{"id":"https://openalex.org/W4416144406","doi":"https://doi.org/10.1145/3721201.3725444","title":"Enhancing Non-English Conversational Agents Using Synthetic Data Generation","display_name":"Enhancing Non-English Conversational Agents Using Synthetic Data Generation","publication_year":2025,"publication_date":"2025-06-24","ids":{"openalex":"https://openalex.org/W4416144406","doi":"https://doi.org/10.1145/3721201.3725444"},"language":"en","primary_location":{"id":"doi:10.1145/3721201.3725444","doi":"https://doi.org/10.1145/3721201.3725444","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721201.3725444","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3725444","source":{"id":"https://openalex.org/S4393919729","display_name":"IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies","issn_l":"2832-2967","issn":["2832-2967"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3725444","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120493711","display_name":"Salar Hashemitaheri","orcid":"https://orcid.org/0009-0007-1265-0691","observed_orcids":["https://orcid.org/0009-0007-1265-0691"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Salar Hashemitaheri","raw_affiliation_strings":["University of California, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0009-0007-1265-0691","affiliations":[{"raw_affiliation_string":"University of California, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037855756","display_name":"Ian G. Harris","orcid":"https://orcid.org/0000-0003-3244-6528","observed_orcids":["https://orcid.org/0000-0003-3244-6528"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Harris","raw_affiliation_strings":["University of California, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3244-6528","affiliations":[{"raw_affiliation_string":"University of California, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38660385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"412","last_page":"417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10060","display_name":"Smoking Behavior and Cessation","score":0.5922999978065491,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10060","display_name":"Smoking Behavior and Cessation","score":0.5922999978065491,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.15600000321865082,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.06509999930858612,"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/smoking-cessation","display_name":"smoking cessation","score":0.7490000128746033},{"id":"https://openalex.org/keywords/chatbots","display_name":"chatbots","score":0.7699999809265137},{"id":"https://openalex.org/keywords/multilingual-chatbot","display_name":"multilingual chatbot","score":0.7129999995231628},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.8109999895095825},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.7170000076293945},{"id":"https://openalex.org/keywords/intent-recognition","display_name":"intent classification","score":0.9129999876022339},{"id":"https://openalex.org/keywords/non-native-english-speakers","display_name":"non-native English speakers","score":0.8370000123977661},{"id":"https://openalex.org/keywords/online-support-groups","display_name":"online support groups","score":0.7409999966621399},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7039999961853027},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.8690000176429749},{"id":"https://openalex.org/keywords/social-media","display_name":"social media","score":0.5839999914169312},{"id":"https://openalex.org/keywords/user-engagement","display_name":"user engagement","score":0.6430000066757202},{"id":"https://openalex.org/keywords/stigma","display_name":"stigma","score":0.6019999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7214999794960022},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C122980154","wikidata":"https://www.wikidata.org/wiki/Q205555","display_name":"Feeling","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39899998903274536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3714999854564667},{"id":"https://openalex.org/C2777843972","wikidata":"https://www.wikidata.org/wiki/Q2462253","display_name":"Smoking