{"id":"https://openalex.org/W7123430500","doi":"https://doi.org/10.48550/arxiv.2601.06870","title":"QASA: Quality-Aware Semantic Augmentation for Robust Multimodal Sentiment Analysis","display_name":"QASA: Quality-Aware Semantic Augmentation for Robust Multimodal Sentiment Analysis","publication_year":2026,"publication_date":"2026-01-11","ids":{"openalex":"https://openalex.org/W7123430500","doi":"https://doi.org/10.48550/arxiv.2601.06870"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.06870","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.06870","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.06870","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122981406","display_name":"Jiazhang Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Jiazhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122978746","display_name":"Jianheng Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Jianheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122961772","display_name":"Miaosen Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Miaosen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122919389","display_name":"Menghua Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Menghua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010270301","display_name":"Sijie Mai","orcid":"https://orcid.org/0000-0001-9763-375X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mai, Sijie","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.25099998712539673,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.25099998712539673,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.2393999993801117,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.19439999759197235,"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/leverage","display_name":"Leverage (statistics)","score":0.6444000005722046},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5802000164985657},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5128999948501587},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4875999987125397},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.453900009393692},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.45339998602867126},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.3750999867916107},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.32989999651908875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688000202178955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6484000086784363},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6444000005722046},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5802000164985657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.517799973487854},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.45339998602867126},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.32989999651908875},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.06870","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.06870","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2601.06870","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.06870","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[{"id":"https://metadata.un.org/sdg/4","score":0.5383815765380859,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1,130],"language":[2],"models":[3,47,123],"have":[4],"demonstrated":[5],"strong":[6],"ability":[7],"in":[8,69,169],"capturing":[9],"semantic":[10,126],"representations":[11],"for":[12],"multimodal":[13,23,62,129],"sentiment":[14],"analysis.":[15],"Their":[16],"capacity":[17],"to":[18,48,108],"learn":[19],"stable":[20,110],"and":[21,52,60,71,106,111,147,167,173,178,187],"generalizable":[22],"features":[24],"is":[25],"limited,":[26],"however,":[27],"by":[28],"the":[29,57,92,101,118,125,155,185],"scarcity":[30],"of":[31,94,103,121,128,165],"high-quality":[32,151],"training":[33,58,88],"data.":[34,152],"To":[35,76],"address":[36],"this,":[37,78],"we":[38,79],"propose":[39],"QASA":[40,160],"(Quality-Aware":[41],"Semantic":[42],"Augmentation),":[43],"which":[44],"uses":[45],"diffusion":[46,122],"generate":[49],"augmented":[50,96],"visual":[51],"auditory":[53],"samples,":[54],"thereby":[55],"enlarging":[56],"dataset":[59,157],"supporting":[61],"learning.":[63],"The":[64,115],"generated":[65],"samples":[66],"can":[67],"vary":[68],"quality":[70],"may":[72],"exhibit":[73],"cross-modal":[74],"inconsistencies.":[75],"manage":[77],"introduce":[80],"a":[81,162],"decoupled":[82],"quality-aware":[83],"scoring":[84],"module":[85],"that":[86,138,159],"assigns":[87],"weights":[89],"based":[90],"on":[91,154,184],"reliability":[93],"each":[95],"sample.":[97],"This":[98],"approach":[99],"reduces":[100],"influence":[102],"low-quality":[104],"data":[105,135],"contributes":[107],"more":[109],"robust":[112],"model":[113],"training.":[114],"framework":[116],"combines":[117],"generative":[119],"capabilities":[120],"with":[124],"reasoning":[127],"models,":[131],"providing":[132],"an":[133],"automated":[134],"augmentation":[136],"strategy":[137],"does":[139],"not":[140],"require":[141],"human":[142],"annotation":[143],"while":[144],"improving":[145],"generalization":[146],"robustness":[148],"under":[149],"limited":[150],"Experiments":[153],"CH-SIMS":[156],"show":[158],"yields":[161],"relative":[163],"increase":[164],"18.0\\%":[166],"5.9\\%":[168],"five-class":[170],"accuracy":[171,175],"(Acc5)":[172],"binary":[174],"(Acc2),":[176],"respectively,":[177],"it":[179],"also":[180],"outperforms":[181],"existing":[182],"methods":[183],"CMU-MOSI":[186],"MUStARD":[188],"benchmarks.":[189]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-01-14T00:00:00"}