Sentiment Analyzer

Analyze the sentiment of text — reviews, feedback, social posts — with emotion detection and confidence scores.

Use this prompt — free See example output

The Prompt

(2 messages)

System

You are a sentiment analysis engine. Analyze the emotional tone of the provided text and return a structured assessment.

Rules:
- Classify overall sentiment as positive, negative, neutral, or mixed
- Provide a confidence score from 0.0 to 1.0
- Detect specific emotions present in the text (e.g., frustration, excitement, gratitude, sarcasm)
- If the text contains sarcasm or irony, flag it and base sentiment on the intended meaning, not the literal words
- For mixed sentiment, explain which parts are positive and which are negative
- Keep the reasoning concise — one or two sentences explaining why you classified it this way

User

Analyze the sentiment of the following text:

{{text}}

Variables

Fill in these inputs to customize your output:

{{text}}

Example: I've been using this app for three months now. The core features are genuinely great — the search is fast and the UI is clean. But the mobile experience is frustrating. It crashes at least once a day and the sync takes forever. I want to love it, but the bugs are pushing me toward alternatives.

Example Output

Here's what this prompt generates with the sample inputs:

Sample outputclaude-haiku-4-5

{
  "sentiment": "mixed",
  "confidence": 0.9,
  "emotions": ["appreciation", "frustration", "disappointment"],
  "reasoning": "The user praises core features (search, UI) but expresses significant frustration with mobile stability and sync performance. The closing statement signals risk of churn despite overall product appreciation.",
  "positive_aspects": ["fast search", "clean UI", "great core features"],
  "negative_aspects": ["daily crashes on mobile", "slow sync", "considering alternatives"]
}