{"id":"https://openalex.org/W4416132502","doi":"https://doi.org/10.1145/3736425.3771957","title":"LLM-Powered Data Annotation for Bridging the Semantic Gap in Air Quality Monitoring","display_name":"LLM-Powered Data Annotation for Bridging the Semantic Gap in Air Quality Monitoring","publication_year":2025,"publication_date":"2025-11-11","ids":{"openalex":"https://openalex.org/W4416132502","doi":"https://doi.org/10.1145/3736425.3771957"},"language":null,"primary_location":{"id":"doi:10.1145/3736425.3771957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736425.3771957","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736425.3771957","source":null,"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 12th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3736425.3771957","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090793612","display_name":"Ragini Gupta","orcid":"https://orcid.org/0000-0002-8474-2348"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ragini Gupta","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana Champaign, Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0002-8474-2348","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana Champaign, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120442804","display_name":"Abbas Ali Mirza","orcid":"https://orcid.org/0009-0001-3670-999X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abbas Ali Mirza","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana Champaign, Illinois, USA"],"raw_orcid":"https://orcid.org/0009-0001-3670-999X","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana Champaign, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029999794","display_name":"Claudiu Danilov","orcid":"https://orcid.org/0000-0002-6031-9270"},"institutions":[{"id":"https://openalex.org/I4210150370","display_name":"Boeing (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210150370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claudiu Danilov","raw_affiliation_strings":["The Boeing Company, Chicago, Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0002-6031-9270","affiliations":[{"raw_affiliation_string":"The Boeing Company, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I4210150370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034394840","display_name":"Josh Eckhardt","orcid":"https://orcid.org/0009-0000-2747-6998"},"institutions":[{"id":"https://openalex.org/I4210150370","display_name":"Boeing (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210150370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josh Eckhardt","raw_affiliation_strings":["The Boeing Company, Chicago, Illinois, USA"],"raw_orcid":"https://orcid.org/0009-0000-2747-6998","affiliations":[{"raw_affiliation_string":"The Boeing Company, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I4210150370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119586769","display_name":"Keyshla Bernard","orcid":"https://orcid.org/0009-0001-2533-5590"},"institutions":[{"id":"https://openalex.org/I4210150370","display_name":"Boeing (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210150370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keyshla Bernard","raw_affiliation_strings":["The Boeing Company, Chicago, Illinois, USA"],"raw_orcid":"https://orcid.org/0009-0001-2533-5590","affiliations":[{"raw_affiliation_string":"The Boeing Company, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I4210150370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074224097","display_name":"Klara Nahrstedt","orcid":"https://orcid.org/0000-0001-6813-3043"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Klara Nahrstedt","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana Champaign, Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0001-6813-3043","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana Champaign, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090793612"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29813971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"394","last_page":"399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12120","display_name":"Air Quality Monitoring and Forecasting","score":0.963699996471405,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12120","display_name":"Air Quality Monitoring and Forecasting","score":0.963699996471405,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.003100000089034438,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.8230000138282776},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.578000009059906},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.5217000246047974},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4706000089645386},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.453900009393692},{"id":"https://openalex.org/keywords/air-quality-index","display_name":"Air quality index","score":0.44449999928474426},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42750000953674316},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42320001125335693},{"id":"https://openalex.org/keywords/semantic-annotation","display_name":"Semantic