US 11,934,437 B2
Stance detection and summarization for data sources
John Bohannon, San Francisco, CA (US); Leonard Apeltsin, Berkeley, CA (US); Raine Morgan Hoover, San Francisco, CA (US); and Wei Gong, San Francisco, CA (US)
Assigned to Primer Technologies, Inc., San Francisco, CA (US)
Filed by Primer Technologies, Inc., San Francisco, CA (US)
Filed on May 24, 2019, as Appl. No. 16/422,554.
Claims priority of provisional application 62/693,294, filed on Jul. 2, 2018.
Prior Publication US 2020/0004770 A1, Jan. 2, 2020
Int. Cl. G06F 16/34 (2019.01); G06F 3/0482 (2013.01); G06F 9/54 (2006.01); G06F 16/31 (2019.01); G06F 16/953 (2019.01)
CPC G06F 16/345 (2019.01) [G06F 3/0482 (2013.01); G06F 9/542 (2013.01); G06F 16/313 (2019.01); G06F 16/328 (2019.01); G06F 16/953 (2019.01)] 12 Claims
OG exemplary drawing
 
1. A method of providing stance detection summaries for events, the method comprising:
identifying, in a stance detection computing system, data objects related to an event from a plurality of data sources based on content in the data objects, wherein the plurality of data sources comprises a plurality of websites, and wherein two or more of the data objects are received from a data source of the plurality of data sources;
identifying a data source from the plurality of data sources for each of the data objects;
for each data object of the data objects, processing the data object to identify pertinent data related to a stance of a plurality of stances for the data source associated with the data object in relation to the event, wherein the pertinent data the data object comprises at least a phrase, a word, or an organization of data in the data object indicative of the stance for the data source;
determining the stance from the plurality of stances for each of the plurality of data sources based on the pertinent data identified in a subset of the data objects from the data source, wherein the stance comprises a score;
generating, for display, a summary based on the stances of the plurality of sources, wherein the summary indicates at least the score associated with each of the plurality of data sources in relation to the event, and wherein the summary displays each of the scores relative to one another for the plurality of data sources;
processing one or more additional data objects that correspond to secondary events to identify additional pertinent data related to a stance for a first data source of the plurality of data sources;
identifying variations in stance over time for the first data source based on the pertinent data identified in the data objects and the additional pertinent data identified in the one or more additional data objects; and
generating, for display, a second summary based on the variations in stance over time.