US 12,306,890 B2
Machine-learned news aggregation and serving
Eva Cicinyte, Manhattan Beach, CA (US); Martin Richard Fisher, Maryland, DC (US); Katelyn Adele Therese Dudzik, Toronto (CA); and John Brien Dilts, Jr., Chagrin Falls, OH (US)
Assigned to Newton Principle Agency Corp., Washington, DC (US)
Filed by Newton Principle Agency Corp., Washington, DC (US)
Filed on Apr. 17, 2023, as Appl. No. 18/301,276.
Prior Publication US 2024/0346098 A1, Oct. 17, 2024
Int. Cl. G06F 16/00 (2019.01); G06F 16/951 (2019.01); G06F 16/9537 (2019.01); G06N 20/00 (2019.01); G06Q 50/00 (2012.01)
CPC G06F 16/9537 (2019.01) [G06F 16/951 (2019.01); G06N 20/00 (2019.01); G06Q 50/01 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method comprising:
retrieving, by a news aggregation system, a plurality of content items from each of a plurality of third-party data sources in each of a plurality of geographies;
querying, by the news aggregation system, a plurality of social networking platforms for user sentiment data associated with the retrieved content items;
processing, using a supervised machine-learned model, the retrieved content items to identify a plurality of keywords associated with the content items;
generating a plurality of clusters of information each associated with a topic by applying an unsupervised machine-learned model to the identified keywords;
generating, using the user sentiment data, a sentiment spectrum for each combination of a topic and a geography, the sentiment spectrum indicating respective portions of positive, neutral, and negative user reactions to retrieved content items associated with the topic and an overall sentiment label for the topic based on the respective portions;
generating a plurality of interfaces for display in a news aggregation application, the interfaces displaying:
for each geography, a ranking of trending topics within the geography based on clusters associated with the geography;
for each topic, a list of content items associated with the topic from the geography and other geographies; and
for each topic, the sentiment spectrum associated with the topic and geography, wherein a first spectrum associated with a first topic and a first geography is different than a second spectrum associated with the first topic and a second geography.