{"id":"https://openalex.org/W7224941969","doi":"https://doi.org/10.5281/zenodo.23792019","title":"Robust NLP for Social Good: Transformer-Based Classification of Noisy Disaster-Related Social Media Messages","display_name":"Robust NLP for Social Good: Transformer-Based Classification of Noisy Disaster-Related Social Media Messages","publication_year":2026,"publication_date":"2026-10-31","ids":{"openalex":"https://openalex.org/W7224941969","doi":"https://doi.org/10.5281/zenodo.23792019"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23792019","doi":"https://doi.org/10.5281/zenodo.23792019","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23792019","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23792019","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160177710","display_name":"A. R. Jayasudha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I43663321","display_name":"Hindustan Institute of Technology and Science","ror":"https://ror.org/037tgdn13","country_code":"IN","type":"education","lineage":["https://openalex.org/I43663321"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jayasudha, A R","raw_affiliation_strings":["Professor, Hindusthan College of Engineering and Technology, TamilNadu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Professor, Hindusthan College of Engineering and Technology, TamilNadu","institution_ids":["https://openalex.org/I43663321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160224059","display_name":"K. Vigneshkumar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I43663321","display_name":"Hindustan Institute of Technology and Science","ror":"https://ror.org/037tgdn13","country_code":"IN","type":"education","lineage":["https://openalex.org/I43663321"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vigneshkumar, K","raw_affiliation_strings":["Assistant Professor, Hindusthan College of Engineering and Technology, TamilNadu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Assistant Professor, Hindusthan College of Engineering and Technology, TamilNadu","institution_ids":["https://openalex.org/I43663321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I43663321"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8169593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.8359000086784363,"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/T11550","display_name":"Text and Document Classification Technologies","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/T11121","display_name":"Public Relations and Crisis Communication","score":0.06880000233650208,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"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":0.06430000066757202,"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/disaster-response","display_name":"disaster response","score":0.9639999866485596},{"id":"https://openalex.org/keywords/social-media-text-classification","display_name":"social media text classification","score":0.7889999747276306},{"id":"https://openalex.org/keywords/noisy-text","display_name":"noisy text","score":0.7099999785423279},{"id":"https://openalex.org/keywords/user-generated-content","display_name":"user-generated content","score":0.6710000038146973},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.75},{"id":"https://openalex.org/keywords/crisis-communication","display_name":"crisis communication","score":0.9259999990463257},{"id":"https://openalex.org/keywords/text-preprocessing","display_name":"text preprocessing","score":0.3610000014305115}],"concepts":[{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.7946000099182129},{"id":"https://openalex.org/C2781426162","wikidata":"https://www.wikidata.org/wiki/Q2275793","display_name":"Casual","level":2,"score":0.732699990272522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5684000253677368},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5519000291824341},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.48100000619888306},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35929998755455017},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C30539005","wikidata":"https://www.wikidata.org/wiki/Q1066689","display_name":"Human communication","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C4727928","wikidata":"https://www.wikidata.org/wiki/Q17164759","display_name":"Social network (sociolinguistics)","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23792019","doi":"https://doi.org/10.5281/zenodo.23792019","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23792019","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.5281/zenodo.23792020","doi":"https://doi.org/10.5281/zenodo.23792020","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23792020","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23792019","doi":"https://doi.org/10.5281/zenodo.23792019","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23792019","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7131387274","https://openalex.org/W4313483670","https://openalex.org/W7171086280","https://openalex.org/W4398756327","https://openalex.org/W4396768561","https://openalex.org/W4309048572","https://openalex.org/W6990528419","https://openalex.org/W7130966905","https://openalex.org/W7223170743","https://openalex.org/W6903874803"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"the":[2,11,51,74,82,89,106,109,121,126,146,149,152,173,180,208,231,248,261],"wake":[3],"of":[4,26,53,84,94,108,111,148,151,154,172,210,233,251,264],"terrible":[5],"occurrences,":[6],"social":[7,122,132,195,239,268],"media":[8,18,123,133,196,240],"has":[9,19],"become":[10,20],"preferred":[12],"source":[13],"for":[14,24,267],"real-time":[15],"information.":[16],"Social":[17],"a":[21,103,159,163,225],"significant":[22],"instrument":[23],"victims":[25],"catastrophes":[27,77,137,158,244],"to":[28,40,69,72,76,97,119,136,141,178,205,243,245,260],"express":[29],"their":[30,41],"needs,":[31],"document":[32],"incidents,":[33],"request":[34],"support":[35],"and":[36,59,81,86,92,162,186,193,212,217,254],"share":[37],"information":[38],"related":[39,96,135],"situation.":[42],"However,":[43],"automated":[44],"analysis":[45],"may":[46,66],"be":[47,67],"fairly":[48],"difficult":[49],"in":[50,88,224,247],"case":[52],"casual,":[54],"abbreviated,":[55],"grammatically":[56],"inconsistent,":[57],"spelling-variant":[58],"other":[60],"textual":[61,155],"noisy":[62,214],"communications.":[63],"Artificial":[64,265],"intelligence":[65],"used":[68,177],"this":[70],"data":[71,216],"enhance":[73],"response":[75],"provided":[78],"by":[79,191],"technology":[80],"well-being":[83],"humans":[85],"help":[87],"improved":[90],"detection":[91],"organization":[93],"communications":[95],"disasters.":[98],"The":[99,188,228],"current":[100],"research":[101,229],"is":[102,138],"study":[104],"on":[105,117,157,238],"feasibility":[107],"use":[110,232],"Natural":[112],"Language":[113],"Processing":[114],"(NLP)":[115],"based":[116],"transformers":[118],"classify":[120],"postings":[124],"about":[125],"tragedy":[127],"with":[128],"background":[129],"noise.":[130],"A":[131],"dataset":[134],"pre-processed":[139],"adequately":[140],"develop":[142],"classification":[143],"models.":[144],"For":[145],"comparison":[147],"performance":[150,175],"handling":[153],"content":[156],"transformer-based":[160,221],"model":[161],"conventional":[164],"machine-learning":[165],"baseline":[166],"are":[167,198],"taken":[168],"into":[169],"consideration.":[170],"Some":[171],"main":[174],"indicators":[176],"evaluate":[179,220],"models":[181],"include":[182],"accuracy,":[183],"precision,":[184],"recall":[185],"F1-score.":[187],"problems":[189],"caused":[190],"casual":[192],"distracting":[194],"text":[197,222],"given":[199],"specific":[200],"attention.":[201],"This":[202],"project":[203],"aims":[204],"(1)":[206],"describe":[207],"challenges":[209],"collecting":[211],"evaluating":[213],"user-generated":[215],"(2)":[218],"empirically":[219],"categorisation":[223],"disaster-response":[226],"setting.":[227],"explores":[230],"AI-driven":[234],"natural":[235],"language":[236],"processing":[237],"platforms":[241],"connected":[242],"assist":[246],"timely":[249],"comprehension":[250],"crisis-related":[252],"communication":[253],"human":[255],"well-being.":[256],"Moreover,":[257],"it":[258],"adds":[259],"greater":[262],"issue":[263],"Intelligence":[266],"benefit.":[269]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-31T00:00:00"}