{"id":"https://openalex.org/W7223671468","doi":"https://doi.org/10.1007/s44564-026-00032-z","title":"Extractive summarization of Indonesian friday sermons using fine-tuned IndoBERT and pseudo-labeled data","display_name":"Extractive summarization of Indonesian friday sermons using fine-tuned IndoBERT and pseudo-labeled data","publication_year":2026,"publication_date":"2026-10-26","ids":{"openalex":"https://openalex.org/W7223671468","doi":"https://doi.org/10.1007/s44564-026-00032-z"},"language":"en","primary_location":{"id":"doi:10.1007/s44564-026-00032-z","doi":"https://doi.org/10.1007/s44564-026-00032-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44564-026-00032-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44564-026-00032-z.pdf","source":{"id":"https://openalex.org/S7407058843","display_name":"Discover Informatics","issn_l":"3005-1754","issn":["3005-1754"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Informatics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s44564-026-00032-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129508877","display_name":"Siti Annisa Rahmiasari","orcid":"https://orcid.org/0009-0006-8925-848X","observed_orcids":["https://orcid.org/0009-0006-8925-848X"]},"institutions":[{"id":"https://openalex.org/I3020190299","display_name":"Universitas Islam Negeri Maulana Malik Ibrahim","ror":"https://ror.org/03a8hhw69","country_code":"ID","type":"education","lineage":["https://openalex.org/I3020190299"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Siti Annisa Rahmiasari","raw_affiliation_strings":["Department of Informatics Engineering, Universitas Islam Negeri Maulana Malik Ibrahim Malang, Malang, Indonesia"],"raw_orcid":"https://orcid.org/0009-0006-8925-848X","affiliations":[{"raw_affiliation_string":"Department of Informatics Engineering, Universitas Islam Negeri Maulana Malik Ibrahim Malang, Malang, Indonesia","institution_ids":["https://openalex.org/I3020190299"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611449","display_name":"Supriyono Supriyono","orcid":"https://orcid.org/0000-0002-4733-9189","observed_orcids":["https://orcid.org/0000-0002-4733-9189"]},"institutions":[{"id":"https://openalex.org/I3020190299","display_name":"Universitas Islam Negeri Maulana Malik Ibrahim","ror":"https://ror.org/03a8hhw69","country_code":"ID","type":"education","lineage":["https://openalex.org/I3020190299"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Supriyono","raw_affiliation_strings":["Department of Informatics Engineering, Universitas Islam Negeri Maulana Malik Ibrahim Malang, Malang, Indonesia"],"raw_orcid":"https://orcid.org/0000-0002-4733-9189","affiliations":[{"raw_affiliation_string":"Department of Informatics Engineering, Universitas Islam Negeri Maulana Malik Ibrahim Malang, Malang, Indonesia","institution_ids":["https://openalex.org/I3020190299"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028024788","display_name":"Okta Qomaruddin Azis","orcid":"https://orcid.org/0000-0003-4530-246X","observed_orcids":["https://orcid.org/0000-0003-4530-246X"]},"institutions":[{"id":"https://openalex.org/I3020190299","display_name":"Universitas Islam Negeri Maulana Malik Ibrahim","ror":"https://ror.org/03a8hhw69","country_code":"ID","type":"education","lineage":["https://openalex.org/I3020190299"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Okta Qomaruddin Aziz","raw_affiliation_strings":["Department of Informatics Engineering, Universitas Islam Negeri Maulana Malik Ibrahim Malang, Malang, Indonesia"],"raw_orcid":"https://orcid.org/0000-0003-4530-246X","affiliations":[{"raw_affiliation_string":"Department of Informatics Engineering, Universitas Islam Negeri Maulana Malik Ibrahim Malang, Malang, Indonesia","institution_ids":["https://openalex.org/I3020190299"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100611449"],"corresponding_institution_ids":["https://openalex.org/I3020190299"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7986879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.8359000086784363,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.8359000086784363,"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/T10028","display_name":"Topic Modeling","score":0.15710000693798065,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.00139999995008111,"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/extractive-summarization","display_name":"extractive