Insight Scoring System
The Insight Score helps you identify and prioritize the most significant insights across your customer journeys. By combining impact and reliability factors, it highlights which insights deserve immediate attention, enabling teams to make informed decisions backed by customer data.
How the Insight Score Works
The Insight Score is calculated by multiplying two key factors:
1. Impact Factor
Measures the overall experience impact based on collected evidence. It aggregates sentiment scores from individual pieces of evidence and uses absolute values to reflect the impact, whether positive or negative. The calculation is based on a sentiment scale ranging from -2 to +2, with 0.1 increments for precision.
2. Reliability Factor
Determines the credibility of an insight based on the diversity and volume of data sources. It increases with the number of unique data points and reaches its highest value when multiple source types are combined. The calculation considers five distinct sources: interviews, support logs, feedback, survey replies, and manually created notes.
Each insight card displays a score badge, making it easy to spot the most impactful and validated insights at a glance.
Example Calculation
If an insight has an Impact Factor of 103.1 and a Reliability Factor of 6.67%, the resulting Insight Score would be 6.87.
How Journey AI Updates the Insight Score
When using Journey AI to generate journeys or upload new research files, we automatically extract and generate insights from your research materials, assign scores to new insights, and recalculate scores when new eviddddence enriches an existing insight.
"Mine Insights" in Journey AI
Each time you run "Mine Insights," Journey AI processes your selected files, extracts relevant insights, matches them to existing insights when applicable, and recalculates Insight Scores accordingly.
Journey AI continuously recalculates scores when insights are updated or enriched—rather than assigning a score only once at creation.
Manually Updating Insight Scores
You can influence and update Insight Scores through manual actions:
Linking/Unlinking Evidence
Adding or removing evidence automatically updates the Insight Score.
Adjusting Experience Impact
You can fine-tune an insight’s impact by clicking the face icon next to a quote in the insight view, setting the experience impact directly in the file context. Adjustments immediately recalculate the score.
Creating Manual Notes
If you have insights that aren’t tied to files, you can click "Add new notes.", enter your note, and set the experience impact. These notes contribute to the score just like quotes extracted from files.
Understanding the Evidence Structure
A key feature is the clear separation between Insights and Evidence.
Evidence Tab vs. Insight Tab
The Evidence tab contains quotes contributing to the score, while the Insight tab displays linked insights that provide context but don’t affect the score. This separation ensures precise control over what influences an Insight Score.
Working with Summary Insights
Summary insights, created via the summarization feature, function slightly differently. Instead of Evidence/Insight tabs, they have a Summary Evidence tab. This tab aggregates insights from nested journeys. The Summary Insight Score is the sum of all included Insight Scores. Any updates to nested insight scores automatically update the summary score.
Using Insight Scores from Older Versions
Legacy Quote Migration
All quotes created before the update have been automatically migrated. Old quotes remain visible in the Insights tab. The same content now appears in the Evidence tab as a new quote entity. You can manage these legacy quotes as needed.
For Very Old Setups (Early 2024)
For insights from early 2024 and before, you can still access old quotes, set experience impact values manually, and view verbatim content on hover.
Cleaning Up Legacy Quotes
If you’d like to remove outdated quotes without affecting new insights, go to the Insights Library, apply a filter for quotes, select them in table view, and click delete—this won’t impact the new quotes in the Evidence tab.
Best Practices for Maximizing Insight Scores
To make the most of the Insight Score system, collect evidence from multiple sources such as interviews, support logs, surveys, and feedback. Aim for 2-3 different source types per insight. Avoid overloading a single source type—too much data from one source reduces reliability. Sort insights using scores to prioritize key pain points, validate findings by comparing scores across multiple data sources.
By leveraging the Insight Score, you can transform raw customer data into actionable priorities—driving meaningful improvements to your customer experience.