Day 1: Preparing Survey Data for Analysis

Survey Objective and Question Map

• Link each question to purpose
• Separate outcome and driver questions
• Identify demographic comparison needs
• Mark questions requiring caution

Survey Data Quality Review

• Check response completeness patterns
• Identify duplicate or suspicious responses
• Standardize scale direction consistently
• Document exclusions before analysis

Scale and Score Interpretation

• Use suitable summary statistics
• Compare scores with meaningful baselines
• Avoid overreading small differences
• Show sample sizes with results

Day 2: Analysing Ratings and Open Text

Open-Text Coding with AI

• Define coding themes before scaling
• Allow new themes to emerge
• Separate sentiment from topic
• Review ambiguous responses manually

Sentiment and Theme Analysis

• Identify recurring positive themes
• Surface material negative concerns
• Compare themes across segments
• Quantify themes without losing nuance

Response Segmentation

• Choose segments with sufficient responses
• Compare like-for-like populations
• Protect anonymity in small groups
• Interpret differences with context

Day 3: Turning Survey Evidence into Actions

Survey Finding Validation

• Recheck generated theme examples
• Confirm quoted text is authentic
• Test alternative coding interpretations
• Flag low-confidence classifications

Insight Prioritization

• Rank issues by impact and frequency
• Separate quick wins from structural issues
• Connect findings to accountable owners
• Define evidence needed for follow-up

Survey Action Report

• Summarize verified headline findings
• Show evidence behind priority themes
• Recommend actions with clear ownership
• Set measures for future comparison

• Case analysis applying Survey Objective and Question to realistic work
• Hands-on workshop developing Open-Text Coding with AI with evidence
• Peer review challenging Insight Prioritization against clear criteria
• Final lab producing Survey Action Report for workplace use