Education
Experiences
- Industry & Sponsorship Chair, Co-OrganizerBNAIC/BeNeLearn 2024 • Utrecht, Netherlands
Planned and executed the leading AI/ML conference in the Benelux region, coordinating keynotes, parallel sessions, and industry partnerships.
- Guest Lecturer – Safe Experimentation with Large Language ModelsEuropean Central Bank & De Nederlandsche Bank • Frankfurt/Amsterdam
Delivered a guest lecture on ASReview and AI in finance, discussing transparency, ethical AI, and reproducible research for central banks and regulators.
- Co-Organizer and PresenterKickstart AI • Amsterdam, Netherlands
Organized and presented a workshop on Makita, a workflow generator for reproducible large-scale simulation studies, providing hands-on training.
- Invited Speaker – Research IndabaNorth-West University, Optentia Research Unit • Cape Town, South Africa
Spoke on AI and GPT technologies, their potential and limitations, and implications for research and practice in the social sciences.
- OCRE Grant Recipient & CollaboratorOCRE Project & VSHN AG • Zurich, Switzerland / Utrecht, Netherlands
Awarded an OCRE cloud grant to run large-scale systematic review simulations using commercial cloud platforms. Collaborated with VSHN on Kubernetes-based deployments using Exoscale.
- Invited SpeakerUniversity of Oxford, Department of Education • Oxford, UK
Presented on the application of machine learning in systematic reviews, with emphasis on dataset quality and open science practices.
- SpeakerSummit AI and Predictive Health (EWUU Alliance) • Wageningen campus, Netherlands
Presented use-cases on inclusive training datasets for text mining, demonstrating importance of diverse coverage in AI training data.
- SpeakerNetherlands National Open Science Festival • Amsterdam, Netherlands
Presented on hybrid models and dataset benchmarking for systematic reviews at the national Open Science event.
- Fellowship RecipientHofvijverkring Fellowship • The Hague, Netherlands
Received competitive fellowship to broaden international collaboration opportunities and networks in data science and AI.
- ResearcherUtrecht University, ASReview Research Group • Utrecht, Netherlands
Contributed to the development and maintenance of ASReview, open-source software for AI-driven systematic reviews.
- Teaching Assistant - Applied Text MiningUtrecht University Summer School • Utrecht, Netherlands
Assisted in teaching text mining and NLP concepts to international students, providing guidance in labs and course projects.
- Deep Learning Models for Active LearningMaster’s Thesis - Utrecht University & ASReview • Utrecht, Netherlands
Developed and evaluated deep neural networks for active learning in systematic reviews, achieving a grade of 9.1. Work led to continuation in the ASReview project.
- Apple Repair Technician (ACMT Certified)Apple Authorised Service Provider • Netherlands
Provided certified Apple hardware repairs while completing academic studies; achieved ACMT 2019, 2020, 2021 certifications.
- Process Mining and Log Sampling ResearchBachelor’s Thesis - Utrecht University • Utrecht, Netherlands
Created a framework for process mining from event log samples, enabling controlled sampling and quality assessment. Completed with a grade of 7.4.
- Christmas Puzzle ParticipantAlgemene Inlichtingen- en Veiligheidsdienst (AIVD) • Netherlands
Ranked 32nd of 430 teams in the AIVD/NBV annual puzzle competition.
- Men’s Eight RowerOrca Rowing Association • Utrecht, Netherlands
Rowed competitively for Orca’s Men’s Eight team during Bachelor’s study, following an intensive training and dietary regime.
Latest publications
-
Simulation-based Active Learning for Systematic Reviews: A Scoping Review of Literature
Authors: J. J. Teijema, S. Seuren, D. Anadria, A. Bagheri, R. van de Schoot
Journal of Information Science • 2025/12/17
Background: Active learning is a proposed method for accelerating the screening phase of systematic reviews. While extensively studied, evidence remains scattered across a fragmented body of literature. Objective: This scoping review investigates whether active learning is recommended for systematic review screening and identifies areas needing further research. Design: We screened 1887 records published since 2006 using ASReview, an active learning tool, and included 60 relevant studies. We also analyzed 238 of 336 collected datasets for study design, dataset usage, and implementation. Results: All 60 studies recommended active learning as a means to improve screening efficiency. Despite some methodological heterogeneity, consistent endorsement was found across the literature. Conclusions: Active learning shows strong potential to support systematic review screening. Standardizing evaluation metrics, encouraging open data practices, and diversifying model configurations are key priorities for advancing this field.
-
Echo State and Band-pass Networks with aqueous memristors: leaky reservoir computing with a leaky substrate
Authors: T. M. Kamsma, J. J. Teijema, R. van Roij, C. Spitoni
Chaos: An Interdisciplinary Journal of Nonlinear Science • 2025/9/12
Recurrent Neural Networks (RNN) are extensively employed for processing sequential data such as time series. Reservoir computing (RC) has drawn attention as an RNN framework due to its fixed network that does not require training, making it an attractive for hardware based machine learning. We establish an explicit correspondence between the well-established mathematical RC implementations of Echo State Networks and Band-pass Networks with Leaky Integrator nodes on the one hand and a physical circuit containing iontronic simple volatile memristors on the other. These aqueous iontronic devices employ ion transport through water as signal carriers, and feature a voltage-dependent (memory) conductance. The activation function and the dynamics of the Leaky Integrator nodes naturally materialise as the (dynamic) conductance properties of iontronic memristors, while a simple fixed local current-to-voltage update rule at the memristor terminals facilitates the relevant matrix coupling between nodes. We process various time series, including pressure data from simulated airways during breathing that can be directly fed into the network due to the intrinsic responsiveness of iontronic devices to applied pressures. This is done while using established physical equations of motion of iontronic memristors for the internal dynamics of the circuit.
-
Large-scale simulation study of active learning models for systematic reviews
Authors: J. J. Teijema, J. de Bruin, A. Bagheri, R. van de Schoot
International Journal of Data Science and Analytics • 2025/5/2
Despite progress in active learning, evaluation remains limited by constraints in simulation size, infrastructure, and dataset availability. This study advocates for large-scale simulations as the gold standard for evaluating active learning models in systematic review screening. Two large-scale simulations, totaling over 29 thousand runs, assessed active learning solutions. The first study evaluated 13 combinations of classification models and feature extraction techniques using high-quality datasets from the SYNERGY dataset. The second expanded this to 92 model combinations with additional classifiers and feature extractors. In every scenario tested, active learning outperformed random screening. The performance gained varied across datasets, models, and screening progression, ranging from considerable to near-flawless results. The findings demonstrate that active learning consistently outperforms random screening in systematic review tasks, offering significant efficiency gains. While the extent of improvement varies depending on the dataset, model choice, and screening stage, the overall advantage is clear. Since model performance differs, active learning systems should remain adaptable to accommodate new classifiers and feature extraction techniques. The publicly available results underscore the importance of open benchmarking to ensure reproducibility and the development of robust, generalizable active learning strategies.
Skills
Python
Programming for data analysis, automation, and research tooling.
Machine Learning
Applied ML methods for text classification, active learning, and explainable AI.
Data Science
Statistical analysis, simulation workflows, and research data pipelines.
Open Science Standards
FAIR data principles, reproducibility, open-source development.
NLP & Systematic Review Automation
Development of tools and workflows to accelerate literature screening.