ASReview

What is ASReview?

ASReview (asreview.nl) is an open-source, free active learning software tool designed to accelerate the screening phase of systematic reviews, scoping reviews, and meta-analyses. Developed and maintained by researchers at Utrecht University, it solves the exhausting burden of manual title and abstract screening by employing artificial intelligence and active machine learning algorithms.

By starting with a few known relevant and irrelevant "prior know" seed papers, ASReview's active learning model continuously trains on reviewer decisions. It intelligently re-ranks unread abstracts, presenting the most likely relevant articles first. Research demonstrates that ASReview can reduce manual screening effort by up to 95% while ensuring researchers do not miss crucial papers.

• Platform Focus: Open-source active learning, AI-assisted abstract screening, text mining, and systematic review acceleration
• Developer / Organization: Utrecht University (Open Source Research Project)
• Launch Year: 2019

Use Cases:

• Accelerating title and abstract screening for large systematic literature reviews across medical, social, and physical sciences
• Reducing human screening workloads by up to 95% using active machine learning algorithms
• Running transparent, reproducible open-source screening pipelines locally or via Python libraries
• Conducting methodological research on AI citation screening efficiency and recall curves

Technology:

• Active learning framework combining feature extraction (TF-IDF, Doc2Vec, BERT) with machine learning classifiers (Logistic Regression, SVM, Neural Networks)
• Cross-platform deployment supporting Python CLI, desktop web app interfaces, and Jupyter notebook extensions
• Completely open-source architecture allowing local execution with zero data privacy leakage

Target Users:

• Academic researchers, PhD students, and librarians conducting systematic and scoping reviews
• Data scientists and methodologists studying active learning and text classification models
• Research teams operating under strict institutional data privacy requirements who need local execution

Corporate Entity: Operates as an open-source academic project hosted at Utrecht University (asreview.nl)

Key features of ASReview

ASReview's key features are

• Active Learning Ranking: Continuously re-ranks unread papers based on your screening decisions, surfacing relevant articles faster.
• 100% Free & Open Source: Completely free software with no licensing fees, usage caps, or commercial paywalls.
• Local Data Privacy: Run entirely on your local machine to ensure sensitive or unpublished research data never leaves your computer.
• Flexible Algorithm Choice: Choose and customize feature extractors (e.g., TF-IDF, BERT) and classifiers (e.g., SVM, Naive Bayes).
• Python API & Extensions: Integrates smoothly into Python data science workflows and Jupyter notebooks.
• Comprehensive Simulation Tools: Evaluate past review datasets to test and benchmark active learning efficiency.

ASReview Pricing

ASReview is 100% free and open-source software licensed under the Apache 2.0 license.

Free Open-Source Access:

• $0 / Completely Free
• Includes full software access, active learning screening models, local desktop app, Python library, and simulation tools

Who is using ASReview?

ASReview is designed for researchers, data scientists, and systematic reviewers, including

• Systematic Reviewers & Epidemiologists: Screening tens of thousands of citations rapidly with high statistical recall
• University Researchers & Students: Automating thesis literature screening at zero cost
• Data Scientists & AI Researchers: Experimenting with active learning text classification algorithms

Best ASReview Alternatives

Some of the strongest ASReview alternatives include

• Rayyan
• Covidence
• EPPI-Reviewer
• DistillerSR
• Paperguide
• Abstrackr

Pros and Cons of ASReview

Pros

• 100% free and open-source with zero subscription costs or record limits
• Local installation ensures complete data privacy and security for confidential manuscripts
r
• Active learning model dramatically cuts down manual screening time (up to 95% effort reduction)
• Extensible Python framework allows advanced users to customize models and pipelines

Cons

• Focused strictly on title/abstract screening—does not manage full-text PDF data extraction or team consensus workflows directly
• Requires technical setup (Python installation or desktop app launcher) compared to turnkey cloud platforms
• Lacks built-in Cochrane integration or automated PRISMA diagram generators

Why Choose ASReview?

ASReview is an ideal choice for researchers and academic teams who want a powerful, free, open-source active learning tool to automate citation screening while maintaining complete control over their data locally.

• Accelerates title and abstract screening by up to 95% using active machine learning
• Completely free and open-source with no commercial subscription barriers
• Runs locally on your computer to guarantee absolute document privacy
• Provides a flexible Python API for advanced data science customization

ASReview vs. Competitors

The main difference between ASReview, Rayyan, Covidence, and DistillerSR is that ASReview is a free, open-source active learning desktop tool focused purely on intelligent citation screening algorithms and local data privacy, whereas Rayyan offers a cloud-based freemium screening platform, Covidence provides Cochrane-partnered team workflows, and DistillerSR targets enterprise regulatory compliance. ASReview stands out for its open-source active learning transparency and zero cost.

How do we rate ASReview?

ASReview Review

ASReview is an exceptional open-source tool for researchers aiming to streamline literature screening. Developed by Utrecht University, its active learning algorithm intelligently re-ranks titles and abstracts to reduce manual review effort by up to 95%. Backed by local execution for total data privacy and a 100% free open-source model, it is an indispensable asset for systematic reviewers and data scientists.

Conclusion

ASReview is a premier open-source active learning platform that revolutionizes citation screening. By combining state-of-the-art machine learning ranking, local data privacy, Python extensibility, and zero cost into a robust software package, it enables researchers worldwide to conduct systematic reviews with unprecedented speed and efficiency.