A Knowledge Graph and Large Language Model Approach for Mapping Associations Between Cognitive Neuroscience and Marketing.

Document Type : Original Article

Authors

Ali Sarabadani ¹

Kheirolah Rahsepar Fard ²

Mahtab Tajvidiyan ¹

¹ IT Engineering (E-Commerce), Department of Computer Engineering and Information Technology, University of Qom, Qom, Iran.

² Department of Computer Engineering and Information Technology, University of Qom, Qom, Iran.

10.22067/cke.2026.97846.1187

Abstract

A semi-automated framework to create a structured association map between cognitive neuroscience and marketing, using expert-validated large language models (LLMs), supports a knowledge graph-based approach. The starting point for this framework is an existing cognitive neuroscience knowledge graph (CNKG) of 312 concepts as the source domain and a curated marketing concept list consisting of 100 concepts as the target domain. The mapping process consists of two distinct phases: the first phase involves automated association generation via four different LLMs (GPT-4, Gemini, Claude, & Grok) producing candidate associations between cognitive neuroscience and marketing by determining synonymous relationships with their word choices; and the second phase includes human-based expert validation in which marketing and economics experts evaluate, revise, and filter the candidate associations produced by the automated associations. This further emphasizes that human supervision is essential in maintaining the scientific integrity of the mapping process. In reviewing and analyzing the graph that was produced through this process, many core concepts within neuroscience were identified as being hub nodes (reward processing, emotion, attention, and decision-making). Additionally, there were strong relationships between the hub neuroscience concepts and many marketing constructs (including the brand).

Keywords

Knowledge Graph

Large Language Models

Cognitive Neuroscience

Neuromarketing

Cross-domain Knowledge Mapping

Subjects

• Computer Science

---

References

[1] F. Aghaee and H. R. Shaker. (2025). RB-LLM control: An intelligent control framework with rule-based large language model decision-making. Aerospace Science and Technology. [Online]. 168, p. 111259. Available: https://doi.org/10.1016/j.ast.2025.111259

[2] S. Wang et al. (2025). Knowledge graph retrieval-augmented generation for LLM-based recommendation. Presented at 63rd Annual Meeting of the Association for Computational Linguistics (ACL). [Online]. Available: https://doi.org/10.18653/v1/2025.acl-long.1317

[3] C. Voinea, S. Porsdam Mann, J. Savulescu, and B. D. Earp. (2025). The calculator analogy: Epistemic virtues for using LLMs. Technology in Society. [Online]. 85, p. 103198. Available: https://doi.org/10.1016/j.techsoc.2025.103198

[4] J. Linders and J. M. Tomczak. (2025). Knowledge graph-extended retrieval augmented generation for question answering. Applied Intelligence. [Online]. 55(17), p. 1102. Available: https://doi.org/10.1007/s10489-025-06885-5

[5] C. Ma, Y. Chen, T. Wu, A. Khan, and H. Wang. (2025). Large language models meet knowledge graphs for question answering: Synthesis and opportunities. Presented at Conference on Empirical Methods in Natural Language Processing (EMNLP). [Online]. Available: https://doi.org/10.48550/arXiv.2505.20099

[6] G. Xiao et al. (2025). LLM4VKG: Leveraging large language models for virtual knowledge graph construction. Presented at 34th International Joint Conference on Artificial Intelligence (IJCAI). [Online]. Available: https://doi.org/10.24963/ijcai.2025/525

[7] X. Li, P. Zheng, J. Bao, L. Gao, and X. Xu. (2025). Achieving cognitive mass personalization via the Self-X cognitive manufacturing network: An industrial knowledge graph- and graph embedding-enabled pathway. Computers & Industrial Engineering. [Online]. 180, p. 109709. Available: https://doi.org/10.1016/j.cie.2025.109709

[8] E. Lavrinovics, R. Biswas, J. Bjerva, and K. Hose. (2025). Knowledge graphs, large language models, and hallucinations: An NLP perspective. Journal of Web Semantics. [Online]. 85, p. 100844. Available: https://doi.org/10.1016/j.websem.2024.100844

[9] R. Haskins and B. Adams. (2026). KEA Explain: A neurosymbolic framework for explaining large language model hallucinations through knowledge graph validation. Journal of Intelligent Systems. [Online]. 5(1). Available: https://hdl.handle.net/10092/109696

[10] J. Liu and J. Tang. (2026). LeAK-GraphRAG: A legal academic knowledge GraphRAG framework with hybrid retrieval for mitigating hallucinations in large language models. In Frontiers in Artificial Intelligence and Applications. [Online]. Vol. 411, Amsterdam, The Netherlands: IOS Press, pp. 597–604. Available: https://doi.org/10.3233/FAIA251624

