I am a Ph.D. candidate in Computer Science at North Carolina State University
under the supervision of Dr. James Lester in the IntelliMedia Lab .
My disseration is on an online Reinforcement Learning framework for AI-driven learning environments where I focus on creating
a unified framework for devising personalized pedagogical support for human-centric RL using synthetic data.
I believe AI will play a pivotal role on shaping next-generation education for supporting students by contextualizing
individial needs in terms of engagement and learning outcomes.
I finished my MSc in Computer Science from North Carolina State University with CGPA 3.8/4.0
and BSc in Computer Science from Bangladesh University of Engineering and Technology with CGPA 3.63/4.0.
I am expecting to complete my PhD in Spring 2024. During my PhD, I did multiple internships in the industry, gathering professional experience in
software engineering and machine learning. Before joining NC State, I worked as a Software Engineer in
Research and Development department of Reve System Ltd. for one and a half years.
My research interest is to provide personalized pedagogical support to student based on individual students' needs and behaviors to
in AI-Driven Learning Environemnts using Deep Reinforcement Learning, Deep Learning, Multimodal Learning, Data Mining, and Machine Learning techniques.
My work focuses on understanding personalized scaffolds in terms of hints, feedback, and explanations leveraging limited-sized dataset.
I am using deep Reinforcement learning, both in online and offline context, with limited-sized dataset for providing adaptive support
to student based on their behaviors and prior knowledge in AI-driven learning environments like educational games,
narrative-centered learning environments, and intelligent tutoring systems. I am developing
a multi-agent modular framework for online RL-based personalized pedagogical support in narrative-centered
learning environments that I believe AI will play a pivotal role on shaping next-generation education for
supporting students by contextualizing their individial needs in terms of engagement and learning outcomes.
I work on multiple projects that encompasses a wide range of collaborations across many institution including
Indiana University, Vanderbelt University, University of Central Florida, and University of North Carolina Chaple Hill.
I am also responsible in developing educational softwares like game-based learning environments. I am also a part of
EngageAI Institute, a multi-institute project by NSF that is shaping up the
next generation of learning environments through interactive narratives.
MSc Research (Graduate Research Assistant)
My MSc research was focused on AI-driven for software engineering using machine learning and data mining.
I worked with Dr. Tim Menzies in
the RAISE lab. I investigated machine learning-based approaches for identifying self-admitted technical debts
in source codes (developer comments left as potential bugs or improvments). We leveraged human-in-the-loop techniques
along with total-recall apporaches as natural language processing that achieved 83% recall with 16% data. I also worked
closly with Lexius Nexux for solving test-case prioritization
for automated UI testing for early failure detection using classical machine leanring.
Worked as a member of the People You May Know (PYMK) Team. Implemented a deep reinforcement learning model called Bid And Rank Together (BART) that encorporate individual user's perference
and friending history to provide friend request suggestion in homepage of Facebook.
Worked as a member of the Facebook Creators Well-Being (BCWB) Team. Implemented a graph neural network embedding using that contextualizes users' previous comment history,
comment interactions, and preferences for ranking comments in public profile posts in Facebook for enhancing engagement.
Developed an internal tool for splitting legacy projects into multiple smaller
SVN repositories that removes bad comments and large commits without permissions to reduced 6% storage in AWS.
Tools used: SVN, Python, Java, Powershell.
Worked as a member of Project Engineering (PE) Team. Developed six SVN repository organizing and monitoring tools for PE team. Created an SVN Splitter that splits projects into new repositories and wipe-out bad commit histories.
Worked in research and development (RnD) department of Reve Systems as part of the billing team.
Worked closely with sales, customers, mobile team, and testing teams for developing and maintaining multiple projects.
Graduate Teaching Assistant
CSC510 - Fall 2019 (Software Engineering) at NCSU
CSC216 - Fall 2018 (Programming Concepts - Java) at NCSU
List of Publications
Journals
Shrikanth, N. C., Nichols, W., Fahid, F. M., & Menzies, T. (2021). Assessing Practitioner Beliefs About Software Engineering. Empirical Software Engineering, 26(4), 73.
Yu, Z., Fahid, F. M., Tu, H., & Menzies, T. (2020). Identifying Self-Admitted Technical Debts with Jitterbug: A Two-Step Approach. IEEE Transactions on Software Engineering, 48(5), 1676-1691.
Conferences
Fahid, F. M., Lee, S., Mott, B., Vandenberg, J., Acosta, H., Brush, T., ... & Lester, J. (2023, March). Effects of Modalities in Detecting Behavioral Engagement in Collaborative Game-Based Learning. In Proceedings of the 13th International Learning Analytics and Knowledge Conference (pp. 208-218). Austin, Tx. Association for Computing Machinery Publications.
