News Science

News Science

Big Data–Driven Public Opinion Mining: A Conceptual Framework for Evidence-Informed Policymaking

Document Type : Original Article

Authors
Ghasem Safaei Nejad 1
Seyed Mehdi Sharifi 2
1 Ph. D. in Media Management, Alborz Campus, University of Tehran, Tehran, Iran. Email: safaeinejad@ut.ac.ir
2 Associate Prof., Department of Media Management, College of Management, University of Tehran, Tehran, Iran. Email: Sharifee@ut.ac.ir
10.22034/lrsi.2026.550018.1443
Abstract
Objective: The present study was conducted with the aim of designing a conceptual model for national opinion mining based on big data. The necessity of this research arises from the fact that traditional opinion polling methods, such as questionnaires and interviews, face limitations including high costs, time delays, and restricted geographical coverage. In contrast, big data generated from citizens’ digital interactions on social media and the web provides unprecedented capacity for real-time monitoring of public opinion dynamics and supporting evidence-informed policymaking.
Methods: This research is developmental–theoretical in nature and was carried out with a qualitative–inferential approach. The data used were collected from secondary sources, including peer-reviewed scientific articles and national and international policy reports. The methodology was based on theoretical analysis and conceptual synthesis. First, a systematic literature review was conducted to identify key concepts and research gaps. Then, using conceptual inference, the essential components and relationships of the opinion mining process were extracted and organized into a five-layer model: (1) data collection, (2) cleaning and preprocessing, (3) analysis and clustering, (4) interpretation and validation, and (5) feedback and application.
Results: The findings of the study indicated that the proposed model can overcome the limitations of traditional opinion polling and enable scalable, multidimensional, and real-time monitoring of public opinion. In the analysis layer, the use of natural language processing and machine learning algorithms (sentiment analysis, topic modeling, clustering, and social network analysis) made it possible to identify emotional trends, dominant topics, and key actors. In the interpretation layer, expert feedback was obtained to enhance the validity of the model. Finally, the feedback and application layer demonstrated that the model’s outputs can be delivered through interactive dashboards and policy briefs to decision-making institutions, thereby serving to complement and strengthen traditional opinion polling through data-driven analysis.
Conclusions: The conceptual model of national opinion mining based on big data provides a novel framework for a gradual transition in certain functions and for complementing traditional opinion polling through data-driven analysis. By reducing costs and time, increasing accuracy and coverage, and enabling real-time insights, this model can serve as a strategic tool for evidence-informed policymaking at the national level. Nevertheless, challenges such as the need for robust computational infrastructure, adherence to ethical and privacy principles, and optimization of natural language processing algorithms for Persian must be taken into account. Overall, the findings of this study can serve as a foundation for developing indigenous opinion mining tools and enhancing data-driven decision-making capacity in Iran.
Keywords
Opinion Mining
Big Data
Sentiment Analysis
Policymaking
Social Media
References:
Abdalla, H. B. (2022). A brief survey on big data: Technologies, terminologies and data intensive applications. Journal of Big Data, 9, Article 107, 1–36. https://doi.org/10.1186/s40537-022-00659-3
Akbas, E. (2017). Opinion mining on non-English short text. In M. Kryszkiewicz, A. Appice, D. Ślęzak, H. Rybinski, A. Skowron, & Z. Raś (Eds.), Foundations of Intelligent Systems: ISMIS 2017 (Lecture Notes in Computer Science, Vol. 10352, pp. 1–10). Springer, Cham. https://doi.org/10.1007/978-3-319-60438-1_41
Aladeemy, A. A., Alzahrani, A., Algarni, M. H., Khalaff, O. I., Wong, W.-K., & Aqburi, S. (2024). Advancements and challenges in Arabic sentiment analysis: A decade of methodologies, applications, and resource development. Heliyon, 10(21), e39786. https://doi.org/10.1016/j.heliyon.2024.e39786
