Discourse AI - Sentiment

[Discourse]

This topic covers the configuration of the Sentiment feature of the Discourse AI plugin.

Required user level: Moderator

Sentiment keeps tabs on your community by analyzing posts and providing sentiment and emotional scores to give you an overall sense of your community for any period of time. These insights can be helpful in determining the type of users posting within your community and interacting with one another.

Features

• Overall sentiment: compares the number of posts classified as either positive or negative
• Bar graph showcasing toggleable numerical value for positive, negative, and overall scores
• Emotion: number of topics and posts classified by multiple emotions, grouped by time frame
  • Today
  • Yesterday
  • Last 7 days
  • Last 30 days
• Reports for any period of time that can be accessed via settings
  • Yearly
  • Quarterly
  • Monthly
  • Weekly
  • Custom range
• Accessible to all staff users (admins and moderators)

Enabling Sentiment

Configuration

Sentiment is enabled by default for hosted customers. For manual steps see below

1. Go to Admin settings-> Plugins → search or find discourse-ai and make sure its enabled
2. Enable ai_sentiment_enabled for Sentiment Analysis
3. Head over to /admin/dashboard/sentiment to see their respective reports

Once enabled, Sentiment will automatically classify all new posts and backfill posts from the last 60 days via a scheduled job that runs every 5 minutes. To backfill posts older than 60 days, increase the ai_sentiment_backfill_post_max_age_days site setting.

Hosted by us?

Contact us at team@discourse.org if you need help adjusting backfill settings.

Self-hosted?

Increase ai_sentiment_backfill_post_max_age_days in your site settings to cover the desired time range. The scheduled backfill job will automatically process the older posts. For details on setting up the required model endpoints, see Self-Hosting Sentiment and Emotion for DiscourseAI.

Technical FAQ

How is topic/post data processed? How are scores assigned?

• Sentiment has a “per post” fidelity. For each post we are able to tell sentiment and then cut that data in many shapes (per tag / category / time etc… ). It compares the number of posts classified as either positive or negative. These are calculated when positive or negative scores exceed a fixed threshold of 0.6 (not currently configurable).

Are there any plans to add support for other languages?

• In the future Yes! both by adding multilingual simple Machine Learning (ML) models and by using multilingual Large Language Models (LLMs) to classify the data, instead of dedicated models.

What models are used to power Sentiment?

• Currently we are using SamLowe/roberta-base-go_emotions · Hugging Face and cardiffnlp/twitter-roberta-base-sentiment-latest · Hugging Face.

Caveats

• Posts classified as neutral (neither positive or negative) are not shown
• Private messages (PMs) are excluded from calculations

Last edited by @keegan 2025-10-23T22:28:36Z

Last checked by @hugh 2024-08-06T05:27:46Z

Check document

Perform check on document: