{"id":"https://openalex.org/W7125233009","doi":"https://doi.org/10.1007/s44443-026-00472-5","title":"SemCap: Sentiment-aware semantic captioning for multimodal aspect-based sentiment analysis","display_name":"SemCap: Sentiment-aware semantic captioning for multimodal aspect-based sentiment analysis","publication_year":2026,"publication_date":"2026-01-21","ids":{"openalex":"https://openalex.org/W7125233009","doi":"https://doi.org/10.1007/s44443-026-00472-5"},"language":"en","primary_location":{"id":"doi:10.1007/s44443-026-00472-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00472-5","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s44443-026-00472-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121066197","display_name":"Kexin Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kexin Jiang","raw_affiliation_strings":["Department of School of Computer Science, South China Business College of Guangdong, University of Foreign Studies, GuangZhou, China"],"affiliations":[{"raw_affiliation_string":"Department of School of Computer Science, South China Business College of Guangdong, University of Foreign Studies, GuangZhou, China","institution_ids":["https://openalex.org/I186272606"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039945902","display_name":"Xiaoqin LuoShi FangYunjun Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Xiao","raw_affiliation_strings":["Department of School of Computer Science, South China Business College of Guangdong, University of Foreign Studies, GuangZhou, China"],"affiliations":[{"raw_affiliation_string":"Department of School of Computer Science, South China Business College of Guangdong, University of Foreign Studies, GuangZhou, China","institution_ids":["https://openalex.org/I186272606"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123524498","display_name":"Xiangxiang Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxiang Lu","raw_affiliation_strings":["Department of School of Computer Science, South China Business College of Guangdong, University of Foreign Studies, GuangZhou, China"],"affiliations":[{"raw_affiliation_string":"Department of School of Computer Science, South China Business College of Guangdong, University of Foreign Studies, GuangZhou, China","institution_ids":["https://openalex.org/I186272606"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123528768","display_name":"Yue Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Qin","raw_affiliation_strings":["Department of School of Computer Science, South China Business College of Guangdong, University of Foreign Studies, GuangZhou, China"],"affiliations":[{"raw_affiliation_string":"Department of School of Computer Science, South China Business College of Guangdong, University of Foreign Studies, GuangZhou, China","institution_ids":["https://openalex.org/I186272606"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5121066197"],"corresponding_institution_ids":["https://openalex.org/I186272606"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21794951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9300000071525574,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9300000071525574,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.022600000724196434,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.016699999570846558,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8215000033378601},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.6349999904632568},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.45730000734329224},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4404999911785126},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41019999980926514},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4023999869823456},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.38519999384880066},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.36629998683929443},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.3521000146865845}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8215000033378601},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187999725341797},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.6349999904632568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5690000057220459},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4936999976634979},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.38519999384880066},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.36629998683929443},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27489998936653137},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44443-026-00472-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00472-5","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1b154bbdb73640eb94e940c20c949979","is_oa":true,"landing_page_url":"https://doaj.org/article/1b154bbdb73640eb94e940c20c949979","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of King Saud University: Computer and Information Sciences, Vol 38, Iss 3 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44443-026-00472-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00472-5","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5522723197937012},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.42858269810676575}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2949660355","https://openalex.org/W2966765144","https://openalex.org/W3035448883","https://openalex.org/W3092378671","https://openalex.org/W3092692431","https://openalex.org/W3114613321","https://openalex.org/W3176038554","https://openalex.org/W3214184275","https://openalex.org/W4224286930","https://openalex.org/W4289516263","https://openalex.org/W4313561432","https://openalex.org/W4381620979","https://openalex.org/W4385570436","https://openalex.org/W4385570945","https://openalex.org/W4385571103","https://openalex.org/W4385572041","https://openalex.org/W4388923785","https://openalex.org/W4389519102","https://openalex.org/W4389987717","https://openalex.org/W4390430684","https://openalex.org/W4390618491","https://openalex.org/W4391057690","https://openalex.org/W4391867272","https://openalex.org/W4392096985","https://openalex.org/W4392385305","https://openalex.org/W4393346089","https://openalex.org/W4395069541","https://openalex.org/W4400191939","https://openalex.org/W4401344631","https://openalex.org/W4401990620","https://openalex.org/W4402053001","https://openalex.org/W4402351992","https://openalex.org/W4402601975","https://openalex.org/W4404654701","https://openalex.org/W4408211979","https://openalex.org/W4409346675","https://openalex.org/W4409917222","https://openalex.org/W4411859226","https://openalex.org/W4411962479","https://openalex.org/W4414360643","https://openalex.org/W4415189790","https://openalex.org/W4415973587","https://openalex.org/W4416793123"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"aspect-based":[1],"sentiment":[2],"analysis":[3],"(MABSA)":[4],"is":[5,77],"critical":[6],"for":[7],"fine-grained":[8],"opinion":[9],"mining":[10],"from":[11,33],"social":[12],"media.":[13],"Current":[14],"mainstream":[15],"methods":[16],"rely":[17],"on":[18,131,144],"feature-level":[19],"fusion":[20,40,102],"and":[21,27,41,52,134,140,147],"attention":[22],"mechanisms":[23],"to":[24,49,84,109,122,137],"align":[25],"visual":[26,34,73,115],"textual":[28,42],"features.":[29],"However,":[30],"MABSA":[31,156],"suffers":[32],"noise":[35,43],"caused":[36,44],"by":[37,45,79,128],"cluttered":[38],"image":[39],"inter-aspect":[46],"interference,":[47],"leading":[48],"modality":[50],"conflicts":[51],"spurious":[53],"aspect":[54,132],"predictions.":[55],"We":[56],"propose":[57],"SemCap,":[58],"a":[59,66,123],"framework":[60],"that":[61],"mitigates":[62],"these":[63],"issues":[64],"using":[65],"sentiment-aware":[67],"caption":[68,76,107],"as":[69],"an":[70],"explicit,":[71],"high-level":[72],"proxy.":[74],"This":[75],"generated":[78],"Qwen3-VL":[80],"under":[81],"sentiment-oriented":[82],"prompts":[83],"selectively":[85],"describe":[86],"emotion-bearing":[87],"entities.":[88],"To":[89],"accurately":[90],"aggregate":[91],"cross-modal":[92],"sentiment,":[93],"we":[94],"design":[95],"the":[96,106,111,145],"Semantic":[97],"Proxy":[98],"Dynamic":[99],"Routing":[100],"(SPDR)":[101],"module,":[103],"which":[104],"uses":[105],"representation":[108],"guide":[110],"selection":[112],"of":[113],"relevant":[114],"patches.":[116],"The":[117],"refined":[118],"features":[119],"are":[120],"input":[121],"multimodal":[124],"interactive":[125],"decoder,":[126],"augmented":[127],"auxiliary":[129],"supervision":[130],"boundaries":[133],"polarity":[135],"labels":[136],"enhance":[138],"localization":[139],"discrimination.":[141],"Extensive":[142],"experiments":[143],"Twitter-2015":[146],"Twitter-2017":[148],"datasets":[149],"demonstrate":[150],"SemCap\u2019s":[151],"superior":[152],"performance":[153],"over":[154],"existing":[155],"methods.":[157]},"counts_by_year":[],"updated_date":"2026-03-17T17:19:04.345684","created_date":"2026-01-22T00:00:00"}