{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:46:51Z","timestamp":1760060811926,"version":"build-2065373602"},"reference-count":20,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:00:00Z","timestamp":1758672000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>This study investigates sentiment analysis of X data about the National Health Service (NHS) during a politically charged period, using lexicon-based, machine learning, and deep learning approaches, as well as topic modelling and aspect-based sentiment analysis (ABSA). This study is distinct in its comparative evaluation of sentiment analysis techniques on NHS-related tweets during a politically sensitive period, offering insights into public opinion shaped by political discourse. A dataset of 35,000 tweets collected and analysed using various techniques, including VADER, TextBlob, Naive Bayes, Support Vector Machines, Logistic Regression, Ensemble Learning, and BERT. Unlike previous studies that focus on structured feedback or general sentiment, this research uniquely explores unstructured public discourse during an election period, capturing real-time political sentiment towards NHS policies. The sentiment distribution from lexicon-based methods depicted that the presence of stop words could affect model performance. While all models achieved high accuracy on the validation dataset, challenges such as class imbalance and limited labelled data impacted performance, with signs of overfitting observed. Topic modelling identified nine topic clusters, with \u201cwaiting list,\u201d \u201cservice,\u201d and \u201cimmigration\u201d carrying negative sentiments. At the same time, words like \u201cthank,\u201d \u201csupport,\u201d \u201ccare,\u201d and \u201cteam\u201d had the most positive sentiments, reflecting public delight in these areas. ABSA identified positive sentiments towards aspects like \u201cuseful service\u201d. This study contributes a comparative framework for evaluating sentiment analysis techniques in politically contextualised healthcare discourse, offering insights for policymakers and researchers. The study underscores the importance of data quality in sentiment analysis. Future research should consider incorporating multilingual datasets, extending data collection periods, optimising deep learning models, and employing hybrid approaches to enhance performance.<\/jats:p>","DOI":"10.3390\/bdcc9100244","type":"journal-article","created":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T09:43:12Z","timestamp":1758706992000},"page":"244","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Comparative Study of X Data About the NHS Using Sentiment Analysis"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4566-7144","authenticated-orcid":false,"given":"Saeed Ur","family":"Rehman","sequence":"first","affiliation":[{"name":"Faculty of Science and Engineering, University of Hull, Hull HU6 7RX, UK"}]},{"given":"Obi Oluchi","family":"Blessing","sequence":"additional","affiliation":[{"name":"Faculty of Science and Engineering, University of Hull, Hull HU6 7RX, UK"}]},{"given":"Anwar","family":"Ali","sequence":"additional","affiliation":[{"name":"Faculty of Science and Engineering, Swansea University Bay Campus, Swansea SA1 8EN, UK"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Yau, N. (2024). Visualize This: The FlowingData Guide to Design, Visualization, and Statistics, John Wiley & Sons.","DOI":"10.1002\/9781394319817"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Gohil, S., Vuik, S., and Darzi, A. (2018). Sentiment analysis of health care tweets: Review of the methods used. JMIR Public Health Surveill., 4.","DOI":"10.2196\/publichealth.5789"},{"key":"ref_3","unstructured":"Liu, B. (2010). Sentiment Analysis and Subjectivity. Handbook of Natural Language Processing, Chapman & Hall\/CRC Press. [2nd ed.]."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.procs.2016.05.124","article-title":"Sentiment analysis: A comparative study on different approaches","volume":"87","author":"Devika","year":"2016","journal-title":"Procedia Comput. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"McKay, K., Wayland, S., Ferguson, D., Petty, J., and Kennedy, E. (2021). \u201cAt Least until the Second Wave Comes\u2026\u201d: A X analysis of the NHS and COVID-19 between March and June 2020. Int. J. Environ. Res. Public Health, 18.","DOI":"10.3390\/ijerph18083943"},{"key":"ref_6","unstructured":"Labour Party (2024, August 13). Build an NHS Fit for the Future. Available online: https:\/\/labour.org.uk\/change\/build-an-nhs-fit-for-the-future\/."