[11] S. Jauhari. (2025). Algorithmic red teaming approaches to secure LLMs. Machine Learning with Applications. [Online]. 23, p. 100815. Available: https://doi.org/10.1016/j.mlwa.2025.100815

[12] S. Chehreh and A. Sarabadani. (2024). A model based on random forest algorithm and Jaya optimization to predict bank customer churn. Journal of Engineering Management and Soft Computing. [Online]. 9(2), pp. 132–148. Available: https://doi.org/10.22091/jemsc.2024.9541.1174

[13] M. Q. Pérez, S. López Bernal, E. Horna Prat, L. Montesano Del Campo, L. Fernández Maimó, and A. Huertas Celdrán. (2025). EEG channel reconstruction using convolutional neural networks in limited BCIs: A proposed method for neuromarketing applications. Applied Soft Computing. [Online]. 181, p. 113455. Available: https://doi.org/10.1016/j.asoc.2025.113455

[14] K. Sun and R. Wang. (2025). Breaking myths in LLM scaling and emergent abilities with a comprehensive statistical analysis. Neural Networks. [Online]. 183, p. 108164. Available: https://doi.org/10.1016/j.neunet.2024.108164

[15] F. Bagheri, D. Buscaldi, and D. Reforgiato Recupero. (2025). Leveraging knowledge graphs and LLMs for content based reviewer assignment. Journal of Intelligent Information Systems. [Online]. Available: https://doi.org/10.1007/s10844-025-01004-9

[16] P. Gajo and A. Barrón-Cedeño. (2025). Natural vs programming language in LLM knowledge graph construction. Information Processing & Management. [Online]. 62, p. 104195. Available: https://doi.org/10.1016/j.ipm.2025.104195

[17] C. Öberg. (2023). Neuroscience in business-to-business marketing research: A literature review, co-citation analysis and research agenda. Industrial Marketing Management. [Online]. 113, pp. 168–179. Available: https://doi.org/10.1016/j.indmarman.2023.06.004

[18] J. Wei et al. (2022). Emergent abilities of large language models. Transactions on Machine Learning Research. [Online]. Available: https://arxiv.org/abs/2206.07682

[19] N. Ibrahim, S. Aboulela, and A. Ibrahim. (2024). A survey on augmenting knowledge graphs (KGs) with large language models (LLMs): Models, evaluation metrics, benchmarks, and challenges. Knowledge and Information Systems. [Online]. 4(1), pp. 1–28. Available: https://doi.org/10.1007/s44163-024-00175-8

[20] H. Purnomo and Y. Novita. (2024). The impact of branding, advertising, and social media marketing on consumer purchase intention, brand loyalty, and brand equity in the Indonesian market. Journal of Management and Business (JOMB). [Online]. 6(3), Art. no. 9653. Available: https://doi.org/10.31539/jomb.v6i3.9653

[21] M. M. Gutiérrez Gutiérrez, J. J. Perona Páez, and F. D. P. Gutiérrez Bonilla. (2024). Models of brand equity: A systematic and critical review. Cogent Business & Management. [Online]. 11(1), p. 2433168. Available: https://doi.org/10.1080/23311975.2024.2433168

[22] L. D. Gonen, T. Tavor, and U. Spiegel. (2024). Unlocking market potential: Strategic consumer segmentation and dynamic pricing for balancing loyalty and deal seeking. Mathematics. [Online]. 12(21), p. 3364. Available: https://doi.org/10.3390/math12213364

[23] E. Tarta and L. Pasaribu. (2024). The impact perceived quality, advertising effectiveness, social media presence and brand image on purchase intention Telkomsel provider. Enrichment: Journal of Management. [Online]. 14(4), pp. 694–704. Available: https://doi.org/10.35335/enrichment.v14i4.2042

[24] A. Sarabadani and K. R. Fard. (2025). GDPKG-LLM: Integrating Gene, Disease, and Pharmacogenomics Knowledge Graphs for Cognitive Neuroscience Using Large Language Models. Computational Science and Information. [Online]. Available: https://doi.org/10.7494/csci.2025.26.3.6673

[25] N. Ibrahim, S. Aboulela, A. Ibrahim, and R. Kashef. (2024). A survey on augmenting knowledge graphs (KGs) with large language models (LLMs): Models, evaluation metrics, benchmarks, and challenges. Discover Artificial Intelligence. [Online]. 4, p. 76. Available: https://doi.org/10.1007/s44163-024-00175-8

[26] S. Seo, H. Cheon, H. Kim, and D. Hyun. (2022). Structural quality metrics to evaluate knowledge graph quality. arXiv. [Online]. Available: https://doi.org/10.48550/arXiv.2211.10011