US 12,093,970 B2
Identifying and quantifying sentiment and promotion bias in social and content networks
Jelena Tesic, San Marcos, TX (US); and Lucas Rusnak, San Marcos, TX (US)
Assigned to Texas State University, San Marcos, TX (US)
Appl. No. 17/435,299
Filed by Texas State University, San Marcos, TX (US)
PCT Filed Apr. 19, 2019, PCT No. PCT/US2019/028317
§ 371(c)(1), (2) Date Aug. 31, 2021,
PCT Pub. No. WO2020/214187, PCT Pub. Date Oct. 22, 2020.
Prior Publication US 2022/0156767 A1, May 19, 2022
Int. Cl. G06Q 30/0202 (2023.01); G06N 7/01 (2023.01); G06Q 50/00 (2012.01)
CPC G06Q 30/0202 (2013.01) [G06N 7/01 (2023.01); G06Q 50/01 (2013.01)] 27 Claims
OG exemplary drawing
 
1. A method for detecting inequality in social networks, the method comprising:
receiving a set of nodes that correspond to users or evaluated content;
receiving a set of sentiments between said set of nodes as a measure of a group opinion, wherein said set of sentiments is expressed as a weight associated with an edge between two vertices in a graph;
generating a probability graph by constructing all possible balanced graphs associated with spanning trees corresponding to multiple views of a signed graph using said set of sentiments, wherein said signed graph is a graph in which each edge has a positive or a negative sign, wherein said spanning graph is a subgraph that is a tree that includes all the vertices of said signed graph with a minimum possible number of edges;
assigning scores for each of said multiple views of said signed graph to determine an influence one group has over another group while maintaining agreement;
obtaining an inequitable ratio of said assigned scores over agreeable sets of vertices of said signed graph; and
identifying and quantifying a sentiment bias based on said inequitable ratio of said associated scores over agreeable sets of vertices of said signed graph.