Ana içeriğe atla

Mehmet Ali Erkan

Res.Assist. Mehmet Ali Erkan

Room No: 138

E-mail: maerkan@metu.edu.tr

Phone: +90 312 210 5320

Fax: +90 312 210 2979

CV || Personal Web Page || Git-Hub

Education:
  • M.Sc.: Department of Statistics, Middle East Technical University, Turkey, 2023 - 2025
  • B.Sc.: Department of Statistics, Middle East Technical University, Turkey, 2019 - 2023
Research Interests: 
  • Statistical Inference for Large Language Models
  • Machine Learning and Deep Learning
  • Natural Language Processing
  • Legal NLP and Retrieval-Augmented Generation
  • Uncertainty Quantification and Risk Control
  • Low-Resource Language Processing
  • Benchmark Construction and Evaluation
  • Sustainable and Energy-Efficient AI
Assisted Courses / Laboratories:
  • STAT 295 - Object Orianted Programming (Spring 2024)
  • STAT 495 - Application in Statistics  (Spring 2024)
  • STAT 311 - Modern Database Systems (Fall 2024, Fal 2025)
  • STAT 333 - Data Structures and Algorithms (Spring 2025, Spring 2026)
  • STAT 250 - Applied Statistics (Spring 2025)
  • STAT 401 - Introduction to Big Data (Spring 2026)
Selected Publications and Research

Refereed Journal Articles

Erkan, M.A., Yozgatlıgil, C. (2026). Sustainable Science Mapping: Benchmarking Green AI against Transformers for Cross-Disciplinary Abstract Classification Using arXiv. Scientific Reports.
https://doi.org/10.1038/s41598-026-48795-7

Deveci, A., Erkan, M.A., Medeni, İ.T., Medeni, T.D., Uzkafalı, A., Özkan, A. (2026). Enhancing IDS Through Multi-Objective Optimization: A Focus on Attack Graph under Worst-Parent Attack. Communications Faculty of Sciences University of Ankara Series A2-A3: Physical Sciences and Engineering, 68(1), 92–109.

Deveci, A., Erkan, M.A., Medeni, İ.T., Medeni, T.D. (2026). A Novel Framework for Next Word Prediction Using Long Short-Term Memory Networks. Dokuz Eylul University Faculty of Engineering Journal of Science and Engineering, 28(82), 113–120.
https://doi.org/10.21205/deufmd.2026288215

Yücesan, E., Erkan, M.A., Deveci, A., Medeni, İ.T. (2024). Bekenbey AI: Innovative Solutions at the Intersection of Deep Learning and Law. Journal of Engineering Faculty, 2(2), 185–192.

Datasets and Software

Erkan, M.A., Yozgatlıgil, C. (2026). TurkishLegalBench: A Comprehensive Multi-Task Benchmark Suite for Turkish Legal NLP. Research dataset and evaluation code.
Dataset: https://doi.org/10.5281/zenodo.18555735
Code: https://github.com/mrkn7/TurkishLegalBench

Refereed Conference Papers

Deveci, A., Erkan, M.A., Medeni, İ.T., Medeni, T.D. (2025). Innovative Approaches to High-Energy Gamma Particle Classification: A Coevolutionary Artificial Neural Network for Cherenkov Telescopes. Proceedings of CAIAC, 25, 37.

Preprints

Erkan, M.A., Koçak, H.E. (2025). Perceptions of the Metaverse at the Peak of the Hype Cycle: A Cross-Sectional Study Among Turkish University Students. arXiv:2512.17750.
https://arxiv.org/abs/2512.17750

International Conference Presentations

Gökalp, N., Erkan, M.A., Yönel, A.A., Başbuğ, B. (2026). Dimensions of Volunteer Engagement in Recovery from the 2023 Türkiye Earthquakes: A Mixed-Methods Study of Tzu Chi Volunteers. 10th Anniversary UKADR Annual Conference: Science, Society, and Solidarity, Aston University, Birmingham, United Kingdom, 14–15 September 2026. 

Akyıldız, E.B., Erkan, M.A., Yozgatlıgil, C. (2026). A Compositional Data Analysis Framework for Diagnosing LLM Reasoning over Time Series Anomalies. DSSV 2026 – Data Science, Statistics and Visualisation, Trento, Italy, 29 June–1 July 2026. 

Başbuğ, B., Gökalp, N., Yönel, A.A., Erkan, M.A. (2026). The Role of Volunteers in the 6 February 2023 Kahramanmaraş Earthquake. NEEDS 2026: Societal Resilience in Times of Cascading Crises and Disasters, Kaunas, Lithuania, 28–30 April 2026. 

Awards, Grants and Fellowships
  • Early Career Researcher (ECR) Support, CODATA – Committee on Data of the International Science Council (2026)
    Competitively selected for supported participation in the 2026 Global Conference of the International Decade of Sciences for Sustainable Development (IDSSD), held at UNESCO Headquarters in Paris, France.

Academic and Professional Experience:

  • Research Assistant in the Department of Statistics, Middle East Technical University, Turkey, December 2023 - Present
  • Project Intern, Presidency of the Republic of Türkiye Human Resources Office, May-July 2023
  • Data Science Intern at Yapı Kredi, July-September 2022

Thesis:

M. A. Erkan, Turkish Legal NLP: A Comprehensive AI Framework for Legal Document Understanding, Summarization, and Retrieval-Augmented Generation, MSc. Thesis. Under the supervision of Yozgatlıgil C.

Son güncelleme