{"id":"https://openalex.org/W4403564262","doi":"https://doi.org/10.1145/3681780.3697252","title":"Automating Bibliometric Analysis with Sentence Transformers and Retrieval-Augmented Generation (RAG): A Pilot Study in Semantic and Contextual Search for Customized Literature Characterization for High-Impact Urban Research","display_name":"Automating Bibliometric Analysis with Sentence Transformers and Retrieval-Augmented Generation (RAG): A Pilot Study in Semantic and Contextual Search for Customized Literature Characterization for High-Impact Urban Research","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4403564262","doi":"https://doi.org/10.1145/3681780.3697252"},"language":"en","primary_location":{"id":"doi:10.1145/3681780.3697252","doi":"https://doi.org/10.1145/3681780.3697252","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3681780.3697252","pdf_url":null,"source":{"id":"https://openalex.org/S7407120723","display_name":"ACM SIGSPATIAL International Workshop on Advances in Urban-AI (UrbanAI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Urban-AI","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.09090","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018883565","display_name":"Haowen Xu","orcid":"https://orcid.org/0000-0002-2309-9176","observed_orcids":["https://orcid.org/0000-0002-2309-9176"]},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haowen Xu","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0002-2309-9176","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406401","display_name":"Xueping Li","orcid":"https://orcid.org/0000-0003-1990-0159","observed_orcids":["https://orcid.org/0000-0003-1990-0159"]},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xueping Li","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0003-1990-0159","affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049679388","display_name":"Jose Tupayachi","orcid":"https://orcid.org/0000-0001-7334-8444","observed_orcids":["https://orcid.org/0000-0001-7334-8444"]},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose Tupayachi","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0001-7334-8444","affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012830322","display_name":"Jianming Jamie Lian","orcid":"https://orcid.org/0000-0003-1270-5350","observed_orcids":["https://orcid.org/0000-0003-1270-5350"]},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianming Jamie Lian","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0003-1270-5350","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066113226","display_name":"Olufemi A. Omitaomu","orcid":"https://orcid.org/0000-0002-3078-7196","observed_orcids":["https://orcid.org/0000-0002-3078-7196"]},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olufemi A. Omitaomu","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0002-3078-7196","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.826,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.99475471,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10102","display_name":"scientometrics and bibliometrics research","score":0.9628999829292297,"subfield":{"id":"https://openalex.org/subfields/3309","display_name":"Library and Information Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10102","display_name":"scientometrics and bibliometrics research","score":0.9628999829292297,"subfield":{"id":"https://openalex.org/subfields/3309","display_name":"Library and Information Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.01979999989271164,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sentence-transformers","display_name":"Sentence Transformers","score":0.6909999847412109},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9919999837875366},{"id":"https://openalex.org/keywords/semantic-search","display_name":"semantic search","score":0.7639999985694885},{"id":"https://openalex.org/keywords/context-aware-information-retrieval","display_name":"context-aware retrieval","score":0.7179999947547913},{"id":"https://openalex.org/keywords/urban-science","display_name":"urban science","score":0.6650000214576721},{"id":"https://openalex.org/keywords/topic-ranking","display_name":"topic ranking","score":0.8420000076293945},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.6779999732971191},{"id":"https://openalex.org/keywords/vector-databases","display_name":"vector databases","score":0.6990000009536743},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9359999895095825},{"id":"https://openalex.org/keywords/research-evaluation","display_name":"research evaluation","score":0.6859999895095825},{"id":"https://openalex.org/keywords/nature-communication","display_name":"nature communication","score":0.6779999732971191},{"id":"https://openalex.org/keywords/high-impact-journals","display_name":"high-impact