{"id":"https://openalex.org/W7166802833","doi":"https://doi.org/10.18653/v1/2026.gem-main.69","title":"Text Analytics Evaluation Framework: A Case Study on LLMs and Social Media","display_name":"Text Analytics Evaluation Framework: A Case Study on LLMs and Social Media","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166802833","doi":"https://doi.org/10.18653/v1/2026.gem-main.69"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.gem-main.69","doi":"https://doi.org/10.18653/v1/2026.gem-main.69","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.gem-main.69","pdf_url":"https://aclanthology.org/2026.gem-main.69.pdf","source":{"id":"https://openalex.org/S7407106858","display_name":"Workshop on Generation, Evaluation and Metrics (GEM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 Fifth Workshop on Generation, Evaluation and Metrics (GEM)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.gem-main.69.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035404685","display_name":"Yuefeng Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuefeng Shi","raw_affiliation_strings":["School of Computer Science and Informatics , Cardiff University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics , Cardiff University","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050190445","display_name":"Nedjma Djouhra Ousidhoum","orcid":"https://orcid.org/0000-0003-3015-4759","observed_orcids":["https://orcid.org/0000-0003-3015-4759"]},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nedjma Ousidhoum","raw_affiliation_strings":["School of Computer Science and Informatics , Cardiff University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics , Cardiff University","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139826130","display_name":"Jose Camacho-Collados","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jose Camacho-Collados","raw_affiliation_strings":["School of Computer Science and Informatics , Cardiff University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics , Cardiff University","institution_ids":["https://openalex.org/I79510175"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79510175"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4376685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"808","last_page":"824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8647000193595886,"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/T10028","display_name":"Topic Modeling","score":0.8647000193595886,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.12399999797344208,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9380000233650208},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.6150000095367432},{"id":"https://openalex.org/keywords/social-media-text","display_name":"social media text","score":0.6890000104904175},{"id":"https://openalex.org/keywords/twitter","display_name":"Twitter","score":0.7260000109672546},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"sentiment analysis","score":0.6340000033378601},{"id":"https://openalex.org/keywords/hate-speech-detection","display_name":"hate speech detection","score":1.0},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"emotion recognition","score":0.9980000257492065},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"multi-label classification","score":0.6549999713897705},{"id":"https://openalex.org/keywords/numerical-reasoning","display_name":"numerical reasoning","score":0.6669999957084656},{"id":"https://openalex.org/keywords/openai-models","display_name":"OpenAI models","score":0.49000000953674316},{"id":"https://openalex.org/keywords/text-analysis","display_name":"text analysis","score":0.3970000147819519}],"concepts":[{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5893999934196472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42480000853538513},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.41929998993873596},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38280001282691956},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.37869998812675476},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.3614000082015991},{"id":"https://openalex.org/C2778729106","wikidata":"https://www.wikidata.org/wiki/Q1140126","display_name":"Social media analytics","level":3,"score":0.3522000014781952},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.33480000495910645},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.27639999985694885},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C29595303","wikidata":"https://www.wikidata.org/wiki/Q165650","display_name":"Media studies","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C545860419","wikidata":"https://www.wikidata.org/wiki/Q5193251","display_name":"Cultural analytics","level":5,"score":0.2538999915122986},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.gem-main.69","doi":"https://doi.org/10.18653/v1/2026.gem-main.69","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.gem-main.69","pdf_url":"https://aclanthology.org/2026.gem-main.69.pdf","source":{"id":"https://openalex.org/S7407106858","display_name":"Workshop on Generation, Evaluation and Metrics (GEM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 Fifth Workshop on Generation, Evaluation and Metrics (GEM)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.gem-main.69","doi":"https://doi.org/10.18653/v1/2026.gem-main.69","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.gem-main.69","pdf_url":"https://aclanthology.org/2026.gem-main.69.pdf","source":{"id":"https://openalex.org/S7407106858","display_name":"Workshop on Generation, Evaluation and Metrics (GEM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 Fifth Workshop on Generation, Evaluation and Metrics (GEM)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.49569517374038696,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166802833.pdf","grobid_xml":"https://content.openalex.org/works/W7166802833.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4401042286","https://openalex.org/W4415721256","https://openalex.org/W7155173899","https://openalex.org/W7167691758","https://openalex.org/W7118296517","https://openalex.org/W6910604236","https://openalex.org/W4413345402","https://openalex.org/W4414648314","https://openalex.org/W7092285751","https://openalex.org/W4409657366"],"abstract_inverted_index":{"LLMs":[0,23,52,179],"have":[1],"demonstrated":[2],"exceptional":[3],"proficiency":[4],"in":[5,16,41,53,119,177],"a":[6,12,58,157],"wide":[7],"range":[8],"of":[9,30,51,113],"NLP":[10,89],"tasks.However,":[11],"notable":[13],"gap":[14],"remains":[15],"practical":[17],"data":[18,115],"analysis":[19,184],"scenarios,":[20],"particularly":[21,162],"when":[22],"are":[24],"required":[25],"to":[26,68,137],"process":[27],"long":[28],"sequences":[29],"unstructured":[31],"documents,":[32],"such":[33,141],"as":[34,38,125,142,147],"news":[35],"feeds":[36],"or,":[37],"specifically":[39],"addressed":[40],"this":[42,54],"paper,":[43],"social":[44],"media":[45],"posts.To":[46],"empirically":[47],"assess":[48],"the":[49,103,111,114,148],"effectiveness":[50],"setting,":[55],"we":[56,155],"introduce":[57],"question-based":[59],"evaluation":[60],"framework":[61],"comprising":[62],"470":[63],"manually":[64],"curated":[65],"questions":[66],"designed":[67],"evaluate":[69],"LLMs'":[70],"semantic":[71,134],"understanding":[72],"and":[73,97,110,145],"reasoning":[74],"abilities":[75],"over":[76,185],"aggregated":[77],"text":[78,187],"data.We":[79],"apply":[80],"our":[81],"benchmark":[82],"on":[83,107,169],"diverse":[84],"Twitter":[85],"datasets":[86],"covering":[87],"various":[88],"tasks,":[90],"including":[91],"sentiment":[92],"analysis,":[93],"hate":[94],"speech":[95],"detection,":[96],"emotion":[98],"recognition.Our":[99],"results":[100],"reveal":[101],"that":[102],"performance":[104,129,165],"depends":[105],"heavily":[106],"input":[108,149],"scale":[109],"complexity":[112,127],"sources,":[116],"declining":[117],"noticeably":[118],"multilabel":[120],"or":[121],"target-dependent":[122],"scenarios.In":[123],"addition,":[124],"task":[126],"increases,":[128],"drops":[130],"progressively":[131],"from":[132],"basic":[133],"existence":[135],"identification":[136],"more":[138],"demanding":[139],"operations":[140],"comparison,":[143],"counting,":[144],"calculation.Furthermore,":[146],"size":[150],"grows":[151],"beyond":[152],"500":[153],"instances,":[154],"identify":[156],"common":[158],"limitation":[159],"across":[160],"LLMs,":[161],"Open-weights":[163],"models:":[164],"degrades":[166],"substantially,":[167],"especially":[168],"numerical":[170],"tasks.These":[171],"findings":[172],"highlight":[173],"critical":[174],"architectural":[175],"bottlenecks":[176],"current":[178],"for":[180],"performing":[181],"rigorous":[182],"quantitative":[183],"large":[186],"collections.":[188]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}