{"id":"https://openalex.org/W3046954785","doi":"https://doi.org/10.1145/3409256.3409831","title":"Analyzing the Influence of Bigrams on Retrieval Bias and Effectiveness","display_name":"Analyzing the Influence of Bigrams on Retrieval Bias and Effectiveness","publication_year":2020,"publication_date":"2020-09-05","ids":{"openalex":"https://openalex.org/W3046954785","doi":"https://doi.org/10.1145/3409256.3409831","mag":"3046954785"},"language":"en","primary_location":{"id":"doi:10.1145/3409256.3409831","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409256.3409831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval","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/A5055982344","display_name":"Abdulaziz Alqatan","orcid":null},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Abdulaziz AlQatan","raw_affiliation_strings":["University of Strathclyde, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Strathclyde, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048218964","display_name":"Leif Azzopardi","orcid":"https://orcid.org/0000-0002-6900-0557"},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leif Azzopardi","raw_affiliation_strings":["University of Strathclyde, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Strathclyde, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059100610","display_name":"Yashar Moshfeghi","orcid":"https://orcid.org/0000-0003-4186-1088"},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yashar Moshfeghi","raw_affiliation_strings":["University of Strathclyde, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Strathclyde, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I181647926"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055982344"],"corresponding_institution_ids":["https://openalex.org/I181647926"],"apc_list":null,"apc_paid":null,"fwci":1.1127,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.843574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"157","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","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/T10286","display_name":"Information Retrieval and Search Behavior","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/T13274","display_name":"Expert finding and Q&A systems","score":0.9879000186920166,"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/T10028","display_name":"Topic Modeling","score":0.9876999855041504,"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/bigram","display_name":"Bigram","score":0.9962205290794373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8127642869949341},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6731737852096558},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5764302015304565},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5271567702293396},{"id":"https://openalex.org/keywords/retrievability","display_name":"Retrievability","score":0.4992187023162842},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.4289627969264984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4089794158935547},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.2681071162223816},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.14508992433547974}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9962205290794373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8127642869949341},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6731737852096558},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5764302015304565},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5271567702293396},{"id":"https://openalex.org/C191072391","wikidata":"https://www.wikidata.org/wiki/Q17043235","display_name":"Retrievability","level":3,"score":0.4992187023162842},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.4289627969264984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4089794158935547},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2681071162223816},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.14508992433547974},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3409256.3409831","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409256.3409831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:strathprints.strath.ac.uk:73422","is_oa":false,"landing_page_url":"https://strathprints.strath.ac.uk/view/author/1111778.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306402226","display_name":"Strathprints: The University of Strathclyde institutional repository (University of Strathclyde)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I181647926","host_organization_name":"University of Strathclyde","host_organization_lineage":["https://openalex.org/I181647926"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W188487579","https://openalex.org/W1574901103","https://openalex.org/W1576022151","https://openalex.org/W1984208669","https://openalex.org/W2010259002","https://openalex.org/W2027875450","https://openalex.org/W2034977219","https://openalex.org/W2047491155","https://openalex.org/W2073109178","https://openalex.org/W2105157020","https://openalex.org/W2126281141","https://openalex.org/W2181863784","https://openalex.org/W2411403793","https://openalex.org/W2767328950","https://openalex.org/W2803159443","https://openalex.org/W2804927761","https://openalex.org/W4213009331","https://openalex.org/W4252076394","https://openalex.org/W6657255468"],"related_works":["https://openalex.org/W1999601537","https://openalex.org/W2072983201","https://openalex.org/W2337771524","https://openalex.org/W2165612380","https://openalex.org/W17684","https://openalex.org/W2358566659","https://openalex.org/W2351505087","https://openalex.org/W2120448205","https://openalex.org/W187510616","https://openalex.org/W3046954785"],"abstract_inverted_index":{"Prior":[0],"work":[1,41],"on":[2,51,86,104],"using":[3,46,92,110],"retrievability":[4],"measures":[5],"in":[6,116,140],"the":[7,17,21,43,49,56,79,88,117,127,142,158,161],"evaluation":[8],"of":[9,45,81,99,129],"information":[10],"retrieval":[11,24,27,52,102,130,175],"(IR)":[12],"systems":[13],"has":[14,38],"laid":[15],"out":[16],"foundations":[18],"for":[19],"investigating":[20],"relationship":[22],"between":[23],"effectiveness":[25],"and":[26,60,156,173],"bias.":[28,53],"While":[29],"various":[30],"factors":[31],"influencing":[32],"bias":[33,80,119],"have":[34],"been":[35,39],"examined,":[36],"there":[37],"no":[40],"examining":[42],"impact":[44],"bigram":[47,112],"within":[48],"index":[50],"Intuitively,":[54],"how":[55,78,87],"documents":[57,89],"are":[58,69,90,136],"represented,":[59],"what":[61],"terms":[62],"they":[63,68],"contain,":[64],"will":[65],"influence":[66],"whether":[67],"retrievable":[70],"or":[71,95],"not.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"investigate":[77],"a":[82,111],"system":[83],"changes":[84],"depending":[85],"represented":[91],"unigrams,":[93],"bigrams":[94,169],"both.":[96],"Our":[97],"analysis":[98],"three":[100,105],"different":[101],"models":[103],"TREC":[106],"collections,":[107],"shows":[108],"that":[109,153,160],"only":[113,123],"representation":[114],"results":[115,139],"lowest":[118],"compared":[120],"to":[121,170],"unigram":[122],"representation,":[124],"but":[125],"at":[126],"expense":[128],"effectiveness.":[131,149],"However,":[132],"when":[133,154],"both":[134],"representations":[135],"combined":[137],"it":[138],"reducing":[141],"overall":[143],"bias,":[144],"as":[145,147],"well":[146],"increasing":[148],"These":[150],"findings":[151],"suggest":[152],"configuring":[155],"indexing":[157],"collection,":[159],"bag-of-words":[162],"approach":[163],"(unigrams),":[164],"should":[165],"be":[166],"augmented":[167],"with":[168],"create":[171],"better":[172],"fairer":[174],"systems.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
