{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T17:41:39Z","timestamp":1770313299005,"version":"3.49.0"},"reference-count":62,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["10063933"],"award-info":[{"award-number":["10063933"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["10062587"],"award-info":[{"award-number":["10062587"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["10064231"],"award-info":[{"award-number":["10064231"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Public authorities frequently conduct surveys and analyze data from citizens, a process that is often labor\u2010intensive when performed manually. This paper explores how generative artificial intelligence (GenAI) can assist in automating data analysis for public authorities. In this respect, we investigate the potential of large language models (LLMs) to perform sentiment analysis and summarization of unstructured data as smart services. Using data from the East Bristol livable neighborhood (EBLN) as a case study, we assess the accuracy and precision of these models and validate the results against ground truth data and expert evaluations. Our findings indicate that sentiment classification achieved over 90% accuracy. Additionally, incorporating retrieval\u2010augmented generation (RAG) further enhances the results obtained. Comparative analysis revealed that LLMs achieved superior performance over traditional summarization techniques based on domain expert evaluation. These results suggest that LLMs offer a promising and impactful approach to improving the efficiency of qualitative analysis, though further research is required to enhance their accuracy and usefulness.<\/jats:p>","DOI":"10.1002\/cpe.70547","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T11:18:15Z","timestamp":1770117495000},"update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging LLMs for Smart Cities Qualitative Data Analysis"],"prefix":"10.1002","volume":"38","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0006-0195-0827","authenticated-orcid":false,"given":"Elisa","family":"Covato","sequence":"first","affiliation":[{"name":"School of Computing and Creative Technologies University of the West of England  Bristol UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kamran","family":"Soomro","sequence":"additional","affiliation":[{"name":"School of Computing and Creative Technologies University of the West of England  Bristol UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaheer","family":"Khan","sequence":"additional","affiliation":[{"name":"School of Computing and Creative Technologies University of the West of England  Bristol UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Bilal","sequence":"additional","affiliation":[{"name":"Birmingham City Business School Birmingham City University  Birmingham UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roisin","family":"Cormack","sequence":"additional","affiliation":[{"name":"Bristol City Council  Bristol UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Green","sequence":"additional","affiliation":[{"name":"Bristol City Council  Bristol UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"key":"e_1_2_13_2_1","doi-asserted-by":"publisher","DOI":"10.1108\/TG\u201009\u20102013\u20100030"},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cities.2011.11.012"},{"key":"e_1_2_13_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2011.10.003"},{"key":"e_1_2_13_5_1","first-page":"359","volume-title":"Big Data Analytics for Smart Cities","author":"Bassoo V.","year":"2018"},{"key":"e_1_2_13_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1319"},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2844341"},{"key":"e_1_2_13_8_1","first-page":"235","volume-title":"Proceedings of the 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS)","author":"Zaouali K.","year":"2018"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-954X.1979.tb00361.x"},{"key":"e_1_2_13_10_1","unstructured":"H.Naveed A. U.Khan S.Qiu et al. \u201cA Comprehensive Overview of Large Language Models \u201d(2024) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2307.06435."},{"key":"e_1_2_13_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40547\u2010024\u201000143\u20104"},{"key":"e_1_2_13_12_1","unstructured":"L.BasyalandM.Sanghvi \u201cText Summarization Using Large Language Models: A Comparative Study of MPT\u20107b\u2010Instruct Falcon\u20107b\u2010Instruct and Openai Chat\u2010GPT Models \u201d(2023) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2310.10449."