analyze_ai_sentiments

This module is part of the AI module ecosystem and included in DXPR CMS.

Your Content's Tone Says More Than You Think

Content that sounds too promotional loses trust. Content that's too academic loses readers. Content aimed at the wrong audience loses both. This module measures the dimensions that determine whether your content actually connects - trust, objectivity, audience fit, and reading level - so you can tune the tone before you publish.

You need AI Sentiments Analysis if

• You publish for different audiences and need to verify the tone matches each segment
• Your content sometimes reads as too promotional, too dry, or too complex - but feedback comes too late
• You need to ensure content meets credibility or objectivity standards (journalism, academia, regulated industries)
• You want a reading level check that goes beyond Flesch-Kincaid to actual CEFR language proficiency levels

What You Get

• Four analysis dimensions per page

  Each content entity is scored on a -1.0 to +1.0 scale across four dimensions, with meaningful labels at each end of the spectrum:

  • Trust & Credibility - Overly Promotional ↔ Authoritative
  • Objectivity & Bias - Opinion-Based ↔ Fact-Based
  • Audience Vibe Check - Gen Z ↔ Boomer targeting
  • CEFR Reading Level - A1 Beginner ↔ C2 Proficient
• Fully customizable dimensions

  Add your own analysis dimensions, rename the labels, reorder by priority, or remove ones that don't apply to your content strategy.

• Batch analysis for content audits

  Score your entire content library to identify tone inconsistencies, find content that's too complex for your audience, or flag pages that read as overly promotional.

• AI Coding Assistant Integration

  Sentiment analysis is available to AI coding assistants
  through the Analyze module's built-in
  Agent
  Skills file. Run
  drush analyze:setup-ai to enable, then ask
  naturally:

  • "Run sentiment analysis on all articles"
  • "Check the trust and objectivity scores for the
    homepage"
  • "Analyze reading level across all blog
    posts"

  Compatible with Claude Code, Codex CLI, Gemini CLI,
  GitHub Copilot, Cursor, and other tools supporting the
  standard.

• Site-wide sentiments report

  A filterable Views report shows sentiment scores across all content - spot patterns by content type, author, or date range.

Getting Started

1. Set up an AI provider at /admin/config/ai/providers
2. Review and customize sentiment dimensions at /admin/config/analyze/sentiments
3. Enable the analyzer per content type at /admin/config/content/analyze-settings
4. Open any content entity's Analyze tab to see the scores

Prefer a turnkey demo site?

Spin up DXPR CMS - Drupal pre-configured with DXPR Builder, DXPR Theme, the full Analyze suite including AI Sentiments, and security best practices out of the box.

Get DXPR CMS »

Additional requirements

This module requires:

• Analyze module (>=1.1.0)
• AI module with a configured chat provider
• Views Color Scales module