{"id":"https://openalex.org/W4408566262","doi":"https://doi.org/10.1109/icdmw65004.2024.00061","title":"Automating Maritime Risk Data Collection and Identification Leveraging Large Language Models","display_name":"Automating Maritime Risk Data Collection and Identification Leveraging Large Language Models","publication_year":2024,"publication_date":"2024-12-09","ids":{"openalex":"https://openalex.org/W4408566262","doi":"https://doi.org/10.1109/icdmw65004.2024.00061"},"language":"en","primary_location":{"id":"doi:10.1109/icdmw65004.2024.00061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw65004.2024.00061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Data Mining Workshops (ICDMW)","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/A5068938035","display_name":"Donghao Huang","orcid":"https://orcid.org/0009-0005-6767-4872"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Donghao Huang","raw_affiliation_strings":["Singapore Management University,School of Computing and Information Systems,Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information Systems,Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071407415","display_name":"Xiuju Fu","orcid":"https://orcid.org/0000-0002-6673-1098"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiuju Fu","raw_affiliation_strings":["Agency for Science, Technology and Research,Institute of High Performance Computing,Singapore"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research,Institute of High Performance Computing,Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698875","display_name":"Xiaofeng Yin","orcid":"https://orcid.org/0000-0003-1152-8890"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaofeng Yin","raw_affiliation_strings":["Agency for Science, Technology and Research,Institute of High Performance Computing,Singapore"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research,Institute of High Performance Computing,Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062463768","display_name":"Haibo Pen","orcid":"https://orcid.org/0000-0002-5361-8344"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Pen","raw_affiliation_strings":["Tianjin University,School of Electrical and Information Engineering,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,School of Electrical and Information Engineering,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003218042","display_name":"Zhaoxia Wang","orcid":"https://orcid.org/0000-0001-7674-5488"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhaoxia Wang","raw_affiliation_strings":["Singapore Management University,School of Computing and Information Systems,Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information Systems,Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068938035"],"corresponding_institution_ids":["https://openalex.org/I79891267"],"apc_list":null,"apc_paid":null,"fwci":1.4014,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8131231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"433","last_page":"439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11622","display_name":"Maritime Navigation and Safety","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11622","display_name":"Maritime Navigation and Safety","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7451157569885254},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6426762342453003},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.45848721265792847},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.44014447927474976},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3983858823776245},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33017098903656006},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23756781220436096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7451157569885254},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6426762342453003},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.45848721265792847},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.44014447927474976},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3983858823776245},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33017098903656006},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23756781220436096},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdmw65004.2024.00061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw65004.2024.00061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Data Mining Workshops (ICDMW)","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":22,"referenced_works":["https://openalex.org/W376370578","https://openalex.org/W1995207790","https://openalex.org/W2022887050","https://openalex.org/W2093428321","https://openalex.org/W2466376234","https://openalex.org/W2886852208","https://openalex.org/W2914408384","https://openalex.org/W2963947304","https://openalex.org/W2981984641","https://openalex.org/W3120985523","https://openalex.org/W4200367225","https://openalex.org/W4207059863","https://openalex.org/W4313680752","https://openalex.org/W4360981072","https://openalex.org/W4367353919","https://openalex.org/W4389473931","https://openalex.org/W4395698424","https://openalex.org/W4401114192","https://openalex.org/W4402053208","https://openalex.org/W4403633914","https://openalex.org/W4405897569","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2186048469","https://openalex.org/W2898732673","https://openalex.org/W3029267192","https://openalex.org/W1967509846","https://openalex.org/W4308662946","https://openalex.org/W2410053581","https://openalex.org/W2383658677","https://openalex.org/W2941073738","https://openalex.org/W3123203398","https://openalex.org/W2480059162"],"abstract_inverted_index":{"Maritime":[0],"risk":[1,29,147,163],"research":[2,122],"is":[3],"crucial":[4],"yet":[5],"challenging":[6],"for":[7,22,73],"improving":[8,139],"safety,":[9],"efficiency,":[10],"and":[11,26,59,68,143,150,172],"sustainability":[12],"in":[13,162],"maritime":[14,34,146],"operations.":[15],"This":[16],"paper":[17],"presents":[18],"an":[19],"innovative":[20],"method":[21,114],"automating":[23],"the":[24,40,48,87,99,112,126,131,141,156],"collection":[25,149,171],"identification":[27,173],"of":[28,42,101,111,145],"data":[30,148,170],"related":[31],"to":[32,85,105,155,168],"global":[33],"risks":[35],"from":[36],"news":[37],"sources,":[38],"addressing":[39],"limitations":[41],"traditional":[43,136],"manual":[44],"methods.":[45],"To":[46],"evaluate":[47,106],"proposed":[49,88,113,127],"method,":[50,89,133],"different":[51,118],"learning-based":[52],"models,":[53,137],"including":[54],"conventional":[55],"machine":[56],"learning":[57],"approaches":[58],"advanced":[60],"Large":[61],"Language":[62],"Models":[63],"(LLMs)":[64],"such":[65],"as":[66],"GPT-4":[67],"LLaMA-3.1,":[69],"are":[70,115],"comprehensively":[71],"studied":[72],"comparison.":[74],"In":[75],"addition,":[76],"not":[77],"only":[78],"do":[79],"we":[80,91],"use":[81],"popular":[82],"evaluation":[83,96,119],"metrics":[84],"assess":[86],"but":[90],"also":[92],"introduce":[93],"a":[94],"new":[95],"metric,":[97],"called":[98],"\"Ratio":[100],"Valid":[102],"Categories":[103],"(RVC),\"":[104],"model":[107],"reliability.":[108],"The":[109,121],"merits":[110],"demonstrated":[116],"across":[117],"metrics.":[120],"results":[123],"show":[124],"that":[125],"LLM-based":[128],"methods,":[129],"particularly":[130],"GPT-4-based":[132],"consistently":[134],"outperform":[135],"significantly":[138],"both":[140],"efficiency":[142],"accuracy":[144],"identification.":[151],"Our":[152],"findings":[153],"contribute":[154],"expanding":[157],"literature":[158],"on":[159],"LLM":[160],"applications":[161],"management,":[164],"demonstrating":[165],"their":[166],"potential":[167],"transform":[169],"practices.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}