Sentiment Classification (Long content )
Sentiment detection for English long-form 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
Type | Speed | Partner Type |
---|---|---|
Post-Process Classifier | On Request | Datastreamer Internal |
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
},
}
Updated 7 days ago