Back to Top

Raza Ul Mustafa

Assistant Professor

Education

Ph.D. Computer Engineering, (2018-2022)

 

Departments

  • College of Arts and Sciences
  • Mathematics and Computer Science

Bio

Dr. Raza Ul Mustafa is an Assistant Professor in the Department of Mathematics and Computer Science at Loyola University New Orleans. Before this, he worked as a Postdoctoral Fellow in Large Language Models (LLMs) at American University in Washington, DC. He earned his Ph.D. in Computer Engineering from the University of Campinas, where he collaborated with the Innovation Center at Ericsson S.A., the São Paulo Research Foundation (FAPESP), Science Foundation Ireland, and INRIA France. His research interests include NLP in Hate Speech, Large Language Models (LLMs), Machine/Deep Learning, and mapping Multimedia Quality of Service (QoS) to Quality of Experience (QoE). He has authored over 25 publications in top-tier conferences and journals, and his research work is reproducible.

Before joining academia, Mustafa made significant contributions to the tech industry as a full-stack developer for over six years. His hands-on industry experience enhances his teaching and provides students with valuable industry perspectives. Mustafa's passion for teaching and real-world experience inspire and empower students to excel in their academic pursuits and beyond.

Classes Taught

Intro to C++ Programming, Python and Data Science, Internet Technologies

Research Interests

Video QoE, QoS, NLP, Machine Learning, Deep Learning

Publications

  • Mustafa, Raza Ul, et al. "QoE of 2D and 360° Video: Insights from 5G Radio Metrics." Mobile Networks and Applications (2025): 1-13.
  • Mustafa, Raza Ul, et al. "Mobile 360° Video QoE: Empirical Analysis of 5G QoS Metrics." 2025 International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems (MSWiM). IEEE, 2025.
  • Mustafa, Raza Ul, Md Tariqul Islam, and Christian Esteve Rothenberg. "Investigating the impact of channel metrics in 5G NSA and SA on video streaming qoe." NOMS 2025-2025 IEEE Network Operations and Management Symposium. IEEE, 2025.
  • Mustafa, Raza Ul, et al. "Can GPT-4 Detect Subcategories of Hatred?" 2024 IEEE Conference on Digital Platforms and Societal Harms, Washington, DC, 14–15 October 2024.
  • Mustafa, Raza Ul, et al. "Coded Term Discovery for Online Hate Speech Detection." 11th IEEE International Conference on Data Science and Advanced Analytics (DSAA 2024).
  • Mustafa, Raza Ul, et al. "YouTube Goes 5G: QoE Benchmarking and ML-Based Stall Prediction." IEEE Wireless Communications and Networking Conference (WCNC), 2024.
  • Mustafa, Raza Ul, et al. "EFFECTOR: DASH QoE and QoS Evaluation Framework for Encrypted Video Traffic." NOMS IEEE/IFIP Network Operations and Management Symposium, 2023.
  • Mustafa, Raza Ul, et al. "A Supervised Machine Learning Approach for DASH Video QoE Prediction in 5G Networks." Proceedings of the 16th ACM Symposium on QoS and Security for Wireless and Mobile Networks, 2020.
            
                

Activities

                
                
  1. Dr. Raza Ul Mustafa will be presenting the paper “Evaluating Large Language Models for Implicit Hate Speech Detection” at the IEEE International Conference on Communications (IEEE ICC 2026).
  2. A research team including Dr. Raza Ul Mustafa will present the paper, “From Radio Signal Dynamics to QoE Degradation Prediction in Immersive Streaming,” at the 17th International Conference on Network of the Future (NoF 2026) in Rome, Italy.

    The research investigates how short-term variations in cellular radio signals can be used to predict Quality of Experience (QoE) degradation in immersive 360° video streaming. Using machine-learning techniques, the work identifies early network indicators associated with streaming performance degradation. The research was conducted in collaboration with researchers associated with SMARTNESS 2030 at the University of Campinas (UNICAMP), Brazil, an international initiative focused on advanced 5G and 6G networks.

    The paper will be presented on October 1, 2026, during the conference session on Traffic Forecasting and QoE Prediction.