What is aspect-based sentiment analysis?

Instead of one overall label, it scores sentiment for each topic or feature mentioned, such as "battery life positive, price negative." This is far more useful for product and support analytics because it tells you what people actually like or dislike.

Why specify a numeric scale?

A fixed scale (3, 5, or 10 points) makes outputs comparable and aggregatable. Without it, models drift between labels and free-text, which breaks downstream charts and thresholds.

Why ask for JSON output?

Structured JSON lets you parse results programmatically and load them into a database or dashboard. The generated prompt pins the exact schema so the model returns clean, machine-readable rows every time.

Does this tool analyze my text?

No. It builds the prompt. You run the prompt in your own LLM with your data. The builder runs locally in your browser and only outputs prompt text.

How does it handle mixed or sarcastic sentiment?

The prompt instructs the model to detect mixed sentiment per aspect, flag sarcasm or irony, and report an emotional intensity score so a strongly worded complaint reads differently from a mild one.

Sentiment Analysis Prompt Builder

Sentiment analysis prompt builder

A single “positive / negative” label throws away most of what a review or support ticket is telling you. This builder writes an LLM prompt that performs aspect-based sentiment analysis: it scores each facet you care about, estimates emotional intensity, identifies the opinion target, and returns the result in a structured format you can parse. You define the dimensions; the prompt enforces them.

How it works

You supply the text type, the aspects to evaluate, a numeric scale, and an output format. The builder assembles a system-style instruction that defines the scale precisely, lists the aspects to score, and pins the output schema — JSON or a table. It also adds standing rules: report per-aspect polarity, flag sarcasm, give an intensity score, and use a neutral midpoint rather than forcing a positive/negative choice. The result is a reusable prompt you drop into a batch pipeline or a one-off analysis.

Tips and example

Name aspects the way customers do. “Shipping speed” and “delivery” may need to be separate columns depending on your product.
Pick the smallest scale that captures variance. A 5-point scale is usually enough; 10-point only helps when you need fine ranking.
Use JSON for pipelines, tables for eyeballing. JSON parses cleanly into a database; the table format is easier to skim by hand.
Batch it. Feed many reviews at once and ask for one JSON array — the prompt already requests one object per input.