{"id":"https://openalex.org/W7129042851","doi":"https://doi.org/10.71448/bcds2561-3","title":"Self-Supervised Code-Mixed Representation Learning for Multi-Label Emoji, Sentiment, and Emotion Prediction","display_name":"Self-Supervised Code-Mixed Representation Learning for Multi-Label Emoji, Sentiment, and Emotion Prediction","publication_year":2025,"publication_date":"2025-03-30","ids":{"openalex":"https://openalex.org/W7129042851","doi":"https://doi.org/10.71448/bcds2561-3"},"language":null,"primary_location":{"id":"doi:10.71448/bcds2561-3","is_oa":true,"landing_page_url":"https://doi.org/10.71448/bcds2561-3","pdf_url":null,"source":{"id":"https://openalex.org/S7407053757","display_name":"Bulletin of Computer and Data Sciences","issn_l":"3072-2926","issn":["3072-2926"],"is_oa":false,"is_in_doaj":false,"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bulletin of Computer and Data Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.71448/bcds2561-3","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109746696","display_name":"Asif Shehzad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asif Shehzad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126123901","display_name":"Rahul Sharma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahul Sharma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126159061","display_name":"Pushpak Bhattacharyya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pushpak Bhattacharyya","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77959507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"1","first_page":"39","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.8977000117301941,"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":0.8977000117301941,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.02669999934732914,"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/T13155","display_name":"Digital Communication and Language","score":0.017000000923871994,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/exploit","display_name":"Exploit","score":0.5564000010490417},{"id":"https://openalex.org/keywords/emoji","display_name":"Emoji","score":0.5045999884605408},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4684999883174896},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4546999931335449},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4528000056743622},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4296000003814697},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42089998722076416},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4162999987602234},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.39660000801086426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670999765396118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050999760627747},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5564000010490417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5562999844551086},{"id":"https://openalex.org/C2779247141","wikidata":"https://www.wikidata.org/wiki/Q1049294","display_name":"Emoji","level":3,"score":0.5045999884605408},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4537000060081482},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42089998722076416},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4162999987602234},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.32910001277923584},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.71448/bcds2561-3","is_oa":true,"landing_page_url":"https://doi.org/10.71448/bcds2561-3","pdf_url":null,"source":{"id":"https://openalex.org/S7407053757","display_name":"Bulletin of Computer and Data Sciences","issn_l":"3072-2926","issn":["3072-2926"],"is_oa":false,"is_in_doaj":false,"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bulletin of Computer and Data Sciences","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.71448/bcds2561-3","is_oa":true,"landing_page_url":"https://doi.org/10.71448/bcds2561-3","pdf_url":null,"source":{"id":"https://openalex.org/S7407053757","display_name":"Bulletin of Computer and Data Sciences","issn_l":"3072-2926","issn":["3072-2926"],"is_oa":false,"is_in_doaj":false,"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bulletin of Computer and Data Sciences","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7681171894073486,"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":{"Emoji":[0],"usage":[1],"and":[2,19,22,38,48,58,73,82,131,152,174,194,213,216,225,239],"code-mixed":[3,26,62,103,117,163,205,237],"language":[4,84,129],"have":[5],"become":[6],"central":[7],"to":[8,33,186,210],"informal":[9],"online":[10],"communication,":[11],"especially":[12],"in":[13,80,139],"multilingual":[14,108,176],"communities.":[15],"Predicting":[16],"suitable":[17],"emojis":[18],"inferring":[20],"sentiment":[21,150],"emotion":[23,59,155],"from":[24,106],"noisy,":[25],"social":[27,118],"media":[28,119],"text":[29],"is":[30],"challenging":[31],"due":[32],"non-standard":[34],"spelling,":[35],"cross-script":[36],"mixing,":[37],"strong":[39,175],"pragmatic":[40],"effects.":[41],"Prior":[42],"work":[43,246],"has":[44],"proposed":[45],"specialized":[46,100],"encoders":[47],"multi-task":[49,141],"frameworks":[50],"for":[51,101,143,181,236,244],"joint":[52],"prediction":[53,183],"of":[54,161,232],"multi-label":[55,145],"emojis,":[56,223],"sentiment,":[57,224],"on":[60,69,114,157,247],"English\u2013Hindi":[61,162],"tweets.":[63,164],"However,":[64],"these":[65],"approaches":[66],"are":[67],"built":[68],"relatively":[70],"shallow":[71],"architectures":[72,173],"do":[74],"not":[75],"fully":[76],"exploit":[77],"recent":[78],"advances":[79],"self-supervised":[81,97,204,234],"large":[83],"model":[85,99],"(LLM)":[86],"based":[87],"representation":[88],"learning.":[89,134],"In":[90],"this":[91],"paper,":[92],"we":[93,111],"introduce":[94],"CodeMixLM,":[95],"a":[96,107,140,241],"transformer":[98,109,177],"Hinglish":[102],"text.":[104],"Starting":[105],"backbone,":[110],"continue":[112],"pretraining":[113,206],"large-scale":[115],"unlabeled":[116],"data":[120],"with":[121],"three":[122],"auxiliary":[123],"objectives:":[124],"masked":[125],"span":[126],"denoising,":[127],"script-aware":[128],"identification,":[130],"emoji-aware":[132,248],"contrastive":[133],"We":[135],"then":[136],"fine-tune":[137],"CodeMixLM":[138,168],"setting":[142],"(i)":[144],"emoji":[146,182],"prediction,":[147],"(ii)":[148],"three-way":[149],"classification,":[151],"(iii)":[153],"seven-way":[154],"classification":[156],"the":[158,220,230],"SENTIMOJI":[159],"dataset":[160],"Across":[165],"all":[166],"tasks,":[167],"substantially":[169],"outperforms":[170],"prior":[171],"task-specific":[172],"baselines,":[178],"improving":[179],"macro-F1":[180],"by":[184],"up":[185],"several":[187],"points":[188],"while":[189],"also":[190],"yielding":[191],"better":[192,218],"calibration":[193],"label":[195],"efficiency":[196],"under":[197],"reduced":[198],"supervision.":[199],"Detailed":[200],"analyses":[201],"show":[202],"that":[203],"(1)":[207],"improves":[208],"robustness":[209],"spelling":[211],"variants":[212],"code-switching":[214],"patterns,":[215],"(2)":[217],"captures":[219],"interaction":[221],"between":[222],"emotion.":[226],"Our":[227],"results":[228],"highlight":[229],"importance":[231],"domain-specialized":[233],"learning":[235],"NLP":[238],"offer":[240],"stronger":[242],"baseline":[243],"future":[245],"affective":[249],"computing.":[250]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-17T00:00:00"}