Method of and system for fact checking flagged comments

• US 9,092,521 B2
• Filed: 07/19/2013
• Issued: 07/28/2015
• Est. Priority Date: 06/10/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: LinkedIn Corporation (Microsoft Corporation)
• Inventors: Myslinski, Lucas J.
• Primary Examiner(s): Airapetian, Mila
• Application Number:
  US13/946,209
• Publication Number:
  US 20130311388A1
• Time in Patent Office: 739 Days
• Field of Search: 705/26.1
• US Class Current: 1/1
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/7837 using objects detected or recognised in the video content
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/018 Certifying business or products
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
• CPC Class Codes: H04L 51/063 Content adaptation, e.g. replacement of unsuitable content
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04N 21/258 Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data arrangements for services using the result on the distributing side of broadcast systems H04H60/66; profiles in network data switching protocols H04L67/30

Abstract

A fact checking system verifies the correctness of information and/or characterizes the information by comparing the information with one or more sources. The fact checking system automatically monitors, processes, fact checks information and indicates a status of the information.

Claims

1. A method programmed in a non-transitory memory of a device comprising:

a. receiving flags by users for flagging a comment within broadcast information; and

b. automatically fact checking the flagged comment within the broadcast information to determine a factual accuracy of the flagged comment by comparing the flagged comment within the broadcast information with source information to generate a result.

2. The method of claim 1 further comprising automatically indicating a status of the flagged comment based on the result of a comparison of the flagged comment with the source information.

3. The method of claim 1 wherein the flags for the comment are at least one of:

true, false, questionable, unverifiable, depending on context, spin, comedy, sarcasm, hyperbole, and hypocritical.

4. The method of claim 1 wherein each user of the users has a flagging rating.

5. The method of claim 4 wherein the flagging rating of each user is determined by comparing flagging by each user with results of corresponding fact checks.

6. The method of claim 5 wherein the flagging rating of a user increases if the user correctly flags comments, and the flagging rating decreases if the user incorrectly flags the comments.

7. The method of claim 6 wherein a flag by the user is not used if the flagging rating of the user is below a flagging threshold.

8. The method of claim 4 wherein if a user has a high flagging rating, a flag by the user is given additional weight.

9. The method of claim 4 wherein a weighting scheme is used so that a weight of a flag of each user is proportional to a correctness of previous flags by each user.

10. The method of claim 1 wherein the users are separated into classes of users, further wherein the classes include:

media, professional, and viewer.

11. The method of claim 1 wherein the flags include selections between thumbs up or thumbs down.

12. The method of claim 1 wherein the flags include a scale from 1 to 10, further wherein 1 is blatantly false and 10 is definitely true.

13. The method of claim 1 wherein a user of the users includes a citation supporting a position of the user for a flag.

14. The method of claim 1 further comprising implementing a competition using flagging wherein the users are asked to assess validity of comments, and a user who is most often correct wins the competition.

15. The method of claim 1 wherein the users flag the comment by voice, body-motion capture, or touchless 3D input.

16. The method of claim 1 wherein fact checking utilizes a plurality of sources, and each source of the plurality of sources has a reliability rating based on an accuracy of information within each source of the plurality of sources, wherein the accuracy is determined based on previous fact checking results, wherein a first source with a first reliability rating is given more weight during fact checking than a second source with a second reliability rating lower than the first reliability rating, wherein each source of the plurality of sources with a reliability rating that is below a threshold is not used in fact checking.

17. The method of claim 1 wherein the result is displayed automatically at an appropriate time during a later telecast.

18. The method of claim 17 wherein each time a user flags information, a timestamp is made which is then used to display corrective comments.

19. A method programmed in a non-transitory memory of a device comprising:

a. receiving a flag for a comment by a user, wherein the user has a flagging rating;

b. automatically fact checking the comment to determine a factual accuracy of the comment by comparing the comment with source information to generate a result; and

c. automatically indicating a status of the comment based on the result of a comparison of the comment with the source information.

20. A device comprising:

a. a memory for storing an application for performing the following steps;

i. receiving a flag for a comment within broadcast information by a user, wherein the user has a flagging rating, further wherein the flagged comment is highlighted;

ii. automatically fact checking the comment within the broadcast information to determine a factual accuracy of the comment by comparing the comment within the broadcast information with source information to generate a result; and

iii. automatically indicating a status of the comment based on the result of a comparison of the comment within the broadcast information with the source information, wherein group video viewing is implemented, and users in a group flag comments to be fact checked and provide user comments, wherein each user is able to flag the user comments, further wherein the user comments are automatically fact checked; and

b. a processor for processing the application.