Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | English |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.18166447 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>This is the author’s self-archived published version of an article originally published in Cognizance Journal of Multidisciplinary Studies. PUBLISHED: at https://doi.org/10.47760/cognizance.2025.v05i07.036. Since two DOIs exist (one from cognizance and another from zenodo), use citation below.</p> <p>Official citation (please use this when citing):</p> <p>Besigomwe, K. (2025). Using Natural Language Processing (NLP) to Analyze Education Policies: A Systematic Review. <em>Cognizance Journal of Multidisciplinary Studies</em>, <em>5</em>(7), 440–454. https://doi.org/10.47760/cognizance.2025.v05i07.036</p> <p>Abstract:</p> <p>As governments worldwide generate an unprecedented volume of education policy texts, ranging<br>from curriculum frameworks to legislative reforms, there is growing demand for scalable and rigorous methods<br>to analyze them. This systematic review examines how Natural Language Processing (NLP) has been applied to<br>education policy analysis from 2015 to 2025, highlighting key methodological trends, theoretical foundations,<br>and ethical considerations. Framed within a pragmatic research paradigm that values methodological pluralism<br>and practical relevance, the study integrates policy analysis theories, including the policy cycle, top-down and<br>bottom-up models, and policy learning, with computational text analysis techniques. Following PRISMA 2020<br>guidelines, a systematic literature search was conducted using Scopus, Web of Science, and arXiv, identifying<br>32 peer-reviewed studies applying validated NLP methods such as topic modeling, sentiment analysis, discourse<br>analysis, and transformer-based summarization to education policy documents. A custom appraisal rubric<br>evaluated methodological transparency, validation metrics, ethical safeguards, and reproducibility. The studies<br>cover 12 countries and diverse policy contexts, though most focus on English-language texts. Findings reveal<br>increasing sophistication in NLP applications, especially through models like BERT and GPT-4, with topic<br>modeling dominating curricular and legislative domains, and sentiment analysis widely used for stakeholder<br>feedback. Critical gaps persist in ethical oversight, multilingual inclusivity, and participatory design. Many<br>studies overlook non-English corpora, limiting global generalizability and reinforcing linguistic inequities. This<br>review offers a theoretically grounded, methodologically rigorous synthesis of NLP’s role in enhancing<br>transparency, efficiency, and responsiveness in education policy analysis. It identifies future priorities including<br>explainable and culturally adaptive models, investment in low-resource language tools, and interdisciplinary<br>collaboration, charting a path toward equitable and evidence-based educational governance worldwide.<br>Keywords: Natural Language Processing (NLP), Education Policy Analysis, Systematic Review, Ethical<br>Considerations, Multilingual Inclusivity</p> <p> </p> <p>Copyright and publication note:</p> <p>This article was originally published in Cognizance Journal of Multidisciplinary Studies in 2025.</p> <p>Copyright and reuse rights are governed by the original journal publication and its DOI.</p> <p>The Zenodo record serves only as a self-archived copy for long-term scholarly access.</p> <p> </p> <p>License: All rights reserved.</p>