Classify Social¶

POST classify/social ¶

Classify a list of social posts and return scored categories and keywords.

There is a hard limit of 1,000 posts per call.

Resource URL ¶

https://api.econtext.com/v2/classify/social

Parameters ¶

Parameter	Type	Description
social (required)	array	A list (no more than 1,000 items) of strings.
classification_type (optional)	integer	Select the classification method: `1` for rule-based, `2` for model-based, or `0` for a hybrid rule-based + model-based (defaults to `1`)
ml_threshold (optional)	float	Specify a confidence threshold for accepting an ML prediction. A lower value increases recall at the expense of precision (defaults to `0.75`)
flags (optional)	boolean	Provide Object Flags to help filter out certain content categories including adult, firearms, gambling, etc (defaults to `false`)
entities (optional)	boolean	Perform Named Entity Recognition (NER) on the content submitted (defaults to `false`)
sentiment (optional)	boolean	Perform sentiment analysis on the content submitted (defaults to `false`)
taxonomy_timestamp (optional)	integer	A Unix timestamp instructing the classifier to use categories from the eContext Taxonomy that existed at this point in time. This will allow recently deleted categories to remain and hides newly created categories
dataset_id (optional)	string	A Custom Taxonomies id to use in lieu of the default eContext Taxonomy
add_last_node (optional)	bool	Include the last category node, or leave at the parent category
classify_limit (optional)	integer	Limit the number of categories that may be returned per post
classify_timeout (optional)	float	The number of seconds to spend on a classification task

The result set includes scored_categories and scored_keywords as well as a categories dictionary. The scored_keywords object contains a list of high-value phrases that eContext was able to pull out of the submitted text as well as associated scores for each. The scored_categories object contains a list of category_id and score objects where the category_id corresponds to an item in the categories dictionary. Higher values indicate a higher score.

Example Request ¶

POST Request ¶

curl -X POST -u username:password --data-binary @classify-social-input.json \
--header "Content-type: application/json" \
https://api.econtext.com/v2/classify/social

The contents of classify-social-input.json:

{
    "entities":true,
    "flags":true,
    "sentiment":true,
    "social":[
        "HAPPY PI DAY 3.141592653589793238462643383279502884197169399375...",
        "Happy birthday, MIT! The Institute was founded April 10, 1861 by William Barton Rogers. #tbt",
        "Consciousness is a state of matter",
        "Flying car by @MITAeroAstro spinoff @Terrafugia moves from science fiction to reality",
        "Amazing Time-Lapse Video Shows Evolution of #Universe Like Never Before",
        "MIT alum @JeopardyJulia now trails only @kenjennings for all-time #Jeopardy! wins",
        "Happy b-day Nikola #Tesla! Startup @WiTricity is bringing his ideas on wireless power to life",
        "Seen at the Student Center this afternoon: Tetris hash browns!",
        "Researchers at @eapsMIT say a large earthquake may occur 5 miles from Istanbul",
        "MIT's robotic cheetah can now run and jump untethered",
        "Spacesuit from @MITAeroAstro shrink-wraps to astronauts' bodies",
        "This social post should be flagged for fireworks and gambling references"
    ]
}