What is the Seekr Score for News?
Seekr uses our proprietary AI platform powered by broad LLMs and natural language processing to score news articles for reliability and produce an easy-to-understand Seekr Score.
Seekr technology reads the entirety of each article, including any available meta data, and produces an overall quality score based upon the highest journalistic standards, detection of cognitive biases, and domain intelligence.
The Seekr Score for News produces a precise score between 1-100 as an integer. This score is then categorized into 5 simple levels of reliability:
Very Low: 1-20Low: 20-40Medium: 40-60High: 60-80Very High: 80-100
Score Factors
In addition to the overall numerical Seekr Score, the API provides the individual Score Factors that went into the overall Seekr Score to provide more insights to the user.
| Syntax | Description |
|---|---|
| Byline | A byline names the author(s) of an article. The AI looks for the absence of a byline. |
| Clickbait | The AI looks for sensational promises. “You won’t believe...” is typically followed by content that under-delivers. Clickbait appeals to curiosity and teases the reader with inaccurate and sometimes inappropriate articles. |
| Personal Attack | The AI looks for Ad Hominem arguments, which show language that attacks the character, motive, or other characteristics of a person rather than their actual argument. |
| Subjectivity | The AI looks for thoughts, beliefs, or attitudes that go beyond just reporting facts. Words that contain sentiment (“outstanding”), that cannot be measured (“quickly”) or comparative words (“smarter”) are a few examples. |
| Title Exaggeration | Seekr AI looks for headlines that portray something as more important than it is or hyperbolizes a claim. |
Seekr Score Filtering
The Seekr API allows requests for various APIs to be filtered and only return results within a certain score range, or within a specific level of reliability.