summarization","score":0.9660000205039978},{"id":"https://openalex.org/keywords/friday-sermon","display_name":"Friday sermon","score":0.8330000042915344},{"id":"https://openalex.org/keywords/indobert","display_name":"IndoBERT","score":0.8539999723434448},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.9750000238418579},{"id":"https://openalex.org/keywords/sentence-level-classification","display_name":"sentence-level classification","score":0.8420000076293945},{"id":"https://openalex.org/keywords/islamic-terminology","display_name":"Islamic terminology","score":0.5920000076293945},{"id":"https://openalex.org/keywords/low-resource-summarization","display_name":"low-resource summarization","score":0.8240000009536743}],"concepts":[{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.816100001335144},{"id":"https://openalex.org/C2778266495","wikidata":"https://www.wikidata.org/wiki/Q60797","display_name":"Sermon","level":2,"score":0.7807000279426575},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7799000144004822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6083999872207642},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5985999703407288},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5824000239372253},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5090000033378601},{"id":"https://openalex.org/C4445939","wikidata":"https://www.wikidata.org/wiki/Q432","display_name":"Islam","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496000111103058},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.361299991607666},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C90464235","wikidata":"https://www.wikidata.org/wiki/Q1051521","display_name":"Discourse marker","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C3018023364","wikidata":"https://www.wikidata.org/wiki/Q425265","display_name":"Significant difference","level":2,"score":0.26969999074935913}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s44564-026-00032-z","doi":"https://doi.org/10.1007/s44564-026-00032-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44564-026-00032-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44564-026-00032-z.pdf","source":{"id":"https://openalex.org/S7407058843","display_name":"Discover Informatics","issn_l":"3005-1754","issn":["3005-1754"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s44564-026-00032-z","doi":"https://doi.org/10.1007/s44564-026-00032-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44564-026-00032-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44564-026-00032-z.pdf","source":{"id":"https://openalex.org/S7407058843","display_name":"Discover Informatics","issn_l":"3005-1754","issn":["3005-1754"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223671468.pdf","grobid_xml":"https://content.openalex.org/works/W7223671468.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1972393702","https://openalex.org/W1983897914","https://openalex.org/W2110693578","https://openalex.org/W2626778328","https://openalex.org/W2798812533","https://openalex.org/W2897803242","https://openalex.org/W2913946806","https://openalex.org/W2924690340","https://openalex.org/W2936695845","https://openalex.org/W2950813464","https://openalex.org/W2952638691","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2970419734","https://openalex.org/W2975059944","https://openalex.org/W2981852735","https://openalex.org/W2982399380","https://openalex.org/W2983040767","https://openalex.org/W2996264288","https://openalex.org/W3007955273","https://openalex.org/W3015468748","https://openalex.org/W3027042170","https://openalex.org/W3033544963","https://openalex.org/W3034199299","https://openalex.org/W3042185737","https://openalex.org/W3045321166","https://openalex.org/W3110604908","https://openalex.org/W3116295307","https://openalex.org/W3116407756","https://openalex.org/W3153266325","https://openalex.org/W4311183537","https://openalex.org/W4321108071","https://openalex.org/W4382202377","https://openalex.org/W4385231981","https://openalex.org/W4388441035","https://openalex.org/W4391382439","https://openalex.org/W4392488514","https://openalex.org/W4402054436","https://openalex.org/W4403903472","https://openalex.org/W4409258338","https://openalex.org/W4411112932","https://openalex.org/W4412879239","https://openalex.org/W4413