},{"key":"e_1_2_13_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00632"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581754.3584136"},{"key":"e_1_2_13_15_1","doi-asserted-by":"crossref","unstructured":"Z.Rasheed M.Waseem A.Ahmad et al. \u201cCan Large Language Models Serve as Data Analysts? A Multi\u2010Agent Assisted Approach for Qualitative Data Analysis \u201d(2024) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2402.01386.","DOI":"10.2139\/ssrn.5149683"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.1177\/16094069241231168"},{"key":"e_1_2_13_17_1","doi-asserted-by":"crossref","unstructured":"I. H.Sarker \u201cMachine Learning: Algorithms Real\u2010World Applications and Research Directions \u201d(2021).","DOI":"10.20944\/preprints202103.0216.v1"},{"key":"e_1_2_13_18_1","first-page":"830","volume-title":"Proceedings of the National Conference on Artificial Intelligence","author":"Chang M. W.","year":"2008"},{"key":"e_1_2_13_19_1","unstructured":"Z.Wang Y.Pang andY.Lin \u201cLarge Language Models Are Zero\u2010Shot Text Classifiers \u201d(2023) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2312.01044."},{"key":"e_1_2_13_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_2_13_21_1","unstructured":"G.Orlanski \u201cEvaluating Prompts Across Multiple Choice Tasks in a Zero\u2010Shot Setting \u201d(2022) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2203.15754."},{"key":"e_1_2_13_22_1","unstructured":"J.Kaddour J.Harris M.Mozes H.Bradley R.Raileanu andR.McHardy \u201cChallenges and Applications of Large Language Models \u201d(2023) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2307.10169."},{"key":"e_1_2_13_23_1","unstructured":"P.Lewis E.Perez A.Piktus et al. \u201cRetrieval\u2010Augmented Generation for Knowledge\u2010Intensive Nlp Tasks \u201d(2021) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2005.11401."},{"key":"e_1_2_13_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29728"},{"key":"e_1_2_13_25_1","unstructured":"A.Balaguer V.Benara R. L.deFreitas Cunha et al. \u201cRag vs Fine\u2010Tuning: Pipelines Tradeoffs and a Case Study on Agriculture \u201d2024 https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2401.08406."},{"key":"e_1_2_13_26_1","first-page":"68","volume-title":"Proceedings of the 2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)","author":"Davoodian Z.","year":"2024"},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41060\u2010024\u201000594\u2010x"},{"key":"e_1_2_13_28_1","doi-asserted-by":"publisher","DOI":"10.31796\/ogummf.1303569"},{"key":"e_1_2_13_29_1","doi-asserted-by":"crossref","unstructured":"A.Izzidien H.Sargeant andF.Steffek \u201cLLM vs. Lawyers: Identifying a Subset of Summary Judgments in a Large UK Case Law Dataset \u201d(2024) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2403.04791.","DOI":"10.2139\/ssrn.4746305"},{"key":"e_1_2_13_30_1","first-page":"24:1","volume-title":"Proceedings of the 12th International Conference on Geographic Information Science (GIScience 2023). Volume 277 of Leibniz International Proceedings in Informatics (LIPIcs)","author":"Covato E.","year":"2023"},{"issue":"70","key":"e_1_2_13_31_1","first-page":"1","article-title":"Scaling Instruction\u2010Finetuned Language Models","volume":"25","author":"Chung H. W.","year":"2024","journal-title":"Journal of Machine Learning Research"},{"issue":"140","key":"e_1_2_13_32_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning With a Unified Text\u2010To\u2010Text Transformer","volume":"21","author":"Raffel C.","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_13_33_1","unstructured":"W.Zhang Y.Deng B.Liu S. J.Pan andL.Bing \u201cSentiment Analysis in the Era of Large Language Models: A Reality Check \u201d(2023) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2305.15005."},{"key":"e_1_2_13_34_1","unstructured":"T. B.Brown B.Mann N.Ryder et al. \u201cLanguage Models are Few\u2010Shot Learners \u201d(2020) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2005.14165."},{"key":"e_1_2_13_35_1","unstructured":"L.Mei J.Yao Y.Ge et al. \u201cA Survey of Context Engineering for Large Language Models \u201d(2025) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2507.13334."},{"key":"e_1_2_13_36_1","first-page":"1546","volume-title":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers","author":"Saeidi M.","year":"2016"},{"key":"e_1_2_13_37_1","unstructured":"M.Li H.Chen Y.Wang et al. \u201cUnderstanding and Mitigating the bias Inheritance in Llm\u2010Based Data Augmentation on Downstream Tasks \u201d(2025) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2502.04419."},{"key":"e_1_2_13_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128255"},{"key":"e_1_2_13_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41870\u2010022\u201000863\u20107"},{"key":"e_1_2_13_40_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"e_1_2_13_41_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1523"},{"key":"e_1_2_13_42_1","unstructured":"M.Lewis Y.Liu N.Goyal et al. \u201cBart: Denoising Sequence\u2010To\u2010Sequence Pre\u2010Training for Natural Language Generation Translation and Comprehension \u201d(2019) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/1910.13461."