US 12,135,948 B2
Generating bias scores from articles
Daniel Carter, Salt Lake City, UT (US); Haochuan Wei, Jiangsu (CN); Arjun Karangiya, Gujarat (IN); and William Lucia, Cassano M. (IT)
Assigned to Biasly, LLC, Sandy, UT (US)
Filed by Biasly, LLC, Sandy, UT (US)
Filed on Dec. 30, 2021, as Appl. No. 17/565,844.
Prior Publication US 2023/0214603 A1, Jul. 6, 2023
Int. Cl. G06F 40/40 (2020.01); G06F 16/35 (2019.01); G06F 40/205 (2020.01)
CPC G06F 40/40 (2020.01) [G06F 16/35 (2019.01); G06F 40/205 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating bias scores from articles comprising:
processing an article to identify each instance of one or more entities and each instance of one or more policies that appear in the article;
for each instance of the one or more entities and each instance of the one or more policies that appear in the article, generating a sentiment value from a portion of the article in which the respective instance appears;
for each of the one or more entities and the one or more policies, generating a sentiment score by combining the sentiment value for each instance of the respective entity or policy;
for each of the one or more entities, adjusting the sentiment score of the respective entity based on a political party of the respective entity;
for each of the one or more policies, adjusting the sentiment score of the respective policy based on a political stance for the respective policy; and
combining the sentiment scores for the one or more entities and the one or more policies to yield a bias score for the article.