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4018\/JOEUC.294901","article-title":"Topic modelling and sentiment analysis of global warming tweets: Evidence from big data analysis","volume":"34","author":"Qiao","year":"2022","journal-title":"J. Organ. End User Comput."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Lyu, J.C., Han, E.L., and Luli, G.K. (2021). COVID-19 Vaccine\u2013Related Discussion on X: Topic Modeling and Sentiment Analysis. J. Med. Internet Res., 23.","DOI":"10.2196\/preprints.24435"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Bahja, M., and Lycett, M. (2016, January 6\u20139). Identifying patient experience from online resources via sentiment analysis and topic modelling. Proceedings of the 3rd IEEE\/ACM International Conference on Big Data Computing, Applications and Technologies, Shanghai, China.","DOI":"10.1145\/3006299.3006335"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Parycek, P., Glassey, O., Janssen, M., Jochen Scholl, H., Tambouris, E., Kalampokis, E., and Virkar, S. (2018). Understanding Public Healthcare Service Quality from Social Media. Electronic Government, Proceedings of the 17th IFIP WG 8.5 International Conference, EGOV 2018, Krems, Austria, 3\u20135 September 2018, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-319-98690-6"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kbaier, D., Kane, A., McJury, M., and Kenny, I. (2024). Prevalence of health misinformation on social media\u2014Challenges and mitigation before, during, and beyond the COVID-19 pandemic: Scoping literature review. J. Med. Internet Res., 26.","DOI":"10.2196\/38786"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Mao, Y., Qun, L., and Yu, Z. (2024). Sentiment analysis methods, applications, and challenges: A systematic literature review. J. King Saud Univ. Comput. Inf. Sci., 36.","DOI":"10.1016\/j.jksuci.2024.102048"},{"key":"ref_13","first-page":"543","article-title":"Serendio: Simple and Practical lexicon based approach to Sentiment Analysis","volume":"Volume 2","author":"Palanisamy","year":"2013","journal-title":"Second Joint Conference on Lexical and Computational Semantics (SEM), Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013), Atlanta, GA, USA, 14\u201315 June 2013"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"79","DOI":"10.3991\/ijet.v15i15.14467","article-title":"X sentiment analysis approaches: A survey","volume":"15","author":"Adwan","year":"2020","journal-title":"Int. J. Emerg. Technol. Learn."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Alexander, G., Bahja, M., and Butt, G.F. (2022). Automating large-scale health care service feedback analysis: Sentiment analysis and topic modelling study. JMIR Med. Inform., 10.","DOI":"10.2196\/29385"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Bouazizi, M., and Ohtsuki, T. (2016, January 4\u20138). Sentiment analysis in X: From classification to quantification of sentiments within tweets. Proceedings of the 2016 IEEE Global Communications Conference (GLOBECOM), Washington, DC, USA.","DOI":"10.1109\/GLOCOM.2016.7842262"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Desai, M., and Mehta, M.A. (2016, January 29\u201330). Techniques for sentiment analysis of X data: A comprehensive survey. Proceedings of the 2016 International Conference on Computing, Communication and Automation (ICCCA), Greater Noida, India.","DOI":"10.1109\/CCAA.2016.7813707"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ghag, K.V., and Shah, K. (2015, January 10\u201312). Comparative analysis of effect of stop words removal on sentiment classification. Proceedings of the 2015 International Conference on Computer, Communication and Control (IC4), Indore, India.","DOI":"10.1109\/IC4.2015.7375527"},{"key":"ref_19","first-page":"265","article-title":"LSTM, VADER and TF-IDF based hybrid sentiment analysis model","volume":"12","author":"Chiny","year":"2021","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_20","first-page":"352","article-title":"Comparing BERT against traditional machine learning text classification","volume":"2","year":"2020","journal-title":"J. Comput. Cogn. Eng."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/10\/244\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:48:44Z","timestamp":1760035724000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/10\/244"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,24]]},"references-count":20,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["bdcc9100244"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9100244","relation":{},"ISSN":["2504-2289"],"issn-type":[{"type":"electronic","value":"2504-2289"}],"subject":[],"published":{"date-parts":[[2025,9,24]]}}}