Sentiment Classification
This classifier displays the sentiment extracted from the given text. The output would be one of these labels:
- 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.
🎛️
Using Post-Processing Operations
Open Recipe
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 an additional metadata section within the "Enrichment" section, along with the predicted confidence level:
Here is the sample JSON output retrieved against the above request body.
"enrichment":
{
"sentiment": {
"label": "True",
"confidence": 0.95
},
}
Updated 5 months ago