Mapping Research Trends in Generative Artificial Intelligence: A Bibliometric and Network Analysis

This study investigates the integration of user?generated social media data into Public Health Surveillance (PHS) through a dynamic, multidimensional analytical framework. Existing approaches largely rely on offline processing of static social network data, leaving a gap in methods capable of handling high?velocity, continuously evolving social streams. We propose a dynamic model that updates multidimensional representations of social data in real time using unsupervised text?mining techniques. By jointly analyzing semantic content and temporal posting patterns, the framework identifies emerging events, topics, and influential or relevant users. To enhance the utility of social data for PHS, we introduce quantitative quality measures that filter low?value or out?of?domain user profiles. The approach is evaluated on a multi?year Twitter data stream, demonstrating its effectiveness in isolating meaningful signals and excluding noisy contributors. We further outline procedures for deriving user profiles from self?descriptions to support targeted filtering. The results show that the proposed model enables robust topic and event detection, audience characterization, and impact assessment. Overall, the dynamic multidimensional framework provides a scalable and adaptable foundation for incorporating social media intelligence into PHS systems.

[1] B. M. Gomes, C. B. Rebelo, and L. A. De Sousa, “Public health, surveillance systems and preventive medicine in an interconnected world,” in One Health, 2022, pp. 33–71. doi: 10.1016/b978-0-12-822794-7.00006-x.

[2] A. Gupta and R. Katarya, “Social media based surveillance systems for healthcare using machine learning: A systematic review,” Journal of Biomedical Informatics, vol. 108, p. 103500, Jul. 2020, doi: 10.1016/j.jbi.2020.103500.

[3] O. Edo-Osagie, B. De La Iglesia, I. Lake, and O. Edeghere, “A scoping review of the use of Twitter for public health research,” Computers in Biology and Medicine, vol. 122, p. 103770, May 2020, doi: 10.1016/j.compbiomed.2020.103770.

[4] L. Zhou, D. Zhang, C. C. Yang, and Y. Wang, “Harnessing social media for health information management,” Electronic Commerce Research and Applications, vol. 27, pp. 139–151, Dec. 2017, doi: 10.1016/j.elerap.2017.12.003.

[5] H. ?gel-Balaban, “The use of online social network sites during the COVID-19 pandemic as a protective or risk factor for well-being of university students,” Cyberpsychology Journal of Psychosocial Research on Cyberspace, vol. 16, no. 3, Jun. 2022, doi: 10.5817/cp2022-3-4.

[6] Y. Wang et al., “From virus to viral: content analysis of HIV-related Twitter messages among young men in the U.S.,” BMC Digital Health, vol. 2, no. 1, Jul. 2024, doi: 10.1186/s44247-024-00102-y.

[7] O. Edo-Osagie, B. De La Iglesia, I. Lake, and O. Edeghere, “A scoping review of the use of Twitter for public health research,” Computers in Biology and Medicine, vol. 122, p. 103770, May 2020, doi: 10.1016/j.compbiomed.2020.103770.

[8] J. Dietrich et al., “Adverse Events in Twitter-Development of a Benchmark Reference Dataset: Results from IMI WEB-RADR,” Drug Safety, vol. 43, no. 5, pp. 467–478, Jan. 2020, doi: 10.1007/s40264-020-00912-9.

[9] A. Rawat, M. A. Wani, M. ElAffendi, A. S. Imran, Z. Kastrati, and S. M. Daudpota, “Drug adverse event detection using Text-Based Convolutional Neural Networks (TextCNN) technique,” Electronics, vol. 11, no. 20, p. 3336, Oct. 2022, doi: 10.3390/electronics11203336.

[10] “Public health surveillance for COVID-19 using Twitter sentiment analysis,” Texila International Journal of Public Health, vol. 12, no. 3, Sep. 2024, doi: 10.21522/tijph.2013.12.03.art034.

[11] M. Mysl?n, S.-H. Zhu, W. Chapman, and M. Conway, “Using Twitter to examine smoking behavior and perceptions of emerging tobacco products,” Journal of Medical Internet Research, vol. 15, no. 8, p. e174, Aug. 2013, doi: 10.2196/jmir.2534.

[12] X. Ji, S. A. Chun, Z. Wei, and J. Geller, “Twitter sentiment classification for measuring public health concerns,” Social Network Analysis and Mining, vol. 5, no. 1, p. 13, May 2015, doi: 10.1007/s13278-015-0253-5.

[13] A. Alessa and M. Faezipour, “Flu outbreak prediction using Twitter posts Classification and linear regression with Historical Centers for Disease Control and Prevention Reports: Prediction Framework Study,” JMIR Public Health and Surveillance, vol. 5, no. 2, p. e12383, May 2019, doi: 10.2196/12383.

[14] P. P. Morita, I. Z. Hussain, J. Kaur, M. Lotto, and Z. A. Butt, “Tweeting for health Using Real-time mining and Artificial Intelligence–Based Analytics: Design and development of a big data ecosystem for detecting and analyzing misinformation on Twitter,” Journal of Medical Internet Research, vol. 25, p. e44356, Mar. 2023, doi: 10.2196/44356.

