{"id":"https://openalex.org/W7154733313","doi":"https://doi.org/10.1109/iwcia68353.2025.11479785","title":"Comparative Performance Evaluation of Large Language Models for Domain-Specific Web Content Extraction","display_name":"Comparative Performance Evaluation of Large Language Models for Domain-Specific Web Content Extraction","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7154733313","doi":"https://doi.org/10.1109/iwcia68353.2025.11479785"},"language":null,"primary_location":{"id":"doi:10.1109/iwcia68353.2025.11479785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcia68353.2025.11479785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 14th International Workshop on Computational Intelligence and Applications (IWCIA)","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/A5133860589","display_name":"Hendrik Hendrik","orcid":null},"institutions":[{"id":"https://openalex.org/I165230279","display_name":"Universitas Gadjah Mada","ror":"https://ror.org/03ke6d638","country_code":"ID","type":"education","lineage":["https://openalex.org/I165230279"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Hendrik Hendrik","raw_affiliation_strings":["Universitas Gadjah Mada,Department of Electrical and Information Engineering,Yogyakarta,Indonesia"],"affiliations":[{"raw_affiliation_string":"Universitas Gadjah Mada,Department of Electrical and Information Engineering,Yogyakarta,Indonesia","institution_ids":["https://openalex.org/I165230279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108644292","display_name":"Silmi Fauziati","orcid":null},"institutions":[{"id":"https://openalex.org/I165230279","display_name":"Universitas Gadjah Mada","ror":"https://ror.org/03ke6d638","country_code":"ID","type":"education","lineage":["https://openalex.org/I165230279"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Silmi Fauziati","raw_affiliation_strings":["Universitas Gadjah Mada,Department of Electrical and Information Engineering,Yogyakarta,Indonesia"],"affiliations":[{"raw_affiliation_string":"Universitas Gadjah Mada,Department of Electrical and Information Engineering,Yogyakarta,Indonesia","institution_ids":["https://openalex.org/I165230279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133873232","display_name":"Adhistya Erna Permanasari","orcid":null},"institutions":[{"id":"https://openalex.org/I165230279","display_name":"Universitas Gadjah Mada","ror":"https://ror.org/03ke6d638","country_code":"ID","type":"education","lineage":["https://openalex.org/I165230279"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Adhistya Erna Permanasari","raw_affiliation_strings":["Universitas Gadjah Mada,Department of Electrical and Information Engineering,Yogyakarta,Indonesia"],"affiliations":[{"raw_affiliation_string":"Universitas Gadjah Mada,Department of Electrical and Information Engineering,Yogyakarta,Indonesia","institution_ids":["https://openalex.org/I165230279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5133860589"],"corresponding_institution_ids":["https://openalex.org/I165230279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86956817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.24570000171661377,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.24570000171661377,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.14090000092983246,"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":0.09839999675750732,"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/language-model","display_name":"Language model","score":0.3831999897956848},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.36070001125335693},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.34950000047683716},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3027999997138977},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.29649999737739563},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.29490000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.73089998960495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5160999894142151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46950000524520874},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwcia68353.2025.11479785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcia68353.2025.11479785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 14th International Workshop on Computational Intelligence and Applications (IWCIA)","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":10,"referenced_works":["https://openalex.org/W2306453302","https://openalex.org/W2810875861","https://openalex.org/W3141376096","https://openalex.org/W4391894867","https://openalex.org/W4391973028","https://openalex.org/W4401042020","https://openalex.org/W4402671712","https://openalex.org/W4409676182","https://openalex.org/W4412627716","https://openalex.org/W4412645251"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,28,48],"comparative":[4],"evaluation":[5,53],"of":[6,165],"seven":[7],"Large":[8],"Language":[9],"Models":[10],"(LLMs)":[11],"for":[12,140,154],"domain-specific":[13,144],"web":[14],"content":[15],"extraction,":[16],"addressing":[17],"the":[18,91,162],"gap":[19],"in":[20,143,168],"performance":[21,83,93,135],"assessment":[22],"across":[23,67,109],"model":[24,86,129],"families.":[25],"We":[26],"developed":[27],"web-based":[29],"extraction":[30,56,117,145,158],"tool":[31],"supporting":[32],"multiple":[33],"LLM":[34,141,166],"providers":[35],"(OpenAI,":[36],"Anthropic,":[37],"Google,":[38],"DeepSeek)":[39],"and":[40,63,76,100,136],"evaluated":[41],"their":[42],"capabilities":[43,167],"using":[44],"halal":[45,70],"tourism":[46,71],"as":[47],"case":[49],"study":[50,126],"domain.":[51],"Our":[52,147],"framework":[54],"assessed":[55],"quality":[57],"through":[58],"precision,":[59],"recall,":[60],"F1-score,":[61],"accuracy,":[62],"processing":[64],"time":[65],"metrics":[66],"three":[68],"Japanese":[69],"websites,":[72],"focusing":[73],"on":[74],"restaurant":[75],"mosque":[77],"entity":[78],"extraction.":[79],"Results":[80],"reveal":[81],"significant":[82],"variations":[84],"among":[85],"families,":[87],"with":[88,119,151],"GPT-4o-mini":[89],"achieving":[90],"highest":[92],"(F1-score:":[94],"0.973)":[95],"while":[96,112],"maintaining":[97],"exceptional":[98],"stability":[99],"computational":[101],"efficiency.":[102],"OpenAI":[103],"models":[104,114],"consistently":[105],"outperformed":[106],"other":[107],"families":[108],"all":[110],"metrics,":[111],"Anthropic":[113],"exhibited":[115],"conservative":[116],"behavior":[118],"high":[120],"precision":[121],"but":[122],"lower":[123],"recall.":[124],"The":[125],"demonstrates":[127],"that":[128],"size":[130],"does":[131],"not":[132],"guarantee":[133],"superior":[134],"establishes":[137],"evidence-based":[138],"guidelines":[139],"selection":[142],"tasks.":[146],"findings":[148],"provide":[149],"practitioners":[150],"actionable":[152],"insights":[153],"implementing":[155],"robust":[156],"knowledge":[157],"systems,":[159],"contributing":[160],"to":[161],"broader":[163],"understanding":[164],"specialized":[169],"applications.":[170]},"counts_by_year":[],"updated_date":"2026-04-19T06:08:04.723047","created_date":"2026-04-18T00:00:00"}