journals","score":0.7689999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721683382987976},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5525189638137817},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5090474486351013},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49052828550338745},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.48108670115470886},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4657972753047943},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4396592378616333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3309032917022705},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11696738004684448},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09911805391311646},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3681780.3697252","doi":"https://doi.org/10.1145/3681780.3697252","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3681780.3697252","pdf_url":null,"source":{"id":"https://openalex.org/S7407120723","display_name":"ACM SIGSPATIAL International Workshop on Advances in Urban-AI (UrbanAI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Urban-AI","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.09090","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09090","pdf_url":"https://arxiv.org/pdf/2410.09090","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.09090","doi":"https://doi.org/10.48550/arxiv.2410.09090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.09090","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.09090","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09090","pdf_url":"https://arxiv.org/pdf/2410.09090","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.7628999948501587,"display_name":"Sustainable cities and communities"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G3759531448","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320332276","display_name":"Advanced Research Projects Agency - Energy","ror":"https://ror.org/03q1rgc19"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403564262.pdf","grobid_xml":"https://content.openalex.org/works/W4403564262.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2915118509","https://openalex.org/W2948852192","https://openalex.org/W2954472560","https://openalex.org/W2989886696","https://openalex.org/W3046572078","https://openalex.org/W3115886087","https://openalex.org/W3160856016","https://openalex.org/W4307154772","https://openalex.org/W4308441536","https://openalex.org/W4392067260","https://openalex.org/W4393065402","https://openalex.org/W4402243741","https://openalex.org/W4402372906","https://openalex.org/W4403371192","https://openalex.org/W4403555373"],"related_works":["https://openalex.org/W4406847525","https://openalex.org/W7108247739","https://openalex.org/W7170513555","https://openalex.org/W7172396632","https://openalex.org/W4394892508","https://openalex.org/W4391707094","https://openalex.org/W7214727382","https://openalex.org/W7154731530","https://openalex.org/W7114798498","https://openalex.org/W4415952415"],"abstract_inverted_index":{"Bibliometric":[0],"analysis":[1,175],"is":[2],"essential":[3],"for":[4,172,190],"understanding":[5],"research":[6,123,192],"trends,":[7],"scope,":[8,158],"and":[9,28,54,63,80,86,109,120,159,176,194],"impact":[10],"in":[11,15,41,60,137,150,163,179],"urban":[12,133,180],"science,":[13],"especially":[14],"high-impact":[16,164],"journals,":[17],"such":[18],"Nature":[19,138],"Portfolios.":[20],"However,":[21],"traditional":[22],"methods,":[23],"relying":[24],"on":[25,155],"keyword":[26],"searches":[27,53],"basic":[29],"NLP":[30],"techniques,":[31],"often":[32],"fail":[33],"to":[34,50,84,114],"uncover":[35],"valuable":[36],"insights":[37],"not":[38],"explicitly":[39],"stated":[40],"article":[42],"titles":[43],"or":[44],"keywords.":[45],"These":[46],"approaches":[47],"are":[48],"unable":[49],"perform":[51],"semantic":[52],"contextual":[55,116],"understanding,":[56],"limiting":[57],"their":[58],"effectiveness":[59,146],"classifying":[61],"topics":[62],"characterizing":[64],"studies.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"address":[70],"these":[71],"limitations":[72],"by":[73],"leveraging":[74],"Generative":[75],"AI":[76,184],"models,":[77],"specifically":[78],"transformers":[79],"Retrieval-Augmented":[81],"Generation":[82],"(RAG),":[83],"automate":[85],"enhance":[87],"bibliometric":[88,174],"analysis.":[89],"We":[90],"developed":[91],"a":[92,97,102,169,187],"technical":[93],"workflow":[94],"that":[95],"integrates":[96],"vector":[98],"database,":[99],"Sentence":[100],"Transformers,":[101],"Gaussian":[103],"Mixture":[104],"Model":[105],"(GMM),":[106],"Retrieval":[107],"Agent,":[108],"Large":[110],"Language":[111],"Models":[112],"(LLMs)":[113],"enable":[115],"search,":[117],"topic":[118],"ranking,":[119],"characterization":[121],"of":[122,147,161],"using":[124],"customized":[125],"prompt":[126],"templates.":[127],"A":[128],"pilot":[129],"study":[130,167],"analyzing":[131],"223":[132],"science-related":[134],"articles":[135],"published":[136],"Communications":[139],"over":[140],"the":[141,145,156],"past":[142],"decade":[143],"highlights":[144],"our":[148],"approach":[149],"generating":[151],"insightful":[152],"summary":[153],"statistics":[154],"quality,":[157],"characteristics":[160],"papers":[162],"journals.":[165],"This":[166],"introduces":[168],"new":[170],"paradigm":[171],"enhancing":[173],"knowledge":[177],"retrieval":[178],"research,":[181],"positioning":[182],"an":[183],"agent":[185],"as":[186],"powerful":[188],"tool":[189],"advancing":[191],"evaluation":[193],"understanding.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-10-20T00:00:00"}