Systems and methods for determining credibility at scale

Abstract

An example system may include instructions to control processor(s) to receive text from content of a first web page, determine, based on the content, a first title topic indicator, a first sentiment indicator, and a first text subjectivity indicator, apply the first title topic indicator, the first sentiment indicator, and the first text subjectivity indicator to a credibility machine learning model to generate a first content credibility score and a first content bias score for the text of the first web page, the credibility machine learning model being trained on text from other web pages using known title topic indicators, known sentiment indicators, and known text subjectivity indicators, and known credibility scores and bias scores, generate a first graphical representation for the first content credibility score and the first bias credibility score, and provide the graphical representation to a first digital device.

1 . A computing system comprising:
 one or more processors; and   memory storing instructions that, when executed by the one or more processors, cause the computing system to:
 receive a request from a first digital device, the request including a first web page identifier that identifies a first web page; 
 if the system has not previously stored a third content credibility score associated with the first web page; then:
 receive text from content of the first web page at a first website; 
 determine a first title topic indicator based on the content of the first web page, the first title topic indicator indicating a relationship between words in a title within the content of the first web page and text of a body in the content of the first web page; 
 determine a first sentiment indicator based on the content of the first web page, the first sentiment indicator indicating a degree of sentiment of the body of the content of the first web page; 
 determine first text subjectivity indicator based on the content of the first web page, the first text subjectivity indicator indicating subjectivity by comparing words and phrases from the content of the first web page to a database of known words and known phrases including known sentiment measures, the first text subjectivity indicator being based on the known sentiment measures; 
 apply the first title topic indicator, the first sentiment indicator, and the first text subjectivity indicator to a credibility machine learning model to generate a first content credibility score; and 
 store the first credibility score associated with the first web page; 
 
 if the system has previously stored a third content credibility score associated with the third web page, then provide the credibility score to the first digital device; 
 receive a request from a second digital device, the request including the first web page identifier that identifies the first web page; and 
 provide the first credibility score associated with the first web page to the second digital device.