Learning Relationships Between Projects

Documentation Index

Fetch the complete documentation index at: https://docs.caplena.com/llms.txt

Use this file to discover all available pages before exploring further.

Learning relationships allow you to reuse topics from one project in another — saving time and maintaining consistency across similar datasets. If you’re looking for instructions on how to set up learning relationships, refer to the following article. Below is a clear explanation of how learning relationships behave in both the Legacy AI and the New AI, and when you should (or shouldn’t) use them.

​

Learning Relationships in the Legacy AI

In the Legacy AI, learning relationships play an important role in ensuring consistency across multiple related projects or waves. A learning relationship allows Project B to inherit both:

• The topic structure (topics, categories, sentiment), and
• The training you performed in Project A.

This means the AI will classify new comments in Project B using the patterns learned from Project A.

​

Learning Cascades (Multiple Projects)

If you connect several projects — e.g. Project A → Project B → Project C — the AI forms a learning cascade:

• C learns from B
• B learns from A
• A indirectly influences C

However, as the chain grows longer, the influence of earlier projects becomes weaker:

• With 3–5 connected projects → still strong
• With 10–20 projects → the earliest projects have minimal impact

​

What happens if you remove the learning relationship?

• Immediately — nothing changes. Your existing topics and assignments remain intact.
• Over time — once you start adjusting topics or making assignment changes, the AI will no longer reinforce the inherited learnings and may gradually lose what it inherited.

​

Ensuring new topics aren’t missed

When using learning relationships across multiple waves, consider: Generating additional topics — after selecting the learning project, use the “Additional Topics” feature to detect emerging patterns specific to the new dataset. Manual review — review a sample of comments without topics or use free-text search to catch new themes that may not exist in the inherited project.

​

Learning Relationships in the New AI

The behavior of learning relationships changes significantly in the New AI. Here is why:

​

Risk of confusing the New AI

Inheriting topics from another project can hurt performance if:

• That project wasn’t trained well, or
• It was trained using the Legacy AI, which works differently.

In these cases, inherited topics may not match your new dataset and can confuse the New AI, leading to lower-quality assignments.

​

Inherited topic descriptions often don’t fit the new dataset

Internal testing shows that if the new project contains even slight variations of the same question or a different data column context, inherited descriptions may no longer match well. This often results in:

• Lower topic assignment confidence
• More unassigned rows
• Inconsistent labeling behavior

​

Adding new topics can increase unassigned rows

When you inherit topics and then add new ones, the AI tries to interpret old descriptions written for the previous dataset alongside new ones written for your current dataset. This mismatch can further reduce assignment quality.