put-up":[30],"subscription-based":[31],"for":[33,132,222,228],"accessing":[34],"their":[35],"content.":[36],"Further,":[37,175],"copyright,":[38],"legal":[41],"issues":[42],"curtailed":[44],"amount":[46],"of":[47,79,91,103,135,149,164,211,237],"text":[48,93,104,235],"content":[49,168],"that":[50,189],"can":[51],"be":[52,117],"freely":[53],"shared":[54],"in":[55,166,170],"a":[56,147],"feed.":[58],"Well-known":[59],"near-duplicate":[60,121,229],"detection":[61,122,139,230],"algorithms":[62],"such":[63,81],"Locality":[65],"Sensitive":[66],"Hashing":[67],"(LSH)":[68],"its":[70],"variants":[71],"been":[73,155],"used":[74],"on":[75,202,232],"full":[76,92],"length":[77],"versions":[78],"documents":[80],"webpages":[83],"articles.":[86],"So,":[87],"unlike":[88],"traditional":[89],"input":[90],"articles,":[94],"we":[95,144,176],"now":[96],"get":[97],"significantly":[100,195],"less":[101,196],"quantity":[102],"available":[105,131],"input.":[107],"This":[108,206],"has":[109],"added":[110],"complexities":[115],"tackled":[118],"algorithms.":[123],"There":[124],"few,":[126],"if":[127],"any,":[128],"gold-standard":[129],"datasets":[130],"this":[133,142,217,233],"variation":[134],"duplicate":[138],"problem.":[140],"In":[141],"paper,":[143],"present":[145],"NDD-NS,":[146],"dataset":[148,218],"business":[150],"snippets":[152,161,239],"which":[153],"annotated":[156],"with":[157],"near-duplicates.":[158],"These":[159],"representative":[163],"received":[169],"feed":[173],"nowadays.":[174],"benchmark":[177],"Minhash-LSH,":[179],"Simhash":[180],"sentence":[182],"transformer":[183],"based":[184,191],"neural":[185],"approaches.":[186],"We":[187,215],"observe":[188],"hashing":[190],"LSH":[192],"approaches":[193,224],"achieve":[194],"accuracy":[197],"than":[198],"what":[199],"it":[200],"achieved":[201],"SpotSigs":[204],"dataset.":[205,214],"highlights":[207],"challenging":[209],"nature":[210],"NDD-NS":[213],"believe":[216],"will":[219],"pave":[220],"way":[221],"novel":[223],"further":[226],"research":[227],"task":[231],"new":[234],"genre":[236],"access-restrictions.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}