{"id":"https://openalex.org/W4409888796","doi":"https://doi.org/10.3390/fi17050195","title":"An Improved Reference Paper Collection System Using Web Scraping with Three Enhancements","display_name":"An Improved Reference Paper Collection System Using Web Scraping with Three Enhancements","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4409888796","doi":"https://doi.org/10.3390/fi17050195"},"language":"en","primary_location":{"id":"doi:10.3390/fi17050195","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi17050195","pdf_url":null,"source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/fi17050195","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027897953","display_name":"Tresna Maulana Fahrudin","orcid":"https://orcid.org/0000-0002-9895-2442"},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tresna Maulana Fahrudin","raw_affiliation_strings":["Department of Information and Communication Systems, Okayama University, Okayama 700-8530, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9895-2442","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Systems, Okayama University, Okayama 700-8530, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057610115","display_name":"Nobuo Funabiki","orcid":"https://orcid.org/0000-0003-3234-3473"},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Nobuo Funabiki","raw_affiliation_strings":["Department of Information and Communication Systems, Okayama University, Okayama 700-8530, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Systems, Okayama University, Okayama 700-8530, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008159036","display_name":"Komang Candra Brata","orcid":"https://orcid.org/0000-0003-2896-6686"},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]},{"id":"https://openalex.org/I177055848","display_name":"University of Brawijaya","ror":"https://ror.org/01wk3d929","country_code":"ID","type":"education","lineage":["https://openalex.org/I177055848"]}],"countries":["ID","JP"],"is_corresponding":false,"raw_author_name":"Komang Candra Brata","raw_affiliation_strings":["Department of Informatics Engineering, Universitas Brawijaya, Malang 65145, Indonesia","Department of Information and Communication Systems, Okayama University, Okayama 700-8530, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2896-6686","affiliations":[{"raw_affiliation_string":"Department of Informatics Engineering, Universitas Brawijaya, Malang 65145, Indonesia","institution_ids":["https://openalex.org/I177055848"]},{"raw_affiliation_string":"Department of Information and Communication Systems, Okayama University, Okayama 700-8530, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093273999","display_name":"Inzali Naing","orcid":null},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Inzali Naing","raw_affiliation_strings":["Department of Information and Communication Systems, Okayama University, Okayama 700-8530, Japan"],"raw_orcid":"https://orcid.org/0009-0006-4395-4164","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Systems, Okayama University, Okayama 700-8530, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012730159","display_name":"Soe Thandar Aung","orcid":"https://orcid.org/0009-0009-4598-0878"},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Soe Thandar Aung","raw_affiliation_strings":["Department of Information and Communication Systems, Okayama University, Okayama 700-8530, Japan"],"raw_orcid":"https://orcid.org/0009-0009-4598-0878","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Systems, Okayama University, Okayama 700-8530, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037017095","display_name":"Amri Muhaimin","orcid":"https://orcid.org/0009-0004-4161-8277"},"institutions":[{"id":"https://openalex.org/I3130997290","display_name":"University of Pembangunan Nasional Veteran Jawa Timur","ror":"https://ror.org/05sbm1c04","country_code":"ID","type":"education","lineage":["https://openalex.org/I3130997290"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Amri Muhaimin","raw_affiliation_strings":["Department of Data Science, Universitas Pembangunan Nasional Veteran Jawa Timur, Surabaya 60294, Indonesia"],"raw_orcid":"https://orcid.org/0009-0004-4161-8277","affiliations":[{"raw_affiliation_string":"Department of Data Science, Universitas Pembangunan Nasional Veteran Jawa Timur, Surabaya 60294, Indonesia","institution_ids":["https://openalex.org/I3130997290"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047200624","display_name":"Dwi Arman Prasetya","orcid":"https://orcid.org/0000-0003-0281-9928"},"institutions":[{"id":"https://openalex.org/I3130997290","display_name":"University of Pembangunan Nasional Veteran Jawa Timur","ror":"https://ror.org/05sbm1c04","country_code":"ID","type":"education","lineage":["https://openalex.org/I3130997290"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dwi Arman Prasetya","raw_affiliation_strings":["Department of Data Science, Universitas Pembangunan Nasional Veteran Jawa Timur, Surabaya 60294, Indonesia"],"raw_orcid":"https://orcid.org/0000-0003-0281-9928","affiliations":[{"raw_affiliation_string":"Department of Data Science, Universitas Pembangunan Nasional Veteran Jawa Timur, Surabaya 60294, Indonesia","institution_ids":["https://openalex.org/I3130997290"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057610115"],"corresponding_institution_ids":["https://openalex.org/I163770644"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":10.5771,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97862851,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"17","issue":"5","first_page":"195","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14025","display_name":"Educational Technology and Assessment","score":0.9821000099182129,"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/T14025","display_name":"Educational Technology and Assessment","score":0.9821000099182129,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9800999760627747,"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/T12171","display_name":"Open Education and