{"id":"https://openalex.org/W7223962234","doi":"https://doi.org/10.15294/sji.v13i4.59181","title":"A Weighted Hybrid of TF-IDF and Winnowing for Content-Based Scientific Article Recommendation with Citation-Based Ground Truth","display_name":"A Weighted Hybrid of TF-IDF and Winnowing for Content-Based Scientific Article Recommendation with Citation-Based Ground Truth","publication_year":2026,"publication_date":"2026-10-26","ids":{"openalex":"https://openalex.org/W7223962234","doi":"https://doi.org/10.15294/sji.v13i4.59181"},"language":"en","primary_location":{"id":"doi:10.15294/sji.v13i4.59181","doi":"https://doi.org/10.15294/sji.v13i4.59181","is_oa":true,"landing_page_url":"https://doi.org/10.15294/sji.v13i4.59181","pdf_url":"https://journal.unnes.ac.id/journals/sji/article/download/59181/12000","source":{"id":"https://openalex.org/S4210171202","display_name":"Scientific Journal of Informatics","issn_l":"2407-7658","issn":["2407-7658","2460-0040"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":"https://openalex.org/P4310315212","host_organization_name":"Jurusan Ilmu Komputer Universitas Negeri Semarang","host_organization_lineage":["https://openalex.org/P4310315212"],"host_organization_lineage_names":["Jurusan Ilmu Komputer Universitas Negeri Semarang"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Journal of Informatics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://journal.unnes.ac.id/journals/sji/article/download/59181/12000","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159125781","display_name":"Moch Zawaruddin Abdullah","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261658","display_name":"Politeknik Negeri Malang","ror":"https://ror.org/05n29k456","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405261658"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Moch Zawaruddin Abdullah","raw_affiliation_strings":["Department of Information Technology, Politeknik Negeri Malang, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Politeknik Negeri Malang, Indonesia","institution_ids":["https://openalex.org/I4405261658"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159778926","display_name":"Krisna Andika Wijaya","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261658","display_name":"Politeknik Negeri Malang","ror":"https://ror.org/05n29k456","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405261658"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Krisna Andika Wijaya","raw_affiliation_strings":["Department of Information Technology, Politeknik Negeri Malang, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Politeknik Negeri Malang, Indonesia","institution_ids":["https://openalex.org/I4405261658"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114458909","display_name":"Imam Fahrur Rozi","orcid":"https://orcid.org/0009-0002-0622-7161","observed_orcids":["https://orcid.org/0009-0002-0622-7161"]},"institutions":[{"id":"https://openalex.org/I4405261658","display_name":"Politeknik Negeri Malang","ror":"https://ror.org/05n29k456","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405261658"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Imam Fahrur Rozi","raw_affiliation_strings":["Department of Information Technology, Politeknik Negeri Malang, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Politeknik Negeri Malang, Indonesia","institution_ids":["https://openalex.org/I4405261658"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072826404","display_name":"Endah Septa Sintiya","orcid":"https://orcid.org/0000-0001-8263-8646","observed_orcids":["https://orcid.org/0000-0001-8263-8646"]},"institutions":[{"id":"https://openalex.org/I4405261658","display_name":"Politeknik Negeri Malang","ror":"https://ror.org/05n29k456","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405261658"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Endah Septa Sintiya","raw_affiliation_strings":["Department of Information Technology, Politeknik Negeri Malang, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Politeknik Negeri Malang, Indonesia","institution_ids":["https://openalex.org/I4405261658"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066847689","display_name":"Dian Septiani Santoso","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387153613","display_name":"Politeknik Elektronika Negeri Surabaya","ror":"https://ror.org/00cf3sf89","country_code":"ID","type":"education","lineage":["https://openalex.org/I4387153613"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dian Septiani Santoso","raw_affiliation_strings":["Department of Informatics and Computer Engineering, Politeknik Elektronika Negeri Surabaya, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics and Computer Engineering, Politeknik Elektronika Negeri Surabaya, Indonesia","institution_ids":["https://openalex.org/I4387153613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8721871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"4","first_page":"807","last_page":"818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9961000084877014,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9961000084877014,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.002099999925121665,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0003000000142492354,"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/scientific-article-recommendation","display_name":"scientific article recommendation","score":0.8519999980926514},{"id":"https://openalex.org/keywords/content-based-filtering","display_name":"content-based filtering","score":0.9290000200271606},{"id":"https://openalex.org/keywords/tf-idf","display_name":"TF-IDF","score":0.9100000262260437},{"id":"https://openalex.org/keywords/winnowing","display_name":"winnowing","score":0.8889999985694885},{"id":"https://openalex.org/keywords/hybrid-recommendation","display_name":"hybrid