# Sentiment

The Sentiment tab provides deep analysis of how AI search platforms talk about your brand. Rather than just tracking whether you're mentioned, Sentiment reveals *what* AI engines say about you and whether it's positive, negative, or neutral — broken down by automatically extracted themes.

## Core Metric

### Sentiment Score

Positive mentions plus half of neutral mentions, divided by total brand mentions (0-100). Higher values indicate more favorable sentiment in how AI platforms portray your brand.

Sentiment scores are color-coded throughout the tab:

| Score Range | Label    | Color |
| ----------- | -------- | ----- |
| 60-100      | Positive | Green |
| 40-59       | Neutral  | Gray  |
| 0-39        | Negative | Red   |

## How Themes Work

AirOps automatically extracts recurring themes from AI-generated answers that mention your brand. Themes are short descriptors (2-3 words) representing topics that AI engines consistently associate with your brand — such as "customer support", "pricing flexibility", or "product reliability".

Themes are extracted using a multi-stage AI analysis of your answer data and are refined over time as new data comes in.

## Sentiment Score Time Series

Track how your sentiment score trends over time with four views:

### Overall

View your aggregate sentiment score trend across all platforms, topics, and themes. Track whether sentiment is improving, stable, or declining.

### By Topic

Break down sentiment score by topic cluster. Identify which topics drive the most positive or negative sentiment and track shifts over time.

### By Platform

Compare sentiment scores across AI answer engines (ChatGPT, Gemini, Perplexity, Google AI Mode, Google AI Overviews). Understand which platforms portray your brand most favorably.

### By Theme

View sentiment score trends for individual themes over time. Track whether specific aspects of your brand perception are improving or declining.

## Sentiment Treemap

The treemap provides a visual overview of all your sentiment themes at a glance:

* **Tile size** represents how frequently the theme appears (occurrences)
* **Tile color** ranges from pink (negative sentiment) to teal (positive sentiment)

Hover over any tile to see the theme name, sentiment score, and a breakdown of positive, negative, and neutral counts.

Use the sentiment filter to focus on **All Sentiments**, **Positive**, or **Negative** themes.

## Sentiment Themes Table

The themes table provides a detailed breakdown of each extracted theme with the following columns:

| Column          | Description                                                         |
| --------------- | ------------------------------------------------------------------- |
| Theme           | The name of the extracted theme                                     |
| Sentiment Score | The theme's sentiment score (0-100), color-coded by sentiment level |
| Volume          | Percentage of total theme occurrences this theme represents         |
| Occurrences     | Total number of times this theme appears across answers             |

### Filtering by Sentiment

Use the sentiment dropdown to filter themes by **All Sentiment**, **Positive** (score >= 60), or **Negative** (score < 40).

### Drill-Down to Answers

Expand any theme row to see the individual AI-generated answers that contributed to that theme's sentiment. Each answer row shows:

* **Provider** — which AI platform generated the answer
* **Date** — when the answer was captured
* **Answer text** — a snippet of the AI-generated response

Click on any answer to open a detail panel with the full answer content.

## Filters

All charts and metrics on this page can be filtered by:

* **Date Range**: Select a time period for your analysis
* **Region**: Filter by geographic region
* **Prompt Type**: Category-related (general prompts) vs Brand-related (prompts mentioning your brand directly)
* **Topic**: Filter by topic clusters
* **Platform**: Filter by specific AI answer engine
* **Persona**: Filter by audience persona