As well as providing an easy-to-use, intuitive coding interface for manual coding, codeit has inbuilt power to support automated coding using text matching, text rules and Artificial Intelligence. This section provides an initial summary of the Artificial Intelligence (AI) available in codeit and when to use each one separately or in combination.


Summary of AI types

The table below summarises the layers of Artificial Intelligence that can be applied during the coding process, either individually or in parallel.  Click on the hyperlinks for a full guide on how to use each method.


AI LayerDetails
Text Matching

Automatically applies codes by matching verbatims against identical previously coded verbatims, or matching the verbatim text against the text of codeframe items.

Text Rules

Automatically applies codes by matching using user-defined text matching rules.
Text matching rules are defined using syntax that define text patterns to search for.

Machine Learning

codeit learns from the coded examples you provide and uses this learning to autocode.
This extends the autocoding beyond text or pattern matching, to autocode based on semantic theme. For example, coding examples like: "It helps me relax", "I find it calming" will enable to Codeit to autocode verbatims like: "This is great for chilling out" and "It is great for unwinding"
even though these phrases are completely textually dissimilar.

Theme Extractioncodeitit performs an automated analysis of a set of new verbatims using a combination of cutting-edge generative AI and our own proprietary AI techniques. As codeit is focused on the task of verbatim analysis it needs to provide tools and techniques that are optimised for this task - beyond those that are possible by "out of the box" generative AI tools. This method differs from the Machine Learning as there is no examples available for the model to learn from.