E-Learning","score":0.9697999954223633,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8984271287918091},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.4578399360179901},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4204271733760834},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40635576844215393},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3627430200576782},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32559216022491455},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13473156094551086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8984271287918091},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4578399360179901},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4204271733760834},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40635576844215393},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3627430200576782},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32559216022491455},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13473156094551086},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/fi17050195","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi17050195","pdf_url":null,"source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jftint:v:17:y:2025:i:5:p:195-:d:1644623","is_oa":false,"landing_page_url":"https://www.mdpi.com/1999-5903/17/5/195/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:7d54792838ba4bd590557b122eef142d","is_oa":true,"landing_page_url":"https://doaj.org/article/7d54792838ba4bd590557b122eef142d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet, Vol 17, Iss 5, p 195 (2025)","raw_type":"article"},{"id":"pmh:oai:irdb.nii.ac.jp:01081:0006991443","is_oa":true,"landing_page_url":"https://ousar.lib.okayama-u.ac.jp/69414","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.3390/fi17050195","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi17050195","pdf_url":null,"source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1005483714","https://openalex.org/W2137922070","https://openalex.org/W2156788195","https://openalex.org/W2308149712","https://openalex.org/W2583041915","https://openalex.org/W2589809526","https://openalex.org/W2613301987","https://openalex.org/W2761760240","https://openalex.org/W2907013361","https://openalex.org/W2919190028","https://openalex.org/W2926822960","https://openalex.org/W2942201226","https://openalex.org/W2978352415","https://openalex.org/W3044444100","https://openalex.org/W3092327201","https://openalex.org/W3109328874","https://openalex.org/W4243798656","https://openalex.org/W4293088923","https://openalex.org/W4296369136","https://openalex.org/W4297751839","https://openalex.org/W4303426887","https://openalex.org/W4311156511","https://openalex.org/W4313022622","https://openalex.org/W4313523485","https://openalex.org/W4315486790","https://openalex.org/W4319915133","https://openalex.org/W4376602130","https://openalex.org/W4379768223","https://openalex.org/W4387696594","https://openalex.org/W4391133530","https://openalex.org/W4392057301","https://openalex.org/W4398768029","https://openalex.org/W4400485122","https://openalex.org/W4400798787","https://openalex.org/W4401387932","https://openalex.org/W4401887978","https://openalex.org/W4403048625","https://openalex.org/W4406592933","https://openalex.org/W6679769357","https://openalex.org/W6697460127","https://openalex.org/W6757294788","https://openalex.org/W6761901797","https://openalex.org/W6848750459","https://openalex.org/W6849052576"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2186048469","https://openalex.org/W3029267192","https://openalex.org/W1967509846","https://openalex.org/W4308662946","https://openalex.org/W2941073738","https://openalex.org/W2003932708","https://openalex.org/W1967424056","https://openalex.org/W2284877871","https://openalex.org/W2138102289"],"abstract_inverted_index":{"Nowadays,":[0],"accessibility":[1],"to":[2,114,155,195,256],"academic":[3],"papers":[4,77,211,244],"has":[5,18,26,276],"been":[6,277],"significantly":[7],"improved":[8,106],"with":[9,111,181,192],"electric":[10],"publications":[11],"on":[12,85,92,163,199,253],"the":[13,22,119,128,133,137,142,146,152,161,206,213,217,236,239,249,270,273],"internet,":[14],"where":[15],"open":[16],"access":[17],"become":[19],"common.":[20],"At":[21],"same":[23],"time,":[24,81],"it":[25,83],"increased":[27],"workloads":[28],"in":[29,132,141,151,227,266,279],"literature":[30,224,263],"surveys":[31],"for":[32,166,184],"researchers":[33],"who":[34],"usually":[35],"manually":[36],"download":[37],"PDF":[38,188],"files":[39],"and":[40,61,90,145,148,169,178,212,222,247],"check":[41],"their":[42],"contents.":[43],"To":[44],"solve":[45,115],"this":[46,101],"drawback,":[47],"we":[48,103,204],"have":[49],"proposed":[50,274],"a":[51,57,71,93,97],"reference":[52,76,107,210,229,243,267],"paper":[53,87,108,123,230],"collection":[54,109],"system":[55,68,110,275],"using":[56],"web":[58,125],"scraping":[59],"technology":[60],"natural":[62],"language":[63],"models.":[64],"However,":[65],"our":[66,219,257,280],"previous":[67,220,258],"often":[69],"finds":[70],"limited":[72],"number":[73,207,240],"of":[74,187,208,241,272],"relevant":[75,242],"after":[78],"taking":[79],"long":[80],"since":[82],"relies":[84],"one":[86],"search":[88,124,130,139,147,225,264],"website":[89],"runs":[91],"single":[94],"thread":[95],"at":[96],"multi-core":[98,167],"CPU.":[99],"In":[100],"paper,":[102],"present":[104],"an":[105],"three":[112],"enhancements":[113],"them:":[116],"(1)":[117],"integrating":[118],"APIs":[120],"from":[121],"multiple":[122,164],"sites,":[126],"namely,":[127],"bulk":[129],"endpoint":[131,140,150],"Semantic":[134],"Scholar":[135],"API,":[136,144],"article":[138,157],"DOAJ":[143],"fetch":[149],"PubMed":[153],"API":[154],"retrieve":[156],"metadata,":[158],"(2)":[159],"running":[160],"program":[162],"threads":[165],"CPU,":[168],"(3)":[170],"implementing":[171],"Dynamic":[172],"URL":[173,176,182],"Redirection,":[174],"Regex-based":[175],"Parsing,":[177],"HTML":[179],"Scraping":[180],"Extraction":[183],"fast":[185],"checking":[186],"file":[189],"accessibility,":[190],"along":[191],"sentence":[193],"embedding":[194],"assess":[196],"relevance":[197],"based":[198],"semantic":[200],"similarity.":[201],"For":[202],"evaluations,":[203],"compare":[205],"obtained":[209],"response":[214],"time":[215,250],"between":[216],"proposal,":[218],"work,":[221,259],"common":[223,262],"tools":[226,265],"five":[228],"queries.":[231],"The":[232],"results":[233],"show":[234],"that":[235],"proposal":[237],"increases":[238],"by":[245,251],"64.38%":[246],"reduces":[248],"59.78%":[252],"average":[254],"compared":[255],"while":[260],"outperforming":[261],"papers.":[268],"Thus,":[269],"effectiveness":[271],"demonstrated":[278],"experiments.":[281]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}