779719","https://openalex.org/W4415589242","https://openalex.org/W4415971943","https://openalex.org/W7128429023","https://openalex.org/W7136147855"],"related_works":["https://openalex.org/W7118585892","https://openalex.org/W7125612360","https://openalex.org/W7124928754","https://openalex.org/W7220859105","https://openalex.org/W7171298010","https://openalex.org/W3110604908","https://openalex.org/W2953480105","https://openalex.org/W4415589242","https://openalex.org/W3170450402","https://openalex.org/W2795571207"],"abstract_inverted_index":{"Abstract":[0],"Automatic":[1],"text":[2],"summarization":[3,37,256,277],"of":[4,57,139,211,257],"Indonesian":[5,40,258],"religious":[6,259],"content,":[7],"particularly":[8],"Friday":[9,41],"sermon":[10,42,231,276],"(Khutbah":[11],"Jumat)":[12],"transcripts,":[13],"remains":[14],"underexplored.":[15],"These":[16],"transcripts":[17,43,61],"contain":[18],"long-form":[19],"spoken":[20],"discourse":[21],"and":[22,82,94,104,125,158,269],"domain-specific":[23],"Islamic":[24,83],"terminology,":[25],"making":[26],"manual":[27],"review":[28],"time-consuming.":[29],"This":[30],"study":[31],"aims":[32],"to":[33,92,153],"develop":[34],"an":[35,96],"extractive":[36,255],"framework":[38,273],"for":[39,52,193,254,274,287],"using":[44,102],"a":[45,133,250,271],"pseudo-labeling":[46,248],"pipeline":[47],"combined":[48],"with":[49,99,263],"fine-tuning":[50],"IndoBERT":[51,168,262],"sentence-level":[53],"classification.":[54],"A":[55],"corpus":[56],"210":[58],"Khutbah":[59],"Jumat":[60],"from":[62],"the":[63,137,229,285],"YouTube":[64],"subset":[65],"was":[66],"preprocessed,":[67],"producing":[68],"approximately":[69],"293,000":[70],"words.":[71],"Sentence-level":[72],"pseudo-labels":[73],"were":[74,89],"generated":[75],"by":[76],"combining":[77],"TF-IDF":[78],"relevance,":[79],"sentence":[80,267],"position,":[81],"keyword":[84],"density.":[85],"The":[86,107,244],"pseudo-labeled":[87,264],"sentences":[88],"then":[90],"used":[91],"train":[93],"evaluate":[95],"IndoBERT-based":[97],"classifier,":[98],"performance":[100],"assessed":[101],"ROUGE":[103],"BERTScore":[105,166],"metrics.":[106],"proposed":[108],"system":[109],"effectively":[110],"selected":[111],"summary-worthy":[112],"sentences,":[113],"achieving":[114],"ROUGE-1":[115,227],"=":[116,123,127,236,239],"0.5181":[117],"(95%":[118],"bootstrap":[119,148],"CI":[120],"0.460\u20130.575),":[121],"ROUGE-2":[122],"0.4273,":[124],"ROUGE-L":[126],"0.4400":[128],"against":[129,214],"pseudo-reference":[130],"summaries":[131,190],"on":[132,143],"21-document":[134],"test":[135],"set,":[136],"highest":[138],"all":[140],"evaluated":[141],"methods":[142,206],"these":[144,151,196],"three":[145],"metrics;":[146],"paired":[147],"comparisons":[149,203],"showed":[150],"gains":[152,177],"be":[154,199],"consistent":[155],"over":[156,163],"TextRank":[157],"generic":[159],"BERTSum":[160,172],"but":[161],"not":[162,179,283],"TF-IDF.":[164],"On":[165],"F1,":[167],"(0.7310)":[169],"remained":[170],"below":[171],"(0.7407),":[173],"indicating":[174],"that":[175,247,278],"lexical-overlap":[176],"did":[178],"consistently":[180],"translate":[181],"into":[182],"greater":[183],"semantic":[184],"similarity.":[185],"As":[186],"no":[187,222],"human-written":[188],"gold-standard":[189],"currently":[191],"exist":[192],"this":[194],"domain,":[195],"scores":[197],"should":[198],"interpreted":[200],"as":[201],"relative":[202],"among":[204],"automatic":[205,275],"rather":[207],"than":[208],"validated":[209],"measures":[210],"summary":[212],"quality":[213],"human":[215],"judgment.":[216],"An":[217],"exploratory":[218],"topic-wise":[219],"analysis":[220],"found":[221],"statistically":[223],"significant":[224],"difference":[225],"in":[226],"across":[228],"five":[230],"topic":[232],"categories":[233],"(Kruskal\u2013Wallis":[234],"p":[235],"0.11;":[237],"n":[238],"3\u20137":[240],"documents":[241],"per":[242],"topic).":[243],"findings":[245],"suggest":[246],"provides":[249],"practical":[251],"low-resource":[252],"strategy":[253],"discourse.":[260],"Fine-tuning":[261],"data":[265],"improves":[266],"selection":[268],"offers":[270],"scalable":[272],"substantially":[279],"reduces,":[280],"though":[281],"does":[282],"eliminate,":[284],"need":[286],"human-annotated":[288],"reference":[289],"summaries.":[290]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-10-27T00:00:00"}
