Formulating Research Problems in Agricultural Social Science with Artificial Intelligence: The Evidence, Context, and Validation Framework
Keywords:
Artificial intelligence, Agricultural social science,, Research problem formulation, Evidence synthesis, Contextual sensitivityAbstract
Artificial intelligence (AI) offers opportunities to improve the efficiency of literature analysis and support scientific research. However, its ability to identify research gaps does not necessarily ensure research problem formulations with theoretical significance, contextual relevance, and empirical feasibility. This challenge is particularly important in agricultural social sciences, where economic, social, institutional, and ecological factors interact in shaping agricultural phenomena. This article aims to develop the Evidence–AI–Context–Validation (EACV) framework as a conceptual approach to AI-assisted research problem formulation. Drawing on a synthesis of literature on conceptual research, human–AI interaction, evidence quality, and participatory knowledge production, the framework integrates four interconnected components: evidence assessment, AI-assisted analysis, contextual interpretation, and systematic validation. The conceptual development generates six theoretical propositions linking AI analytical capacity, evidence quality, contextual sensitivity, participatory validation, evidence-based verification, and process transparency to research problem quality. The EACV framework provides a conceptual foundation for the critical and responsible use of AI in formulating research problems in agricultural social sciences. Nevertheless, its theoretical propositions require empirical testing across different research contexts to establish their applicability and contribution
References
1] E. Jaakkola, “Designing conceptual articles: Four approaches,” AMS Review, vol. 10, pp. 18–26, 2020, doi: 10.1007/s13162-020-00161-0.
[2] D. A. Whetten, “What constitutes a theoretical contribution?” Academy of Management Review, vol. 14, no. 4, pp. 490–495, 1989, doi: 10.5465/amr.1989.4308371.
[3] R. J. Torraco, “Writing integrative literature reviews: Guidelines and examples,” Human Resource Development Review, vol. 4, no. 3, pp. 356–367, 2005, doi: 10.1177/1534484305278283.
[4] F. Bolaños, A. Salatino, F. Osborne, and E. Motta, “Artificial intelligence for literature reviews: Opportunities and challenges,” Artificial Intelligence Review, vol. 57, Art. no. 259, 2024, doi: 10.1007/s10462-024-10902-3.
[5] L. Messeri and M. J. Crockett, “Artificial intelligence and illusions of understanding in scientific research,” Nature, vol. 627, pp. 49–58, 2024, doi: 10.1038/s41586-024-07146-0.
[6] W. H. Walters and E. I. Wilder, “Fabrication and errors in the bibliographic citations generated by ChatGPT,” Scientific Reports, vol. 13, Art. no. 14045, 2023, doi: 10.1038/s41598-023-41032-5.
[7] P. R. Bhagat, F. Naz, and R. Magda, “Artificial intelligence solutions enabling sustainable agriculture: A bibliometric analysis,” PLOS ONE, vol. 17, no. 6, Art. no. e0268989, 2022, doi: 10.1371/journal.pone.0268989.
[8] J. D. Lee and K. A. See, “Trust in automation: Designing for appropriate reliance,” Human Factors, vol. 46, no. 1, pp. 50–80, 2004, doi: 10.1518/hfes.46.1.50_30392.
[9] R. Parasuraman and V. Riley, “Humans and automation: Use, misuse, disuse, abuse,” Human Factors, vol. 39, no. 2, pp. 230–253, 1997, doi: 10.1518/001872097778543886.
[10] S. Amershi et al., “Guidelines for human-AI interaction,” in Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, Glasgow, UK, 2019, Art. no. 3, pp. 1–13, doi: 10.1145/3290605.3300233.
[11] W. C. Clark et al., “Knowledge systems for sustainable development,” Proceedings of the National Academy of Sciences, vol. 100, no. 14, pp. 8086–8091, 2003, doi: 10.1073/pnas.1231332100.
[12] M. Tengö, E. S. Brondizio, T. Elmqvist, P. Malmer, and M. Spierenburg, “Connecting diverse knowledge systems for enhanced ecosystem governance: The multiple evidence base approach,” Ambio, vol. 43, pp. 579–591, 2014, doi: 10.1007/s13280-014-0501-3.
[13] R. D. Norström et al., “Principles for knowledge co-production in sustainability research,” Nature Sustainability, vol. 3, pp. 182–190, 2020, doi: 10.1038/s41893-019-0448-2.
[14] R. Chambers, “The origins and practice of participatory rural appraisal,” World Development, vol. 22, no. 7, pp. 953–969, 1994, doi: 10.1016/0305-750X(94)90141-4.
[15] M. S. Reed, “Stakeholder participation for environmental management: A literature review,” Biological Conservation, vol. 141, no. 10, pp. 2417–2431, 2008, doi: 10.1016/j.biocon.2008.07.014.
[16] M. J. Page et al., “The PRISMA 2020 statement: An updated guideline for reporting systematic reviews,” BMJ, vol. 372, Art. no. n71, 2021, doi: 10.1136/bmj.n71.
[17] F. Miao and W. Holmes, Guidance for Generative AI in Education and Research. Paris, France: UNESCO, 2023, doi: 10.54675/EWZM9535.
[18] National Institute of Standards and Technology, Artificial Intelligence Risk Management Framework (AI RMF 1.0). Gaithersburg, MD, USA: NIST, NIST AI 100-1, 2023, doi: 10.6028/NIST.AI.100-1.