recommendation","score":0.6729999780654907},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"cosine similarity","score":0.703000009059906},{"id":"https://openalex.org/keywords/jaccard-similarity","display_name":"Jaccard similarity","score":0.9990000128746033},{"id":"https://openalex.org/keywords/k-gram","display_name":"k-gram","score":0.6439999938011169}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8644999861717224},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6751999855041504},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6323999762535095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6000999808311462},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5979999899864197},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5077000260353088},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39430001378059387},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3458000123500824},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.15294/sji.v13i4.59181","doi":"https://doi.org/10.15294/sji.v13i4.59181","is_oa":true,"landing_page_url":"https://doi.org/10.15294/sji.v13i4.59181","pdf_url":"https://journal.unnes.ac.id/journals/sji/article/download/59181/12000","source":{"id":"https://openalex.org/S4210171202","display_name":"Scientific Journal of Informatics","issn_l":"2407-7658","issn":["2407-7658","2460-0040"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":"https://openalex.org/P4310315212","host_organization_name":"Jurusan Ilmu Komputer Universitas Negeri Semarang","host_organization_lineage":["https://openalex.org/P4310315212"],"host_organization_lineage_names":["Jurusan Ilmu Komputer Universitas Negeri Semarang"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Journal of Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.15294/sji.v13i4.59181","doi":"https://doi.org/10.15294/sji.v13i4.59181","is_oa":true,"landing_page_url":"https://doi.org/10.15294/sji.v13i4.59181","pdf_url":"https://journal.unnes.ac.id/journals/sji/article/download/59181/12000","source":{"id":"https://openalex.org/S4210171202","display_name":"Scientific Journal of Informatics","issn_l":"2407-7658","issn":["2407-7658","2460-0040"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":"https://openalex.org/P4310315212","host_organization_name":"Jurusan Ilmu Komputer Universitas Negeri Semarang","host_organization_lineage":["https://openalex.org/P4310315212"],"host_organization_lineage_names":["Jurusan Ilmu Komputer Universitas Negeri Semarang"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Journal of Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223962234.pdf","grobid_xml":"https://content.openalex.org/works/W7223962234.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4405425744","https://openalex.org/W4400698163","https://openalex.org/W2584067221","https://openalex.org/W2769778028","https://openalex.org/W4405686306","https://openalex.org/W6912813424","https://openalex.org/W181122678","https://openalex.org/W4206478093","https://openalex.org/W7124944898","https://openalex.org/W7220658188"],"abstract_inverted_index":{"Purpose:":[0],"The":[1,72,113,141,156],"rapid":[2],"growth":[3],"of":[4,62,135,139],"digital":[5],"scientific":[6,27],"publications":[7],"makes":[8],"it":[9],"increasingly":[10],"difficult":[11],"for":[12,26,39,48,188],"researchers":[13],"to":[14],"identify":[15],"relevant":[16],"literature.":[17],"This":[18],"study":[19],"develops":[20],"a":[21,59,131,159,174],"content-based":[22],"filtering":[23],"recommendation":[24],"system":[25],"articles":[28,56,77],"that":[29,163],"fuses":[30],"two":[31],"complementary":[32],"similarity":[33,168],"channels:":[34],"TF-IDF":[35,126],"with":[36,45,103,124,147,169],"Cosine":[37],"Similarity":[38,47],"global":[40],"semantic":[41],"weighting":[42],"and":[43,54,69,90,101,127,137,153,166,185],"Winnowing":[44],"Jaccard":[46],"local":[49,175],"structural":[50],"similarity.":[51],"Methods:":[52],"Query":[53],"corpus":[55,73,177],"pass":[57],"through":[58],"preprocessing":[60],"pipeline":[61],"case":[63],"folding,":[64],"filtering,":[65],"tokenizing,":[66],"stopword":[67],"removal,":[68],"Sastrawi":[70],"stemming.":[71],"contains":[74],"2,059":[75],"scholarly":[76],"from":[78,108],"the":[79,109],"host":[80],"institution.":[81],"A":[82],"systematic":[83],"grid":[84],"search":[85],"over":[86],"K-gram,":[87],"window":[88,120],"size,":[89],"TF-IDF/Winnowing":[91],"weight":[92],"combinations":[93],"was":[94,116],"evaluated":[95],"using":[96,178],"Precision@K,":[97],"Recall@K,":[98],"F1-Score@K,":[99],"MAP,":[100],"NDCG,":[102],"citation-based":[104,179],"ground":[105,180],"truth":[106,181],"derived":[107],"harvested":[110],"metadata.":[111],"Result:":[112],"optimal":[114],"configuration":[115],"K-gram":[117],"=":[118,122],"9,":[119],"size":[121],"6,":[123],"60%":[125],"40%":[128],"Winnowing,":[129],"reaching":[130],"peak":[132],"aggregate":[133],"score":[134],"0.2609":[136],"MAP@20":[138],"0.3091.":[140],"hybrid":[142,161],"approach":[143],"outperformed":[144],"single-method":[145],"baselines,":[146],"positive":[148],"N-gain":[149],"at":[150],"MAP@5,":[151],"MAP@10,":[152],"MAP@20.":[154],"Novelty:":[155],"work":[157],"contributes":[158],"four-method":[160],"recommender":[162],"combines":[164],"TF-IDF-Cosine":[165],"Winnowing-Jaccard":[167],"grid-search-optimized":[170],"weights,":[171],"validated":[172],"on":[173],"institutional":[176],"as":[182],"an":[183],"objective":[184],"reproducible":[186],"proxy":[187],"academic":[189],"relevance.":[190]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-10-28T00:00:00"}
