Next, is the Tagging module. Here, you can build a customized tag hierarchy of concepts of interest, and then apply these tags to records in your nest to extract qualitative data. The hierarchy you build is specific to your nest, and should reflect the qualitative information you want to present.
For each nest, you need to configure a Tag Hierarchy before tagging that nest's records. Tag Hierarchies structure the qualitative content that you tag, and Qualitative Synthesis uses the Tag Hierarchy as the basis for its structure.
Core Smart Tags is an AI Extraction tool for commonly extracted elements in research projects: Population, Interventions/Comparators, & Outcomes (PICOs), Study Type, Study Location, and Study Size. There are several advantages of Core Smart Tags: The tool currently extracts from Study Abstracts and is incorporated in several parts of the AutoLit workflow including Search Exploration...
For enterprise level users only, Adaptive Smart Tags (ASTs) can be used to recommend or extract custom data from all study abstracts and/or full texts using an OpenAI Large Language Model (LLM). See a full disclosure of what data Adaptive Smart Tags use and how it works, see the Nested Knowledge AI Disclosure. Adaptive Smart Tags...
Tags reflect the qualitative content of underlying studies and provide method for attaching text or images from these studies. After tags have been configured, and you have included studies, you can begin applying tags in the Tagging module. You can also apply tags during the Screening stage! Once a tag is applied, it is immediately viewable...
You may have a legacy or existing project you wish to upload and continue in Nested Knowledge. To do this, first ensure you have imported your records via a Literature Search and uploaded screening decisions, which will be matched to these records (and will only do so if they already exist in your nest!). The next...
