Simulation Infrastructure

ASReview - Simulation Infrastructure

The true power of ASReview is the simulation research infrastructure we offer to run large simulation studies on many datasets using many different models.

It's crucial to have a high quality, fully labeled dataset. Remember our mantra: "Quality in => Quality out". For optimal dataset quality, check out our ASReview DataTools package. ASReview Datatools is an extension to ASReview LAB that can be used to: Describe basic properties of a dataset, Convert file formats, Deduplicate data, Stack multiple datasets, Compose a single (labeled, partly labeled, or unlabeled) dataset from multiple datasets.
SYNERGY is a free and open dataset on study selection in systematic reviews, comprising 169,288 academic works from 26 systematic reviews. Only 2,834 (1.67%) of the academic works in the binary classified dataset are included in the systematic reviews. This makes the SYNERGY dataset a unique dataset for the development of information retrieval algorithms, especially for sparse labels. Due to the many variables available per record (i.e. titles, abstracts, authors, references, topics), this dataset is useful for researchers in NLP, machine learning, network analysis, and more. In total, the dataset contains 82,668,134 trainable data points.
Command Line Interface
ASReview LAB comes with a command line interface for simulating the performance of ASReview algorithm.
This official extension to ASReview LAB extends the software with tools for plotting recall curves and extracting the statistical results of several performance metrics. It computes the the confusion matrix consist of the True Positives (TP), False Positives (FP), True Negatives (TN), and False Negatives (FN). Also, performance metrics are available like the Work Saved over Sampling at a given recall (WSS), the Time to Discover a relevant record as the fraction of records needed to screen to detect this record (TD), and the Average Time to Discover (ATD) as an indicator of how many records need to be screened on average to find all relevant records in the dataset.
Unlock the full Power of Simulation Mode
ASReviews' Makita (MAKe IT Automatic) is a workflow generator for simulation studies using the command line interface of ASReview LAB. Makita can be used to effortlessly generate the framework and code for your simulation study. Using Makita templates, different study structures can be generated to fit the needs of your very own study. If your study requires a unique template, you can create a new one and use it instead.
Cloud usage
We offer several solutions for running simulations in the cloud via SURF, Digital Ocean, AWS, Azure, Kubernetes.
Work together with ASReview
We offer open teaching materials to get you introduced to the research infrastructure.
Visit our discussion forum to get inspired or to ask questions.

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.