annotation","score":0.414900004863739}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8230000138282776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930999994277954},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.578000009059906},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5217000246047974},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44449999928474426},{"id":"https://openalex.org/C126314574","wikidata":"https://www.wikidata.org/wiki/Q2364111","display_name":"Air quality index","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42800000309944153},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C2985727698","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Semantic annotation","level":3,"score":0.414900004863739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40939998626708984},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.38499999046325684},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C2776356880","wikidata":"https://www.wikidata.org/wiki/Q5381206","display_name":"Environmental data","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.32249999046325684},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3736425.3771957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736425.3771957","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736425.3771957","source":null,"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 12th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3736425.3771957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736425.3771957","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736425.3771957","source":null,"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 12th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416132502.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2576817675","https://openalex.org/W2914477964","https://openalex.org/W3022583980","https://openalex.org/W4226087031","https://openalex.org/W4384283312","https://openalex.org/W4390909748","https://openalex.org/W4399629207","https://openalex.org/W4399940351","https://openalex.org/W4402675515","https://openalex.org/W4412743715"],"related_works":[],"abstract_inverted_index":{"Accurately":[0],"annotating":[1],"raw":[2,83],"sensor":[3,26,84,104,176],"data":[4,85,105,129],"with":[5,140,152],"Air":[6],"Quality":[7],"Index":[8],"(AQI)":[9],"categories":[10,101],"presents":[11],"significant":[12],"challenges":[13],"in":[14,130],"traditional":[15,207],"approaches,":[16],"primarily":[17],"due":[18],"to":[19,42,74,98,134,173,202],"the":[20,120,170,186,204],"fundamental":[21],"semantic":[22,77,171],"gap":[23,172],"between":[24],"low-level":[25],"readings":[27],"and":[28,39,45,56,143,178],"high-level":[29],"air":[30],"quality":[31],"interpretations.":[32],"Rule-based":[33],"systems":[34],"require":[35],"perfect":[36],"domain":[37],"expertise":[38],"are":[40,138],"prone":[41],"labeling":[43],"errors":[44],"inconsistencies,":[46],"while":[47],"supervised":[48],"machine":[49],"learning":[50],"models":[51],"demand":[52],"extensive":[53],"labeled":[54],"datasets":[55],"computational":[57],"resources.":[58],"This":[59],"work":[60,184],"explores":[61],"an":[62,145],"alternative":[63],"paradigm":[64],"by":[65],"leveraging":[66],"Large":[67],"Language":[68],"Models":[69],"(LLMs)":[70],"as":[71,190],"virtual":[72,193],"annotators":[73,194],"bridge":[75],"this":[76],"gap,":[78],"enabling":[79],"direct":[80],"interpretation":[81],"of":[82,110,188,206],"without":[86,210],"explicit":[87],"formulaic":[88],"programming.":[89],"We":[90],"develop":[91],"a":[92,199],"comprehensive":[93],"framework":[94],"using":[95,126],"GPT-3.5":[96],"Turbo":[97],"classify":[99],"AQI":[100,181],"from":[102,107],"multi-variate":[103],"collected":[106],"Chicago's":[108],"Array":[109],"Things":[111],"network.":[112],"Our":[113,183],"systematic":[114],"evaluation":[115],"reveals":[116],"several":[117],"key":[118],"findings:":[119],"LLM":[121],"achieves":[122],"82%":[123],"average":[124],"accuracy":[125],"only":[127],"pollutant":[128],"zero-shot":[131],"settings,":[132],"improves":[133],"88%":[135],"when":[136,150],"prompts":[137],"supported":[139],"bootstrap":[141],"examples,":[142],"gains":[144],"additional":[146],"4%":[147],"performance":[148],"boost":[149],"augmented":[151],"environmental":[153,196],"context":[154],"(temperature,":[155],"humidity).":[156],"These":[157],"results,":[158],"validated":[159],"through":[160],"principled":[161],"statistical":[162],"analysis,":[163],"demonstrate":[164],"that":[165],"LLMs":[166,189],"can":[167],"effectively":[168],"overcome":[169,203],"comprehend":[174],"complex":[175,213],"patterns":[177],"provide":[179],"reliable":[180],"annotations.":[182],"establishes":[185],"viability":[187],"scalable,":[191],"context-aware":[192],"for":[195],"monitoring,":[197],"offering":[198],"promising":[200],"solution":[201],"limitations":[205],"annotation":[208],"methods":[209],"relying":[211],"on":[212],"prompt-engineering":[214],"or":[215],"model":[216],"fine-tuning.":[217]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-11T00:00:00"}