Hard News
The Hard News classifier is a specialized text classifier that operates on news posts. It is meant to identify news containing authoritative, fact-based, and timely events. It differentiates between ‘soft news’, which focuses on more opinion-based content that is narrow in scope.
Statistics
Type | Speed | Partner Type |
---|---|---|
Stream Integrated Classifier + Post Processing | Instant | Datastreamer Internal |
Example Use Cases
The Hard News classifier identifies objective news articles versus subjective, more fact versus opinion-based, and consists of timely events. For example, using the hard news classifier on a keyword search on news sources can help the searcher find content about recent incidents while filtering out editorials, commentary, or opinion pieces that may contain those keywords but are not specific news reports.
Streaming Usage
Compatible Data Scoures
As a stream-integrated classifier, it is run on ingestion for specific sources.
Applicable Data Sources | Compatible? |
---|---|
wsl_news | Yes, English only |
opoint_news | Yes, English only |
Output
The Intent classifier is a binary label. The label value is ‘True’ if the news article is hard news, ‘False’ otherwise.
"enrichment":
{
"hard_news": {
"label": "No",
"confidence": 0.87
},
Post-Processing Usage
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": "hard_news",
"destination_path": "operations.hard_news",
"parameters": {
"language": "enrichment.language",
"main": "content.body"
}
}
]
}
```
Updated 5 months ago