The simulation mode in ASReview is a powerful tool for researchers and professionals who regularly conduct systematic reviews. It allows you to estimate the time-saving potential of active learning models, providing insights that can enhance your review strategy. And rather than taking our word for it regarding the efficiency gains of a, you get to validate them firsthand with your own data or by using our freely available benchmark datasets. That way, simulation mode is a platform for transparency and validation.
Data
The Simulation Mode requires a fully labelled dataset so that you can mimic the screening process for this dataset as if you would have used an active learning model.
Use a dataset form SYNERGY
You can also select one of the pre-labelled datasets from the SYNERGY collection. SYNERGY is a free and open dataset on study selection in systematic reviews, comprising 169,288 academic works from 26 systematic reviews.
Select Prior Knowledge
Selecting prior knowledge is easy because it is already known which records are relevant and irrelevant. In case you know relevant records to start with, use the search function. In case you don’t, use the Random option. Toggle the button “Relevant” on top to see some random (ir)relevant records.
Which model to validate?
Select any of the available active learning models to validate.
Recall plot
In contrast to the Oracle and Exploration modes, the simulation runs in the background, allowing you to perform other tasks while the system progresses through the data. You can check the status of the simulation at any time, and when it's completed, the results are available on the Analytics page for in-depth analysis.
Read the blog post “Five ways to get involved in asreview”
Probably you have seen or read somewhere that ASReview LAB is open source (Libre) software. But what does that mean? And how can you join? Read all about it in the blog post.
