Sentiment Classification (long content)

This classifier analyzes sentiment in English long-form content, producing one of three labels with a confidence score ranging from 0 to 1. While it performs effectively across various English content, it delivers optimal results when applied to long-form inputs.

• Neutral
• Positive
• Negative

Statistics

Compatible Data Sources

As a Post-Processing operation, it can be run on any data source.

📘

Recipe Available

View the below recipe to see it in action, and easily view how to integrate it into your own data pipeline.

Usage

This Operation allows a user to specify the destination field, source fields, and any separator.

{
    "query": {
		...
},
    "operations": [
        {
            "name": "sentiment",
            "destination_path": "operations.sentiment",
            "parameters": {
                "language": "enrichment.language",
                "body": "content.body"
            }
        }
    ]
}

Output

The classifier adds a new metadata section within the "Enrichment" section, along with the predicted confidence level. Here is the sample JSON output retrieved against the above request:

"enrichment":  
    {  
      "sentiment": {  
        "label": "True",  
        "confidence": 0.95  
       },  
    }