US 12,001,493 B2
Method and system for content bias detection
Dan Pelleg, Haifa (IL); Avihai Mejer, Atlit (IL); and Ali Tabaja, Haifa (IL)
Assigned to YAHOO ASSETS LLC, Dulles, VA (US)
Filed by YAHOO ASSETS LLC, New York, NY (US)
Filed on Feb. 6, 2023, as Appl. No. 18/164,855.
Application 18/164,855 is a continuation of application No. 16/426,138, filed on May 30, 2019, granted, now 11,574,024.
Prior Publication US 2023/0177092 A1, Jun. 8, 2023
Int. Cl. G06F 16/00 (2019.01); G06F 16/332 (2019.01); G06F 16/951 (2019.01); G06Q 30/0251 (2023.01); G06Q 30/0282 (2023.01)
CPC G06F 16/951 (2019.01) [G06F 16/332 (2019.01); G06Q 30/0256 (2013.01); G06Q 30/0282 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for providing bias information of source, the method comprising:
obtaining a plurality of content items;
identifying, based on publication information associated with each of the plurality of content items, multiple sources that published the content item;
determining multiple topics associated with each of the plurality of content items;
clustering the plurality of content items to generate a source-topic archive, wherein the source-topic archive includes:
a quantity of one or more of the plurality of content items published by each of the multiple sources on each of the multiple topics, and
a probability of each of the multiple sources publishing each of the multiple topics;
determining, by a computing topic based bias determiner, based on the quantities and the probabilities included in the source-topic archive, a topic coverage bias for each of the multiple sources; and
storing, by the computing topic based bias determiner, information of the topic coverage bias in a database for a search engine to access to label a query content item of the plurality of content items retrieved from one of the multiple sources in response to a search query from a user.