cessation","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C2779070825","wikidata":"https://www.wikidata.org/wiki/Q760434","display_name":"Augment","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C204854418","wikidata":"https://www.wikidata.org/wiki/Q1362921","display_name":"Polling","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.265500009059906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3721201.3725444","doi":"https://doi.org/10.1145/3721201.3725444","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721201.3725444","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3725444","source":{"id":"https://openalex.org/S4393919729","display_name":"IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies","issn_l":"2832-2967","issn":["2832-2967"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3721201.3725444","doi":"https://doi.org/10.1145/3721201.3725444","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721201.3725444","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3725444","source":{"id":"https://openalex.org/S4393919729","display_name":"IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies","issn_l":"2832-2967","issn":["2832-2967"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5683000087738037,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416144406.pdf","grobid_xml":"https://content.openalex.org/works/W4416144406.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2062196548","https://openalex.org/W2131952570","https://openalex.org/W2538964163","https://openalex.org/W2983040767","https://openalex.org/W4292223606","https://openalex.org/W4327810158","https://openalex.org/W4365813461","https://openalex.org/W4384918448"],"related_works":["https://openalex.org/W7147156170","https://openalex.org/W7116858039","https://openalex.org/W4413962393","https://openalex.org/W7126058931","https://openalex.org/W7214921017","https://openalex.org/W7132965170","https://openalex.org/W2943046147","https://openalex.org/W2886936422","https://openalex.org/W4282843657","https://openalex.org/W4379117809"],"abstract_inverted_index":{"Online":[0],"support":[1,74],"groups":[2,19],"for":[3,11,246],"smoking":[4,33,145,243],"cessation":[5,146,244],"provide":[6],"an":[7],"accessible,":[8],"cost-effective":[9],"method":[10],"assisting":[12],"individuals":[13],"looking":[14],"to":[15,24,69,97,107,227],"quit.":[16],"However,":[17],"these":[18,57],"often":[20],"face":[21],"challenges":[22],"related":[23],"low":[25],"user":[26,99],"engagement":[27],"and":[28,52,83,101,131,238],"the":[29,89,95,108,156,169,172,195,203,240],"stigma":[30],"associated":[31],"with":[32,175],"cessation.":[34],"Non-native":[35],"English":[36,248],"speakers":[37],"encounter":[38],"additional":[39],"barriers":[40],"in":[41,75,115,185,189,201],"accessing":[42],"effective":[43],"support,":[44],"as":[45,221],"language":[46,141],"differences":[47],"increase":[48,188],"feelings":[49],"of":[50,88,111,171,197,205,242],"isolation":[51],"discourage":[53],"participation.":[54],"To":[55,149],"address":[56],"issues,":[58],"this":[59,211],"study":[60],"focuses":[61],"on":[62,143],"developing":[63],"a":[64,120,138,186,229],"multilingual":[65,144],"conversational":[66,207,212],"agent":[67,96,213],"designed":[68],"offer":[70,228],"real-time,":[71],"culturally":[72],"sensitive":[73],"multiple":[76],"languages,":[77,117],"including":[78],"Mandarin,":[79],"Arabic,":[80],"Hindi,":[81],"Spanish,":[82],"Farsi.":[84],"A":[85],"critical":[86],"aspect":[87],"system":[90],"is":[91],"intent":[92,151],"classification,":[93],"enabling":[94],"understand":[98],"inputs":[100],"generate":[102],"contextually":[103],"appropriate":[104],"responses.":[105],"Due":[106],"limited":[109],"availability":[110],"high-quality":[112],"training":[113,157],"data":[114,122,129,133,182],"non-English":[116,206],"we":[118,136,154,225],"introduce":[119],"synthetic":[121,128,161,181],"augmentation":[123,183,199],"strategy":[124],"that":[125,180,233],"combines":[126],"both":[127],"generation":[130],"real":[132],"scraping.":[134],"Initially,":[135],"fine-tune":[137],"pre-trained":[139],"large":[140],"model":[142],"group":[147],"data.":[148],"enhance":[150],"detection":[152],"accuracy,":[153],"augment":[155],"dataset":[158],"by":[159],"generating":[160],"posts":[162],"using":[163],"advanced":[164],"prompt":[165],"engineering.":[166],"We":[167],"compare":[168],"performance":[170],"fine-tuned":[173],"LLM":[174],"its":[176],"non-fine-tuned":[177],"counterpart,":[178],"demonstrating":[179],"results":[184],"35.5%":[187],"F1":[190],"scores.":[191],"This":[192],"improvement":[193],"validates":[194],"effectiveness":[196,241],"our":[198],"approach":[200],"boosting":[202],"accuracy":[204],"agents.":[208],"By":[209],"integrating":[210],"into":[214],"widely":[215],"used":[216],"social":[217],"media":[218],"platforms,":[219],"such":[220],"GroupMe":[222],"or":[223],"X,":[224],"aim":[226],"scalable,":[230],"inclusive":[231],"solution":[232],"reduces":[234],"stigma,":[235],"enhances":[236],"engagement,":[237],"improves":[239],"programs":[245],"non-native":[247],"speakers.":[249]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-11-12T00:00:00"}