},{"key":"e_1_2_13_43_1","unstructured":"J.Zhang Y.Zhao M.Saleh andP. J.Liu \u201cPegasus: Pre\u2010Training With Extracted Gap\u2010Sentences for Abstractive Summarization \u201d(2020) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/1912.08777."},{"key":"e_1_2_13_44_1","first-page":"1693","volume-title":"Advances in Neural Information Processing Systems","author":"Hermann K. M.","year":"2015"},{"key":"e_1_2_13_45_1","unstructured":"A.Grattafiori A.Dubey A.Jauhri et al. \u201cThe Llama 3 Herd of Models \u201d(2024) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2407.21783."},{"key":"e_1_2_13_46_1","unstructured":"A. Q.Jiang A.Sablayrolles A.Mensch et al. \u201cMistral 7b \u201d(2023) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2310.06825."},{"key":"e_1_2_13_47_1","unstructured":"S.Schulhoff M.Ilie N.Balepur et al. \u201cThe Prompt Report: A Systematic Survey of Prompt Engineering Techniques \u201d(2025) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2406.06608."},{"key":"e_1_2_13_48_1","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1145\/3603287.3651183","volume-title":"Proceedings of the 2024 ACM Southeast Conference","author":"Stigall W.","year":"2024"},{"key":"e_1_2_13_49_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00524"},{"key":"e_1_2_13_50_1","unstructured":"P.M\u00e6hlum D.Samuel R. M.Norman et al. \u201cIt's Difficult To Be Neutral\u00a0\u2013\u00a0Human and Llm\u2010Based Sentiment Annotation of Patient Comments \u201d(2024) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2404.18832."},{"key":"e_1_2_13_51_1","unstructured":"J.Hoffmann S.Borgeaud A.Mensch et al. \u201cTraining Compute\u2010Optimal Large Language Models \u201d(2022) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2203.15556."},{"key":"e_1_2_13_52_1","unstructured":"J.Kaplan S.McCandlish T.Henighan et al. Scaling Laws for Neural Language Models(2020) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2001.08361."},{"key":"e_1_2_13_53_1","unstructured":"Y.Liu X.Zhu Z.Shen et al. \u201cDo Large Language Models Possess Sensitive to Sentiment?\u201d(2025) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2409.02370."},{"key":"e_1_2_13_54_1","unstructured":"Y.Duan F.Tang K.Wu et al. \u201cRanking of Large Language Model (LLM) Regional Bias\u2014DIKWP Research Group International Standard Evaluation\u201d(2024)."},{"key":"e_1_2_13_55_1","unstructured":"R.Manvi S.Khanna M.Burke D.Lobell andS.Ermon \u201cLarge Language Models Are Geographically Biased \u201d(2024) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2402.02680."},{"key":"e_1_2_13_56_1","first-page":"100","volume-title":"Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures","author":"Liu J.","year":"2022"},{"key":"e_1_2_13_57_1","doi-asserted-by":"crossref","first-page":"8086","DOI":"10.18653\/v1\/2022.acl-long.556","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Lu Y.","year":"2022"},{"key":"e_1_2_13_58_1","doi-asserted-by":"crossref","first-page":"6784","DOI":"10.18653\/v1\/2024.naacl-long.378","volume-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","author":"Reif Y.","year":"2024"},{"key":"e_1_2_13_59_1","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"Yu G.","year":"2023"},{"key":"e_1_2_13_60_1","unstructured":"J.Devlin M.\u2010W.Chang K.Lee andK.Toutanova \u201cBert: Pre\u2010Training of Deep Bidirectional Transformers for Language Understanding \u201d(2019) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/1810.04805."},{"key":"e_1_2_13_61_1","unstructured":"C.Sun X.Qiu Y.Xu andX.Huang \u201cHow to Fine\u2010Tune Bert for Text Classification?\u201d(2020) https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/1905.05583."},{"key":"e_1_2_13_62_1","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/978-3-031-87639-4_16","volume-title":"Intelligent Distributed Computing XVII","author":"Covato E.","year":"2025"},{"key":"e_1_2_13_63_1","volume-title":"Technical","author":"Hong K.","year":"2025"}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70547","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cpe.70547","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T03:06:23Z","timestamp":1770260783000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":62,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1002\/cpe.70547"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1002\/cpe.70547","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"2024-12-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70547"}}