{"id":"https://openalex.org/W2805550038","doi":"https://doi.org/10.1109/ictas.2018.8368766","title":"A comparative analysis of text similarity measures and algorithms in research paper recommender systems","display_name":"A comparative analysis of text similarity measures and algorithms in research paper recommender systems","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2805550038","doi":"https://doi.org/10.1109/ictas.2018.8368766","mag":"2805550038"},"language":"en","primary_location":{"id":"doi:10.1109/ictas.2018.8368766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictas.2018.8368766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Conference on Information Communications Technology and Society (ICTAS)","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":null,"display_name":"Maake Benard Magara","orcid":null},"institutions":[{"id":"https://openalex.org/I137616099","display_name":"Tshwane University of Technology","ror":"https://ror.org/037mrss42","country_code":"ZA","type":"education","lineage":["https://openalex.org/I137616099"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Maake Benard Magara","raw_affiliation_strings":["Computer Systems Engineering, Tshwane University of Technology, Pretoria, South Africa"],"affiliations":[{"raw_affiliation_string":"Computer Systems Engineering, Tshwane University of Technology, Pretoria, South Africa","institution_ids":["https://openalex.org/I137616099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046107382","display_name":"Sunday O. Ojo","orcid":"https://orcid.org/0000-0002-7197-8853"},"institutions":[{"id":"https://openalex.org/I137616099","display_name":"Tshwane University of Technology","ror":"https://ror.org/037mrss42","country_code":"ZA","type":"education","lineage":["https://openalex.org/I137616099"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Sunday O. Ojo","raw_affiliation_strings":["Computer Systems Engineering, Tshwane University of Technology, Pretoria, South Africa"],"affiliations":[{"raw_affiliation_string":"Computer Systems Engineering, Tshwane University of Technology, Pretoria, South Africa","institution_ids":["https://openalex.org/I137616099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037962292","display_name":"Tranos Zuva","orcid":"https://orcid.org/0000-0001-9579-3899"},"institutions":[{"id":"https://openalex.org/I129615261","display_name":"Vaal University of Technology","ror":"https://ror.org/05ey7mm31","country_code":"ZA","type":"education","lineage":["https://openalex.org/I129615261"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Tranos Zuva","raw_affiliation_strings":["Department of ICT, Vaal University of Technology, Vanderbijlpark, South Africa"],"affiliations":[{"raw_affiliation_string":"Department of ICT, Vaal University of Technology, Vanderbijlpark, South Africa","institution_ids":["https://openalex.org/I129615261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I137616099"],"apc_list":null,"apc_paid":null,"fwci":3.8927,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.94736529,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9990000128746033,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7860115170478821},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7795592546463013},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.7337336540222168},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7336514592170715},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5969563722610474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5678043961524963},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5313743948936462},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5293772220611572},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5221489071846008},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4999101161956787},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.453460156917572},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4418529272079468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41071081161499023},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.17641332745552063},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11170092225074768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860115170478821},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7795592546463013},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.7337336540222168},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7336514592170715},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5969563722610474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5678043961524963},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5313743948936462},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5293772220611572},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5221489071846008},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4999101161956787},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.453460156917572},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4418529272079468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41071081161499023},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.17641332745552063},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11170092225074768},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictas.2018.8368766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictas.2018.8368766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Conference on Information Communications Technology and Society (ICTAS)","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":15,"referenced_works":["https://openalex.org/W26591655","https://openalex.org/W39617701","https://openalex.org/W100415715","https://openalex.org/W429766147","https://openalex.org/W1522930108","https://openalex.org/W1965398296","https://openalex.org/W1997423738","https://openalex.org/W2090012551","https://openalex.org/W2171313960","https://openalex.org/W2207136466","https://openalex.org/W2513641002","https://openalex.org/W4285719527","https://openalex.org/W6601626325","https://openalex.org/W6604108467","https://openalex.org/W6688275423"],"related_works":["https://openalex.org/W2951075339","https://openalex.org/W1966742602","https://openalex.org/W4226161247","https://openalex.org/W3134944010","https://openalex.org/W2034680797","https://openalex.org/W2967426019","https://openalex.org/W3210752578","https://openalex.org/W4207040723","https://openalex.org/W2990537558","https://openalex.org/W2621610018"],"abstract_inverted_index":{"The":[0,126,156],"increase":[1],"in":[2,68,182],"the":[3,14,18,42,62,92,109,135,138,164],"number":[4],"of":[5,17,66,150,190],"online":[6,26],"published":[7],"research":[8,70,121,204],"papers":[9],"can":[10,57,200],"be":[11,58,176,201],"attributed":[12],"to":[13,38,49,60,90,134,175,196],"recent":[15],"developments":[16],"internet":[19],"and":[20,25,34,53,64,95,115,137,147,152,171,192,208,212],"web":[21],"technologies.":[22],"However,":[23],"researchers":[24],"users":[27],"have":[28],"a":[29,69],"difficult":[30],"time":[31,148],"getting":[32,143],"relevant":[33],"accurate":[35],"information":[36,39],"due":[37],"explosion":[40],"on":[41,120],"internet.":[43],"In":[44],"this":[45,183],"paper,":[46],"we":[47],"seek":[48],"establish":[50],"which":[51],"algorithms":[52,79,119,141,193],"similarity":[54,82,99,123,158,166,169,206],"metric":[55],"combinations":[56,189],"used":[59,202],"optimise":[61],"search":[63],"recommendation":[65],"articles":[67],"paper":[71,122,184,205],"recommender":[72],"systems.":[73],"Our":[74],"investigation":[75],"utilised":[76,89],"non-linear":[77],"classification":[78],"with":[80,163],"text":[81],"measures.":[83],"An":[84],"offline":[85],"evaluation":[86,124,207],"approach":[87],"is":[88],"determine":[91],"models":[93,198],"accuracy":[94,146],"performance,":[96],"while":[97],"various":[98],"metrics":[100,170,191],"are":[101,173,187,215],"assessed":[102],"using":[103],"available":[104],"datasets.":[105,125],"We":[106],"will":[107],"utilise":[108],"Recursive":[110],"PARTitioning":[111],"(rpart),":[112],"Random":[113,139],"Forest":[114,140],"Boosted":[116,136],"machine":[117],"learning":[118],"rpart":[127],"algorithm":[128],"generally":[129],"performed":[130,159],"well":[131],"when":[132,161,194],"compared":[133,162],"by":[142],"an":[144],"average":[145],"efficiency":[149],"80.73":[151],"2.354628":[153],"seconds":[154],"respectively.":[155],"cosine":[157],"best":[160],"other":[165],"metrics.":[167],"New":[168],"measures":[172],"going":[174],"proposed.":[177],"It":[178],"has":[179],"been":[180],"established":[181],"that":[185,199],"there":[186],"better":[188],"attempting":[195],"develop":[197],"for":[203],"recommendation.":[209],"Further":[210],"challenges":[211],"open":[213],"issues":[214],"identified.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}