# Introducing Discourse AI Sentiment Analysis: New Admin Report Available

**URL:** <https://meta.discourse.org/t/introducing-discourse-ai-sentiment-analysis-new-admin-report-available/355901>\
**Category:** Announcements\
**Tags:** ai, ai-sentiment\
**Created:** [March 5, 2025, 6:01pm UTC](https://meta.discourse.org/t/introducing-discourse-ai-sentiment-analysis-new-admin-report-available/355901 "2025-03-05T18:01:04Z")\
**Posts on this page:** 1\
**Showing post:** 5

<div class="post-metadata">

**Author:** ![putty](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/putty/32/370902_2.png) [@putty](https://meta.discourse.org/u/putty)\
**Post date:** [March 7, 2025, 3:45pm UTC](https://meta.discourse.org/t/introducing-discourse-ai-sentiment-analysis-new-admin-report-available/355901/5 "2025-03-07T15:45:43Z")

</div>

Is there a way to modify an analysis that is incorrect?

For example, we have a section of our community for guides, which use a “issue/problem addressed & solution” format. It’s flagging all these as negative, presumably because they’re describing an issue—but I think they are far from negative when it comes to sentiment.

---

_[View the full topic](https://meta.discourse.org/t/introducing-discourse-ai-sentiment-analysis-new-admin-report-available/355901)._