IP Library Granted Patent US 11,521,098
Granted Patent B2
US 11,521,098 · App. 16/367,734 · Granted Dec 6, 2022

Modeling controversy within populations

Inventors: Myungha Jang (Amherst, MA); Shiri Dori-Hacohen (Granby, MA); James Allan (Amherst, MA)
Assignee: University of Massachusetts
G06N7/00G06F17/18G06Q30/0201H04L51/52
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,521,098
App. No.
16/367,734
Granted
Dec 6, 2022
Kind
B2
Abstract

Disclosed herein are systems and methods for modeling controversy as a combination of at least contention and importance with respect to a given population. An example system for modeling controversy within a population includes an interface, memory, and processor. The interface is configured to obtain information regarding stances of individuals in the population on a topic. The processor is configured to determine, and store in the memory, a representation of contention on the topic among individuals of the population. The representation of contention is based on the stances of individuals in the population. The processor is further configured to determine, and store in the memory, a representation of importance of the topic within the population. The processor is configured to create, and store in the memory, a model of controversy for the topic based on the representations of contention and importance.

Claims (32)

1. A system for modeling controversy within a population, the system comprising:

an interface configured to obtain information regarding stances of individuals in the population on a topic;

memory; and

a processor configured to:

determine and store in the memory a representation of contention on the topic among individuals of the population, the representation of contention being determined based on (i) the stances of individuals in the population and (ii) a measure of exclusivity between the stances, wherein the representation of contention quantifies a proportion of individuals in the population, from amongst a total number of individuals in the population, in disagreement regarding the topic;

determine and store in the memory a representation of importance of the topic within the population, the representation of importance indicating a number of individuals in the population affected by the topic; and

create and store in the memory a model of controversy for the topic based on the representation of contention on the topic and the representation of importance of the topic.

2. A system as in claim 1 wherein the processor is further configured to predict whether the topic is controversial based on the model of controversy.

3. A system as in claim 1 wherein the processor is further configured to determine a controversy score for the topic based on the model of controversy.

4. A system as in claim 1 wherein the processor is further configured to determine contention on the topic by determining the proportion of individuals in the population, from amongst the total number of individuals in the population, that are in disagreement regarding the topic.

5. A system as in claim 1 wherein the processor is further configured to determine pairs of stances that are mutually exclusive stances.

6. A system as in claim 1 wherein the processor is further configured to determine contention on the topic by determining a probability that two given individuals have conflicting stances on the topic.

7. A system as in claim 1 wherein the processor is further configured to determine importance of the topic by determining a probability that the topic is important to a given individual in the population.

8. A method of modeling controversy within a population, the method comprising:

determining contention on a topic among individuals of the population based on (i) stances of individuals in the population and (ii) a measure of exclusivity between the stances, the determined contention quantifying a proportion of individuals in the population, from amongst a total number of individuals in the population, in disagreement regarding the topic;

determining importance of the topic within the population, the determined importance indicating a number of individuals in the population affected by the topic; and

creating a model of controversy for the topic based on the contention on the topic and the importance of the topic.

9. A method as in claim 8 further comprising predicting whether the topic is controversial based on the model of controversy.

10. A method as in claim 8 further comprising determining a controversy score for the topic based on the model of controversy.

11. A method as in claim 8 wherein determining contention on the topic includes determining the proportion of individuals in the population, from amongst the total number of individuals in the population, that are in disagreement regarding the topic.

12. A method as in claim 8 wherein determining contention on the topic includes determining the stances that the individuals in the population have on the topic.

13. A method as in claim 12 wherein determining contention on the topic includes determining a probability that two given individuals have conflicting stances on the topic.

14. A method as in claim 8 wherein determining importance of the topic includes determining a probability that the topic is important to a given individual in the population.

15. A non-transitory machine-readable storage medium having stored thereon a computer program for modeling controversy within a population, the computer program comprising a routine of set instructions for causing the machine to:

determine contention on a topic among individuals of the population based on (i) stances of individuals in the population and (ii) a measure of exclusivity between the stances, the determined contention quantifying a proportion of individuals in the population, from amongst a total number of individuals in the population, in disagreement regarding the topic;

determine importance of the topic within the population, the determined importance indicating a number of individuals in the population affected by the topic; and

create a model of controversy for the topic based on the contention on the topic and the importance of the topic.

16. A machine-readable storage medium as in claim 15 further comprising instructions for causing the machine to predict whether the topic is controversial based on the model of controversy.

17. A machine-readable storage medium as in claim 15 further comprising instructions for causing the machine to determine a controversy score for the topic based on the model of controversy.

18. A machine-readable storage medium as in claim 15 further comprising instructions for causing the machine to determine contention on the topic by determining the proportion of individuals in the population, from amongst the total number of individuals in the population, in disagreement regarding the topic.

19. A machine-readable storage medium as in claim 15 further comprising instructions for causing the machine to determine contention on the topic by determining the stances that the individuals in the population have on the topic.

20. A machine-readable storage medium as in claim 19 further comprising instructions for causing the machine to determine contention on the topic by determining a probability that two given individuals have conflicting stances on the topic.

Assignments (2)
CONFIRMATORY LICENSE Recorded Sep 25, 2019
From: UNIVERSITY OF MASSACHUSETTS, AMHERST
To: NATIONAL SCIENCE FOUNDATION
Reel/Frame 050483/0089 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 13, 2019
From: JANG, MYUNGHA; DORI-HACOHEN, SHIRI; ALLAN, JAMES
To: UNIVERSITY OF MASSACHUSETTS
Reel/Frame 050036/0558 →
Continuity (2)
Provisional Application 62649423 · Mar 28, 2018
Related Publication 20190303784A1 · Oct 3, 2019