ANALYZE

Community Learning Resource

Step 3: Analyze

The Analyze step of the feedback loop is where raw feedback starts to become meaningful.

Here, you look across everything you’ve collected and identify patterns, themes, and trends that can guide decisions. In an AI- and tech-enabled loop, tools and large language models can help cluster open-ended responses into common themes, quantify how often each issue shows up, and visualize results over time.

But, more analysis is not always better: your choices about methods and tools should be driven by the questions and decisions you surfaced in the buy-in and design steps, the type of data you have (quantitative, qualitative, or both), and your team’s actual capacity.

Because AI can misread nuance or reinforce bias—especially across languages and dialects—it’s essential to use models trained on diverse linguistic patterns and have staff review and interpret outputs, combining automated insights with human judgment and, where possible, with the perspectives of the people whose feedback you’re analyzing.

Typical Challenges Organizations Face

Here is a common challenge that we have found organizations experience in the Analyze stage of their feedback loop:

Response Variation

Large volume of open-ended responses

Tech Tools & Use Cases

Here are two ways that we have found organizations using technology tools in the Analyze stage of their feedback loop:

Tools

Quantify qualitative data

Quantify open-ended question responses into common themes and mark the frequency/volume of feedback

AI Tools & Use Cases

Some organizations have found using Large Language Models (LLMs) to help them during the Analyze stage of their listening and feedback strategy.

Large Language Models (LLMs)

ChatGPT, Latimer, Gemini, CoPilot
Beehive.ai

Response Categorization

Use AI text clustering to categorize open-ended survey responses by theme (e.g., “access,” “staff communication,” “wait times”)

Here is a resource to consider if using an LLM to design your strategy is the right move for your organization.

Ethical Considerations

Staff, Organizational, and AI Bias

Ensure the AI model is trained on diverse linguistic patterns; staff review outputs for nuance

Learn more about ethical considerations and recommendations here.

Page updated

Report abuse