[15] P. Missier et al., “Tracking dengue epidemics using Twitter content classification and topic modelling,” in Lecture notes in computer science, 2016, pp. 80–92. doi: 10.1007/978-3-319-46963-8_7.

[16] K. W. Prier, M. S. Smith, C. Giraud-Carrier, and C. L. Hanson, “Identifying Health-Related topics on Twitter,” in Lecture notes in computer science, 2011, pp. 18–25. doi: 10.1007/978-3-642-19656-0_4.

[17] W. H. Bangyal, M. Iqbal, A. Bashir, and G. Ubakanma, Polarity Classification of Twitter Data Using Machine Learning Approach. 2023, pp. 1–6. doi: 10.1109/hccs59561.2023.10452557.

[18] Y. Liscano, L. a. A. Arrieta, J. F. Montenegro, D. Prieto-Alvarado, and J. Ordo?ez, “Early warning of infectious disease outbreaks using social media and digital data: A scoping review,” International Journal of Environmental Research and Public Health, vol. 22, no. 7, p. 1104, Jul. 2025, doi: 10.3390/ijerph22071104.

[19] M. D. Soufi, P. R. Hachesu, and R. Ferdousi, “Oncology Informatics for Lynch Syndrome Research and Care: A Literature review,” JCO Clinical Cancer Informatics, vol. 6, no. 6, p. e2200087, Nov. 2022, doi: 10.1200/cci.22.00087.

[20] S. Amin, M. I. Uddin, M. A. Zeb, A. A. Alarood, M. Mahmoud, and M. H. Alkinani, “Detecting information on the spread of dengue on Twitter using artificial neural networks,” Computers, Materials & Continua/Computers, Materials & Continua (Print), vol. 67, no. 1, pp. 1317–1332, Jan. 2021, doi: 10.32604/cmc.2021.014733.

[21] J. Sleigh, J. Amann, M. Schneider, and E. Vayena, “Qualitative analysis of visual risk communication on twitter during the Covid-19 pandemic,” BMC Public Health, vol. 21, no. 1, p. 810, Apr. 2021, doi: 10.1186/s12889-021-10851-4.

[22] A. H. Zadeh, H. M. Zolbanin, R. Sharda, and D. Delen, “Social media for nowcasting flu activity: Spatio-Temporal Big data analysis,” Information Systems Frontiers, vol. 21, no. 4, pp. 743–760, Jan. 2019, doi: 10.1007/s10796-018-9893-0.

[23] A. Z. Klein, A. Magge, K. O’Connor, J. I. F. Amaro, D. Weissenbacher, and G. G. Hernandez, “Toward using Twitter for tracking COVID-19: a natural language processing pipeline and exploratory data set,” Journal of Medical Internet Research, vol. 23, no. 1, p. e25314, Jan. 2021, doi: 10.2196/25314.

[24] G. Livraga, A. Motta, and M. Viviani, Assessing User Privacy on Social Media: The Twitter Case Study. 2022, pp. 1–9. doi: 10.1145/3524010.3539502.

[25] Leon, “Data Warehouse Building: A comprehensive Overview,” BI4Dynamics - Business Intelligence for Microsoft Dynamics, Jan. 06, 2025. https://www.bi4dynamics.com/data-warehouse-building-a-comprehensive-overview/

[26] E. Blomqvist, “The use of Semantic Web technologies for decision support – a survey,” Semantic Web, vol. 5, no. 3, pp. 177–201, Jan. 2014, doi: 10.3233/sw-2012-0084.

[27] S. Moon and D. Iacobucci, “Social Media Analytics and its applications in marketing,” Foundations and Trends® in Marketing, vol. 15, no. 4, pp. 213–292, Mar. 2022, doi: 10.1561/1700000073.

[28] E. French and B. T. McInnes, “An overview of biomedical entity linking throughout the years,” Journal of Biomedical Informatics, vol. 137, p. 104252, Dec. 2022, doi: 10.1016/j.jbi.2022.104252.

[29] K. Mouyassir, M. Hanine, and H. Ouahmane, “Business Intelligence Model to analyze Social Media through Big Data analytics,” SHS Web of Conferences, vol. 119, p. 07006, Jan. 2021, doi: 10.1051/shsconf/202111907006.

[30] B. Alabduallah, A. Banga, N. Iqbal, A. Ikram, and H. Diab, “Advancing cryptographic security with a new Delannoy-Derived Chaotic S-Box,” IEEE Access, vol. 12, pp. 82926–82937, Jan. 2024, doi: 10.1109/access.2024.3410668.

[31] A. Mahajan, B. Kaushik, M. K. I. Rahmani, and A. S. Banga, “A hybrid feature selection and ensemble stacked learning models on Multi-Variant CVD datasets for effective classification,” IEEE Access, vol. 12, pp. 87023–87038, Jan. 2024, doi: 10.1109/access.2024.3412077.

[32] E. F. Siddiqui, M. Haleem, S. F. Ahmad, A. Salhi, A. T. Zamani, and N. Varish, “A Multi-Layered AI-Driven cybersecurity architecture: integrating entropy analytics, fuzzy reasoning, game theory, and Multi-Agent reinforcement learning for adaptive threat defense,” IEEE Access, vol. 13, pp. 170235–170257, Jan. 2025, doi: 10.1109/access.2025.3610526.