{"id":"https://openalex.org/W7127585353","doi":"https://doi.org/10.48550/arxiv.2602.02601","title":"CaST: Causal Discovery via Spatio-Temporal Graphs in Disaster Tweets","display_name":"CaST: Causal Discovery via Spatio-Temporal Graphs in Disaster Tweets","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7127585353","doi":"https://doi.org/10.48550/arxiv.2602.02601"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.02601","doi":"https://doi.org/10.48550/arxiv.2602.02601","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.02601","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":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.02601","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Duong, Hieu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duong, Hieu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030905020","display_name":"Eugene L. Levin","orcid":"https://orcid.org/0000-0002-8127-3208","observed_orcids":["https://orcid.org/0000-0002-8127-3208"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Levin, Eugene","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112532699","display_name":"Todd Gary","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gary, Todd","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124887843","display_name":"Long Nguyen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Long","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T10028","display_name":"Topic Modeling","score":0.5615000128746033,"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/T10028","display_name":"Topic Modeling","score":0.5615000128746033,"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":0.14059999585151672,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.053700000047683716,"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/causal-discovery","display_name":"causal discovery","score":0.9929999709129333},{"id":"https://openalex.org/keywords/disaster-tweets","display_name":"disaster tweets","score":0.8650000095367432},{"id":"https://openalex.org/keywords/spatio-temporal-graph","display_name":"spatio-temporal graph","score":0.9679999947547913},{"id":"https://openalex.org/keywords/event-graphs","display_name":"event graphs","score":0.671999990940094},{"id":"https://openalex.org/keywords/graph-attention-networks","display_name":"graph attention networks","score":0.746999979019165},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7039999961853027},{"id":"https://openalex.org/keywords/hurricane-harvey","display_name":"Hurricane Harvey","score":0.7609999775886536},{"id":"https://openalex.org/keywords/situational-awareness","display_name":"situational awareness","score":0.7210000157356262},{"id":"https://openalex.org/keywords/event-extraction","display_name":"event extraction","score":0.48500001430511475},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"semantic similarity","score":0.5529999732971191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7134000062942505},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6485000252723694},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.5669000148773193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46650001406669617},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3628999888896942},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3353999853134155},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C145804949","wikidata":"https://www.wikidata.org/wiki/Q478123","display_name":"Situation awareness","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2777810175","wikidata":"https://www.wikidata.org/wiki/Q5416730","display_name":"Event structure","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.02601","doi":"https://doi.org/10.48550/arxiv.2602.02601","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.02601","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.02601","doi":"https://doi.org/10.48550/arxiv.2602.02601","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.02601","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":"Preprint"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.7800506949424744}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"causality":[1],"between":[2,22],"real-world":[3],"events":[4],"from":[5,74],"social":[6,191],"media":[7,192],"is":[8,76,105],"essential":[9],"for":[10,39,66],"situational":[11],"awareness,":[12],"yet":[13],"existing":[14],"causal":[15,40,118,187],"discovery":[16,41,188],"methods":[17],"often":[18],"overlook":[19],"the":[20,137],"interplay":[21],"semantic,":[23],"spatial,":[24],"and":[25,49,89,134,151,161,168,185],"temporal":[26,90,162],"contexts.":[27],"We":[28,120],"propose":[29],"CaST:":[30],"Causal":[31],"Discovery":[32],"via":[33],"Spatio-Temporal":[34],"Graphs,":[35],"a":[36,79,100,108],"unified":[37],"framework":[38],"in":[42,189],"disaster":[43,59],"domain":[44],"that":[45,143,158,175],"integrates":[46],"semantic":[47],"similarity":[48],"spatio-temporal":[50,101,177],"proximity":[51],"using":[52,107],"Large":[53],"Language":[54],"Models":[55],"(LLMs)":[56],"pretrained":[57],"on":[58],"datasets.":[60],"CaST":[61,144,173],"constructs":[62],"an":[63,122],"event":[64,72,93,102,180],"graph":[65],"each":[67],"window":[68],"of":[69,125],"tweets.":[70],"Each":[71],"extracted":[73],"tweets":[75,129],"represented":[77],"as":[78],"node":[80],"embedding":[81],"enriched":[82],"with":[83],"its":[84],"contextual":[85],"semantics,":[86],"geographic":[87],"coordinates,":[88],"features.":[91],"These":[92],"nodes":[94],"are":[95],"then":[96],"connected":[97],"to":[98,115],"form":[99],"graph,":[103],"which":[104],"processed":[106],"multi-head":[109],"Graph":[110],"Attention":[111],"Network":[112],"(GAT)":[113],"\\cite{gat}":[114],"learn":[116],"directed":[117],"relationships.":[119],"construct":[121],"in-house":[123],"dataset":[124],"approximately":[126],"167K":[127],"disaster-related":[128,190],"collected":[130],"during":[131,170],"Hurricane":[132],"Harvey":[133],"annotated":[135],"following":[136],"MAVEN-ERE":[138],"schema.":[139],"Experimental":[140],"results":[141],"show":[142],"achieves":[145],"superior":[146],"performance":[147],"over":[148],"both":[149,166],"traditional":[150],"state-of-the-art":[152],"methods.":[153],"Ablation":[154],"studies":[155],"further":[156],"confirm":[157],"incorporating":[159],"spatial":[160],"signals":[163],"substantially":[164],"improves":[165],"recall":[167],"stability":[169],"training.":[171],"Overall,":[172],"demonstrates":[174],"integrating":[176],"reasoning":[178],"into":[179],"graphs":[181],"enables":[182],"more":[183],"robust":[184],"interpretable":[186],"text.":[193]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-02-06T00:00:00"}