Fahid, F. M., Rowe, J. P., Spain, R. D., Goldberg, B. S., Pokorny, R., & Lester, J. (2022, July). Robust Adaptive Scaffolding with Inverse Reinforcement Learning-Based Reward Design. In Proceedings of the 23rd International Conference on Artificial Intelligence in Education (pp. 204-207). Durham, UK. Springer International Publications.
Fahid, F. M., Acosta, H., Lee, S., Carpenter, D., Mott, B., Bae, H., ... & Lester, J. (2022, July). Multimodal behavioral disengagement detection for collaborative game-based learning. In Proceedings of the International Conference on Artificial Intelligence in Education (pp. 218-221). Durham, UK. Springer International Publications.
Bounajim, D., Rachmatullah, A., Hinckle, M., Mott, B., Lester, J., Smith, A., ... & Wiebe, E. (2021, September). Applying Cognitive Load Theory to Examine STEM Undergraduate Students' Experiences in An Adaptive Learning Environment: A Mixed-Methods Study. In Proceedings of the Human Factors and Ergonomics Society Annual Meeting (Vol. 65, No. 1, pp. 556-560). Los Angeles, CA. SAGE Publications.
Morshed Fahid, F., Tian, X., Emerson, A., B. Wiggins, J., Bounajim, D., Smith, A., ... & Lester, J. (2021, June). Progression trajectory-based student modeling for novice block-based programming. In Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization (pp. 189-200). Barcelona, Spain. Association for Computing Machinery Publications.
Tian, X., Wiggins, J. B., Fahid, F. M., Emerson, A., Bounajim, D., Smith, A., ... & Lester, J. (2021, June). Modeling Frustration Trajectories and Problem-Solving Behaviors in Adaptive Learning Environments for Introductory Computer Science. In Proceedings of the 22nd International Conference on Artificial Intelligence in Education (pp. 355-360). Utrecht, Netherlands. Springer International Publications.
Fahid, F. M., Rowe, J. P., Spain, R. D., Goldberg, B. S., Pokorny, R., & Lester, J. (2021, June). Adaptively scaffolding cognitive engagement with batch constrained deep Q-networks. In Proceedings of the 22nd International Conference on Artificial Intelligence in Education (pp. 113-124). Utrecht, Netherlands. Springer International Publishing.
Wiggins, J. B., Fahid, F. M., Emerson, A., Hinckle, M., Smith, A., Boyer, K. E., ... & Lester, J. (2021, March). Exploring novice programmers' hint requests in an intelligent block-based coding environment. In Proceedings of the 52nd ACM Technical Symposium on Computer Science Education (pp. 52-58). Virtual. Association for Computing Machinery Publications.
Yu, Z., Fahid, F., Menzies, T., Rothermel, G., Patrick, K., & Cherian, S. (2019, August). TERMINATOR: Better Automated UI Test Case Prioritization. In Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (pp. 883-894). Paris, France. Association for Computing Machinery Publications.
Book Chapters
Lester, J., Gupta, A., Fahid, F. M., & Pande, J. (2023). Learner Modeling in Intelligent Tutoring Systems SWOT Analysis. Book: Design Recommendations for Intelligent Tutoring Systems, 43.
ArXivs
Fahid, F. M., Yu, Z., & Menzies, T. (2019). Better Technical Debt Detection via Surveying. arXiv preprint arXiv:1905.08297.
Chakraborty, J., Xia, T., Fahid, F. M., & Menzies, T. (2019). Software Engineering for Fairness: A Case Study with Hyperparameter Optimization. arXiv preprint arXiv:1905.05786.
Course Project (CSC791 Foundation of Software Engineering and Data Science) - Data Mining, Machine Learning, Word Embedding, Hyper-parameter Optimization, Multi-processing, Clustering, Classification
Developed clustering based SVMmodels with automated hyper-parameter optimization to understand the similarities between posts using word embedding. 10% speedup and 5% better F1 score over the baselien of over the baseline of Majumdar et al. 2018.
Course Project (CSC522 Automated Learning and Data Analysis) - Data Mining, Machine Learning, Word Embedding, Hyper-parameter Optimization, Noise Reduction, Feature Reduction, Classification
Analyzed different regression and classification approaches to predict the impact of TedTalk using heterogeneous data merging. Implemented the complete data-mining pipeline such as feature reduction, normalization, vectorization, noise reduction etc.
Compared the Code Smells, Runtime, Render-time, Community and Repository structures etc. Findings: although Plotly offeres many state-of-the-art functionalities like cross language integration,
web integration, interactive graphs etc., Matplotlib is still a Safer (Code Smells and Oper-source community) and Cheaper (Runtime and
Render Time) choice over Plotly.
Two day National Level Hackathon in Bangladesh. This website was designed to show the trash location, current environemtal hazards.
Two different types of users were used. One Admin type, who manages the databases and updates, while a regular user, who can post new hazard locations.
This project was in the Top 10 Projects under Environemnt Category.