Semantic Vector Representation: An Introduction to Its Foundations and Applications in the Humanities

Document Type : Original Article

Authors

1 . PhD Candidate in Culture and Communication, Baqir al-Olum University, Qom, Iran

2 Assistant Professor, Department of Cultural Policy, Baqir al-Olum University, Qom, Iran

Abstract

This study aims to elucidate the theoretical foundations of semantic vector representation and introduce its potential for textual analysis, the discovery of semantic relationships, and the development of research methods in the humanities. The central research problem lies in the inability of machines to directly comprehend natural language, coupled with the relative limitations of traditional and classical digital methods in analyzing large-scale textual data. Adopting a descriptive–analytical approach and drawing on a review of established works in natural language processing and computational linguistics, the study examines the foundations of semantic vector representation, the distributional hypothesis of meaning, and its role in the computational modeling of language. The findings indicate that by transforming words and texts into multidimensional spaces, vector representations enable the measurement of semantic similarity, analysis of conceptual relationships, tracking of the historical evolution of concepts, extraction of discourse clusters, and development of semantic search in humanities texts. Nevertheless, because such models lack lived experience, intentionality, and consciousness, they cannot replace human understanding and interpretation; rather, they function as complementary tools for expanding research and knowledge management capabilities in the humanities.

Keywords

Main Subjects

References

میرعرب، علی. (1402). بررسی راهکارهای جستجو و بازیابی معنایی متون فارسی و عربی. علوم و فنون، 9(4)، صص 185–204.
Almeida, Felipe; & Xexéo, Geraldo. (2019). Word Embeddings: A Survey. CoRR, abs/1901. 09069. https://doi. org/10. 48550/arXiv. 1901. 09069
Caliskan, Aylin; Bryson, Joanna J. ; & Narayanan, Arvind. (2017). Semantics Derived Automatically from Language Corpora Contain Human-Like Biases. Science, 356(6334), 183–186. https://doi. org/10. 1126/science. aal4230
Ferrone, Lorenzo; & Zanzotto, Fabio Massimo. (2020). Symbolic, Distributed, and Distributional Representations for Natural Language Processing in the Era of Deep Learning: A Survey. Frontiers in Robotics and AI, 6, 153. https://doi. org/10. 3389/frobt. 2019. 00153
Garg, Nikhil; Schiebinger, Londa; Jurafsky, Dan; & Zou, James. (2018). Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes. Proceedings of the National Academy of Sciences, 115(16), E3635–E3644. https://doi. org/10. 1073/pnas. 1720347115
Grimmer, Justin; & Stewart, Brandon M. (2013). Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts. Political Analysis, 21(1), 1–31. https://doi. org/10. 1093/pan/mps028
Hamilton, William L. ; Leskovec, Jure; & Jurafsky, Dan. (2016). Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change. In K. Erk & N. A. Smith (Eds.), (K. Erk & N. A. Smith, Eds.), Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 1489–1501). Berlin, Germany: Association for Computational Linguistics. https://doi. org/10. 18653/v1/P16-1141
Jurafsky, Daniel; & Martin, James H. (2026). Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models (3rd ed.).
Liu, Bing. (2012). Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers.
Manning, Christopher D. (2015). Computational Linguistics and Deep Learning. Computational Linguistics, 41(4), 701–707. https://doi. org/10. 1162/COLI_ a_00239
Merrill, William; Goldberg, Yoav; Schwartz, Roy; & Smith, Noah A. (2021). Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand? Transactions of the Association for Computational Linguistics, 9, 1047–1060. https://doi. org/10. 1162/tacl_a_00412
Mikolov, Tomas; Chen, Kai; Corrado, Greg; & Dean, Jeffrey. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv:1301. 3781 [Cs:CL]. https://doi. org/10. 48550/arXiv. 1301. 3781
Mitchell, Melanie; & Krakauer, David C. (2023). The Debate Over Understanding in AI’s Large Language Models. Proceedings of the National Academy of Sciences, 120(13), e2215907120. https://doi. org/10. 1073/pnas. 2215907120
Mohamed, E. H. ; & Shokry, E. M. (2022). QSST: A Quranic Semantic Search Tool Based on Word Embedding. Journal of King Saud University: Computer and Information Sciences, 34(3), 934–945. https://doi. org/10. 1016/j. jksuci. 2020. 01. 004
Rafiei, Mahdi; & Khadangi, Ehsan. (2025). Sentiment and Tone Analysis of the Holy Qur’an Using Natural Language Processing. Journal of Interdisciplinary Qur’anic Studies, 4(2). https://doi. org/10. 37264/JIQS. V4I2. 5
Rahman, A. M. (2025). Digital Humanities: Computational Methods for Research. International Research Journal of Arts and Social Sciences, 13(2), 1–5. https://doi. org/http:/dx. doi. org/10. 14303/2276‐6502. 2025. 114
Sarmadi, Mehran; Alikhani, Morteza; Zinvandi, Erfan; & Pourbahman, Zahra. (2025). Hakim: Farsi Text Embedding Model. arXiv:2505. 08435 [Cs:CL, Cs:Cs:AI, Cs:Cs:LG]. https://doi. org/DOI:10. 48550/arXiv. 2505. 08435
Schomacker, Thorben; & Tropmann-Frick, Marina. (2021). Language Representation Models: An Overview. Entropy, 23(11), 1422. https://doi. org/10. 3390/e23111422
Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; Uszkoreit, Jakob; Jones, Llion; Gomez, Aidan N. ; … Polosukhin, Illia. (2017). Attention Is All You Need. CoRR, abs/1706. 03762. https://doi. org/10. 48550/arXiv. 1706. 03762
Wevers, Melvin; & Koolen, Marijn. (2020). Digital Begriffsgeschichte: Tracing Semantic Change Using Word Embeddings. Historical Methods, 53(4), 226–243. https://doi. org/10. 1080/01615440. 2020. 1760157
Wohlgenannt, Gerhard; Chernyak, Ekaterina; Ilvovsky, Dmitry I. ; Barinova, Ariadna; & Mouromtsev, Dmitry. (2019). Relation Extraction Datasets in the Digital Humanities Domain and their Evaluation with Word Embeddings. CoRR, abs/1903. 01284. https://doi. org/10. 48550/arXiv. 1903. 01284
Islamic Knowledge Management
Volume 7, Issue 2 - Serial Number 14
October 2025
Pages 166-195

Files

History

  • Receive Date: 26 May 2025
  • Revise Date: 18 August 2025
  • Accept Date: 08 September 2025

Share

How to cite

Statistics