ASReview

Implements an iterative human-in-the-loop active learning loop where the system presents documents to reviewers, collects relevance judgments, retrains ML models on labeled data, and re-ranks unlabeled documents by predicted relevance for the next screening cycle. The approach prioritizes documents most likely to be relevant based on accumulated human feedback, reducing the total number of documents a reviewer must manually assess.

Supports multiple machine learning models for document relevance prediction with an extensible architecture allowing third parties to add custom models. The system abstracts model selection and retraining, though specific algorithms (Naive Bayes, SVM, neural networks, etc.) are not documented. Models are retrained on accumulated human judgments after each screening batch to adapt to reviewer preferences.

Provides open learning materials, documentation, and community support channels including weekly Thursday stand-ups and user meetings. The project is coordinated at Utrecht University with active community engagement. Learning resources enable researchers and developers to understand systematic review methodology, active learning concepts, and ASReview usage without formal training.

Allows researchers to simulate AI-aided reviewing by replaying historical screening decisions against different model configurations and active learning strategies. The simulation mode evaluates how different algorithms would have performed on past screening tasks, enabling comparison of model effectiveness without requiring new human labeling effort. Includes a Benchmark Platform for standardized performance comparison across configurations.

Distributes document screening across multiple expert reviewers in parallel, with AI proposing records to the crowd and coordinating their judgments. The system manages workflow distribution, collects independent relevance assessments from multiple reviewers, and aggregates their decisions. Enables large-scale screening by parallelizing reviewer effort across a team rather than requiring sequential single-reviewer assessment.

Accepts large-scale document collections and prepares them for screening through an ingestion pipeline. The system handles document parsing, metadata extraction, and preparation for ML model processing. Specific input formats, preprocessing steps, and vectorization methods are not documented, but the system claims to handle large-scale text screening without specified upper limits on corpus size.

Provides a user interface for reviewers to assess document relevance one-at-a-time or in batches, collecting binary (include/exclude) or multi-class relevance judgments. The interface presents documents prioritized by the active learning model, allowing reviewers to make rapid relevance decisions. Human judgments are immediately fed back to the system for model retraining and re-ranking of remaining documents.

Estimates and tracks the reduction in manual screening effort achieved through active learning prioritization. The system monitors how many documents reviewers can skip by relying on model predictions, typically claiming 95% workload reduction. Progress tracking shows reviewers how many documents remain to be screened and provides estimates of time to completion based on current screening velocity.

Enables researchers to create and manage screening projects with configurable parameters such as model selection, active learning strategy, stopping criteria, and reviewer assignments. Projects encapsulate a complete screening workflow including document corpus, human judgments, trained models, and metadata. Supports project persistence, allowing screening to be paused and resumed across sessions.

Provides an extensible architecture allowing developers to add custom modules for ML models, data processors, and screening workflows without modifying core code. The system is open-source with a public GitHub repository, enabling community contributions and custom deployments. Third parties can integrate custom algorithms, preprocessing pipelines, and domain-specific screening logic through a documented module interface.

Supports self-hosted deployment on local infrastructure, providing full control over data, models, and screening workflows without reliance on cloud services or vendor infrastructure. The open-source codebase can be deployed on institutional servers, ensuring data privacy and compliance with research governance requirements. Deployment method (Docker, direct installation, etc.) and infrastructure requirements are not documented.