|
Vol.14, No.4, November 2025. ISSN: 2217-8309 eISSN: 2217-8333
TEM Journal
TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS Association for Information Communication Technology Education and Science |
Revolutionizing Academic Excellence: Machine Learning for Faculty Competency Mapping
Aida Fauzia Rahmatika, Dian Indiyati, Andry Alamsyah
© 2025 Aida Fauzia Rahmatika, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)
Citation Information: TEM Journal. Volume 14, Issue 4, Pages 3728-3736, ISSN 2217-8309, DOI: 10.18421/TEM144-76, November 2025.
Received: 04 January 2025.
Abstract:
Lecturers are at the forefront of higher education, shaping competencies and preparing talents for industry needs. Ensuring their competence and reputation is therefore essential not only for universities but also for institutions such as the Indonesian Higher Education Services (LLDIKTI), which is responsible for maintaining education quality, regulatory compliance, and alignment with the national roadmap. One potential strategy is talent mapping, a method widely applied in industry to optimize workforce development but rarely used for lecturers. This study develops a talent map for the LLDIKTI IV region by analyzing secondary data from scientific literature databases. Using Latent Dirichlet Allocation (LDA) topic modelling on more than 32,000 articles authored by lecturers from 65 universities, eight distinct talent clusters were identified: Customer Experience Management, Digital Product Management, Digital Marketing, Financial Management, Marketing, Leadership, Human Resource Management, and Business Performance Management. These clusters align with four major areas of management. The findings provide insights into lecturer competence distribution, highlight reputable individuals in each cluster, and suggest practical implications for enhancing higher education quality. This study demonstrates the potential of talent mapping in academia, offering a data-driven approach for LLDIKTI to strengthen lecturer development, support institutional reputation, and contribute to regional and national goals.
Keywords – Competence, reputation, talent mapping, LDA model, higher education. |
|
----------------------------------------------------------------------------------------------------------- ----------------------------------------------------------------------------------------------------------- |