# Score forum comments for toxicity in bulk

**Use case:** 

Score a batch of forum or community comments for toxicity, severe toxicity, insults, threats, identity attacks and profanity. Each comment gets six scores from 0 to 1 and a flagged value. The attribute names are the same as in the Google Perspective API, so you can keep your moderation rules. English only.

## Input

```json
{
  "texts": [
    "Interesting point about the new update. I did not know that.",
    "Has anyone tested this on Linux? Mine crashes at startup.",
    "Nobody asked for your opinion, you clueless idiot.",
    "I disagree with the moderators here, but thanks for explaining the rule.",
    "You people are pathetic and this game is trash.",
    "This thread is full of useless trolls. Go back under your bridge."
  ],
  "attributes": [
    "TOXICITY",
    "SEVERE_TOXICITY",
    "INSULT",
    "THREAT",
    "IDENTITY_ATTACK",
    "PROFANITY"
  ],
  "threshold": "0.5"
}
```

## Output

```json
{
  "text": {
    "label": "Text",
    "format": "string"
  },
  "flagged": {
    "label": "Flagged",
    "format": "boolean"
  },
  "scores.TOXICITY": {
    "label": "Toxicity",
    "format": "number"
  },
  "scores.SEVERE_TOXICITY": {
    "label": "Severe toxicity",
    "format": "number"
  },
  "scores.INSULT": {
    "label": "Insult",
    "format": "number"
  },
  "scores.PROFANITY": {
    "label": "Profanity",
    "format": "number"
  },
  "scores.THREAT": {
    "label": "Threat",
    "format": "number"
  },
  "scores.IDENTITY_ATTACK": {
    "label": "Identity attack",
    "format": "number"
  }
}
```

## About this Actor

This example demonstrates how to use [Perspective API Alternative - Toxicity Detection API & MCP](https://apify.com/koyourmoon/perspective-api-alternative.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/koyourmoon/perspective-api-alternative.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/koyourmoon/perspective-api-alternative.md

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).