# Extract restaurant review signals from X (Twitter)

**Use case:** 

Score dining posts on food, service and value with custom questions, so restaurant groups build review dashboards from public posts without survey costs.

## Input

```json
{
  "searchTerms": [
    "(restaurant OR dinner OR brunch) (delicious OR terrible OR \"service was\" OR overpriced) lang:en -filter:retweets"
  ],
  "texts": [
    "We shipped dark mode today. Try it and tell us what breaks."
  ],
  "maxItems": 100000,
  "analysis": {
    "questions": [
      {
        "id": "food",
        "type": "score",
        "version": "1",
        "instructions": "How does the author rate the food?",
        "levels": [
          "Negative.",
          "Neutral or mixed.",
          "Positive."
        ]
      },
      {
        "id": "service",
        "type": "score",
        "version": "1",
        "instructions": "How does the author rate the service?",
        "levels": [
          "Negative.",
          "Neutral or mixed.",
          "Positive."
        ]
      },
      {
        "id": "value",
        "type": "probability",
        "version": "1",
        "instructions": "Does the author consider the meal worth its price?"
      }
    ]
  },
  "monitor": {
    "maxBaselineRows": 100000
  },
  "twitterContent": "web scraping OR #datascience",
  "twitterHandles": [
    "elonmusk",
    "@nasa"
  ],
  "tweetIds": [
    "1846987139428634858"
  ],
  "listIds": [
    "1748648376080666720"
  ],
  "mode": "legacy",
  "queryType": "Latest",
  "lang": "en",
  "filter:has_engagement": false,
  "include:nativeretweets": false,
  "filter:twimg": false,
  "filter:native_video": false,
  "filter:vine": false,
  "filter:consumer_video": false,
  "filter:pro_video": false,
  "filter:spaces": false,
  "filter:mentions": false,
  "filter:hashtags": false,
  "includeSearchTerms": true,
  "respectProfileSubpages": false,
  "min_faves": 0,
  "-min_faves": 0,
  "min_retweets": 0,
  "-min_retweets": 0,
  "min_replies": 0,
  "-min_replies": 0,
  "filter:blue_verified": false,
  "filter:nativeretweets": false,
  "filter:replies": false,
  "filter:quote": false,
  "filter:media": false,
  "filter:images": false,
  "filter:videos": false,
  "filter:links": false,
  "filter:news": false,
  "filter:safe": false,
  "within": "10km",
  "geocode": "37.7749,-122.4194,10km",
  "includeRaw": false,
  "includeArticles": false,
  "includeUnavailableFields": false,
  "includeOriginalTweet": false
}
```

## Output

```json
{
  "tweet": {
    "label": "Original tweet",
    "format": "object"
  },
  "analysis": {
    "label": "Analysis",
    "format": "object"
  },
  "monitor": {
    "label": "Change since baseline",
    "format": "object"
  }
}
```

## About this Actor

This example demonstrates how to use [X Tweet Classifier with AI Analysis | $0.0003/Tweet](https://apify.com/xquik/x-twitter-tweet-classifier.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/xquik/x-twitter-tweet-classifier.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/xquik/x-twitter-tweet-classifier.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`).