
Jev Review Intelligence — Classify Customer Reviews
Classify supplied product reviews into typed topic, severity, and actionability fields using your TypeSafe Jev key.
Jev Review Intelligence — Classify Customer Reviews returns 8 documented output fields, including index, sourceId, review, topic and severity. Every field carries a declared type, a written description and an example value. 22 runs are recorded on Apify.
- 8
- Output fields
- 3
- Inputs
- 22
- Runs
- 2026-10-16
- Last run
01 — output
What it returns
Every field the extractor writes to its dataset, with its type, a written description and an example value.
| Field | Type | What it holds | Example |
|---|---|---|---|
| index | string | number | boolean | array | objectnull | Position of this row within the run. | 1 |
| sourceId | string | number | boolean | array | objectnull | Identifier of the input record this row came from. | rec_01 |
| review | string | number | boolean | array | objectnull | The review text that was judged. | The battery lasted two days. |
| topic | string | number | boolean | array | objectnull | The topic assigned to this row. | usability |
| severity | string | number | boolean | array | objectnull | How severe this row is judged to be. | 2 |
| actionableProbability | string | number | boolean | array | objectnull | Probability the row contains something actionable, on a 0-1 scale. | 0.4 |
| judgments | string | number | boolean | array | objectnull | The full structured judgement returned by the model. | {"stance":{"choice":"recommended"}} |
| model | string | number | boolean | array | objectnull | Identifier of the model that produced the judgement. | jev-latest |
02 — sample
One record
Assembled from the example values declared on the schema above, not invented at render time.
{
"index": 1,
"sourceId": "rec_01",
"review": "The battery lasted two days.",
"topic": "usability",
"severity": 2,
"actionableProbability": 0.4,
"judgments": "{\"stance\":{\"choice\":\"recommended\"}}",
"model": "jev-latest"
}03 — input
What you give it
| Input | Type | Description |
|---|---|---|
| records | arrayrequired | Rows containing review text. |
| typesafeApiKey | stringoptional | Secret — supply your own value. |
| maxItems | integeroptional | Hard cap on enriched rows. |
04 — run
Run Jev Review Intelligence on your own input
It runs in the cloud on Apify. Nothing to install, and you are billed per result returned rather than per attempt.
05 — questions
Asked before running it
8 of 8 fields described
- What does Jev Review Intelligence — Classify Customer Reviews return?
- It returns 8 documented output fields: index, sourceId, review, topic, severity, actionableProbability, judgments and model. Each field declares its type, a description of what it holds, and an example value.
- What input does Jev Review Intelligence — Classify Customer Reviews require?
- records is required. A further 2 inputs are optional. The full input schema, with types and defaults, is below.
- Does Jev Review Intelligence — Classify Customer Reviews need an API key or login?
- Yes — typesafeApiKey is marked secret and must be supplied by you. Nothing else in the input schema needs credentials.
- How do I run Jev Review Intelligence — Classify Customer Reviews?
- It runs on Apify. Start it from its listing with the inputs above, or call the Apify API with the Actor's ID. Results land in a dataset you can export as JSON, CSV or Excel, or read through the Apify API into your own pipeline.