The Zen of Elas¶
Elas is the mascotte of ASReview and your Electronic Learning Assistant who will guide you through the interactive process of making decisions using Artificial Intelligence in ASReview. Elas comes with some important principles:
Humans are the Oracle It’s the interaction between humans and machines which will take science a major leap forward. We believe a human should make the final decision about whether to mark a record as relevant/irrelevant (hence, is the Oracle), and the software merely orders the records on the relevance score as predicted by the model in each iteration of the active learning cycle.
Open & Transparent We are strong proponents of open science, and therefore ASReview code is free and openly available. We value your privacy and hence do not get to see any of your data (everything stays on your device). We do hope you believe like us in the FAIR data principles and publish your data, results, and project file on a data repository.
Unbiasedness ASReview signed the DORA-declaration. ASReview only presents text for unbiased decision making. When screening, for example, academic papers, ASReview show titles and abstracts only, and does not present authors or journal names. This way, you can focus on what is truly important (the content) and don’t get tempted to use irrelevant information.
AI-aided Interface Simplicity is the ultimate sophistication (Davinci), and, therefore, we keep the front-end as clean as possible. Boring but efficient because the magic happens under the hood.
Garbage in garbage out ASReview focuses on the machine learning part of the pipeline and not on the preprocessing or postprocessing of the data (which reference managers are designed for). Be aware of the principle GIGO and check the quality of your data first. Don’t blame Elas if the performance is not as good as expected due to low-quality input data.