Albalawi, R., Yeap, T. H., & Benyoucef, M. (2020). Using topic modeling methods for short-text data: A comparative analysis. Frontiers in Artificial Intelligence, 3, Article 42. https://doi.org/10.3389/frai.2020.00042
Atkin, C., & Gaudino, J. (1984). The impact of polling on the mass media. The ANNALS of the American Academy of Political and Social Science, 472(1), 119–128. https://doi.org/10.1177/0002716284472001011
Bovet, A., Morone, F., & Makse, H. (2018). Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump. Scientific Reports, 8, Article 6789, 1–16. https://doi.org/10.1038/s41598-018-26951-y
Cen, Y., & Wang, Y. (2016). Social public opinion analysis and decision making support with big data. Data Analysis and Knowledge Discovery, 32(7), 3–11. https://doi.org/10.11925/infotech.1003-3513.2016.07.02
Cortis, K., & Davis, B. (2021). Over a decade of social opinion mining: A systematic review. Artificial Intelligence Review, 54(7), 4873–4965. https://doi.org/10.1007/s10462-021-10030-2
Farrokhi, M. (2004). Public opinion polling in Iran. Majlis Research Center (Iranian Parliament Research Center). (In Persian)
Farzindar, A., & Louis, A. (2016). Natural language processing for social media [Book review]. Computational Linguistics, 42(4), 833–836. https://doi.org/10.1162/COLI_r_00270
Featherstone, J. D., & Barnett, G. A. (2020). Validating sentiment analysis on opinion mining using self-reported attitude scores. In 2020 Seventh International Conference on Social Networks Analysis, Management and Security (SNAMS) (pp. 1–4). Paris, France. https://doi.org/10.1109/SNAMS52053.2020.9336540
Heidari, E. (2020). A study of big data in social networks. New Research Quarterly in Humanities, New Series(26), 109–130. (In Persian)
Lasswell, H. D. (1948). The structure and function of communication in society. In L. Bryson (Ed.), The communication of ideas (pp. 37–51). Harper & Row.
Lincoln, Y. S., & Guba, E. G. (1985). Naturalistic inquiry. Sage Publications.
Miller, P. V. (2017). Is there a future for surveys? Public Opinion Quarterly, 81(S1), 205–212. https://doi.org/10.1093/poq/nfx008
Patil, A. S. (2016). Opinion mining techniques for non-English languages: An overview. International Journal of Computational Linguistics (IJCL), 7(2), 1–16.
Rahmanian, P., Mousavi, S. M. R., & Sadraldini, M. H. (2025). Multimodal sentiment analysis in Persian using transformer-based models and sentiment recognition capsules. Theoretical and Applied Research in Machine Intelligence, 3(1), 51–67. https://doi.org/10.22034/abmir.2025.23347.1137 (In Persian)
Rajabi, Z., Velvi, M. R., & Hourali, M. (2022). A review of sentiment analysis methods in Persian texts. Signal and Data Processing, 10(52), 107–132. (In Persian)
Sandelowski, M., Barroso, J., & Voils, C. I. (2007). Using qualitative metasummary to synthesize qualitative and quantitative descriptive findings. Research in Nursing & Health, 30(1), 99–111. https://doi.org/10.1002/nur.20176
Schaefer, T., & Brooker, R. (2005). Public opinion in the 21st century: Let the people speak? Houghton Mifflin Harcourt Publishing Company.
Shang, S., Shi, M., Shang, W., & Hong, Z. (2015). Research on public opinion based on big data. In 2015 IEEE/ACIS 14th International Conference on Computer and Information Science (ICIS) (pp. 559–562). https://doi.org/10.1109/ICIS.2015.7166655
Shi, Z., & Agrawal, R. (2025). A comprehensive survey of contemporary Arabic sentiment analysis: Methods, challenges, and future directions. In Findings of the Association for Computational Linguistics: NAACL 2025 (pp. 3760–3772). Albuquerque, NM: Association for Computational Linguistics.
Stahl, B. C. (2025). The ethics of data and its governance: A discourse theoretical approach. Information, 16(6), 497. https://doi.org/10.3390/info16060497
Temporão, M. (2019). Measuring public opinion using big data: Applications in computational social sciences* [Doctoral dissertation, Laval University]. Canada.
Wang, Y., Guo, J., Yuan, C., & Li, B. (2022). Sentiment analysis of Twitter data. Applied Sciences, 12(22), 11775. https://doi.org/10.3390/app122211775
Zahed, A., & Sakhi, M. R. (2016, December 19). A review of big data techniques [Conference presentation]. First National Conference on Electrical and Computer Engineering, Distributed Systems and Smart Networks, Islamic Azad University, Kashan Branch, Iran.
Zhao, Z., Liu, W., & Wang, K. (2023). Research on sentiment analysis method of opinion mining based on multi-model fusion transfer learning. Journal of Big Data, 10, Article 155. https://doi.org/10.1186/s40537-023-00837-x