Analyze User Feedback Sentiment by Segment with ChatGPT
Group supplied feedback by situation or job and summarize what drives satisfaction or frustration. Track how each theme relates to the original comments.
中文Install in ChatGPT
The publisher targets Codex. Try the standalone text instructions in an eligible ChatGPT workspace with skills and uploads enabled. The documented installation path was checked. Workspace runtime verification is pending.
- Download pm-market-research/skills/sentiment-analysis/SKILL.md from the pinned GitHub source. Put the file in a folder named sentiment-analysis and keep its filename, name, and description.
- In an eligible ChatGPT workspace with uploads enabled, open Plugins, Skills, Create, and Upload from your computer. Use a skill package format accepted by your file picker.
- Check the scan and the Installed list. You can also choose Create with editor and keep the original name, description, and instructions. In a new chat, select the skill with @ and try the fictional example.
Example task
Use three fictional comments. A browser likes filters but sees too many choices, an editor saves time with bulk edits but finds preview slow, and an administrator likes change history but wants export. Summarize themes and evidence by group.What to check
Each group has grounded positive and negative themes. Any score states its method and small-sample limit. Findings describe the three supplied comments.
Original SKILL.md on GitHub · Updated
Frequently asked question
Can I calculate a real NPS from three comments?
NPS needs responses to the standard recommendation question and an appropriate sample. Use these comments for themes and qualitative sentiment, and note that recommendation scores are unavailable.