Fact checking method and system

• US 8,185,448 B1
• Filed: 11/02/2011
• Issued: 05/22/2012
• Est. Priority Date: 06/10/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Lucas Myslinski
• Inventors: Myslinski, Lucas J.
• Primary Examiner(s): Airapetian, Mila
• Application Number:
  US13/287,804
• Time in Patent Office: 202 Days
• Field of Search: 705/26.1
• US Class Current: 705/26.1
• 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 memory in a device comprising:

a. automatically monitoring broadcast information;

b. automatically processing the broadcast information including converting the broadcast information into searchable information and parsing the searchable information into fact checkable portions;

c. automatically fact checking the fact checkable portions by comparing the fact checkable portions with source information; and

d. automatically indicating a status of the broadcast information in real-time based on a result of the comparison of the fact checkable portions with the source information.

2. The method of claim 1 wherein real-time is at most 1 second.

3. The method of claim 1 further comprising formatting the fact checkable portion for fact checking.

4. The method of claim 1 wherein the source information comprises a plurality of sources, and a source of the plurality of sources is not used if a reliability rating of the source is below a threshold.

5. The method of claim 1 wherein the broadcast information comprises a commercial, and the commercial is fact checked.

6. The method of claim 4 wherein each source of the plurality of sources is rated by an independent rating agency.

7. The method of claim 4 wherein each source of the plurality of sources is rated based on previous fact checking results.

8. The method of claim 1 wherein the result includes a result accuracy rating indicating how accurate the result is.

9. The method of claim 1 wherein the broadcast information comprises a subjective statement, and ratings, objective information and subjective information are used to determine the accuracy of the subjective statement.

10. The method of claim 1 wherein context determination is used in fact checking.

11. The method of claim 1 further comprising displaying an advertisement while indicating the status.

12. The method of claim 1 wherein the broadcast information comprises an entity making a statement, and the entity has a validity rating comprising statistical information related to factually inaccurate comments made by the entity.

13. The method of claim 12 wherein at least one of people, facial, voice or biometric recognition is implemented to identify the entity.

14. The method of claim 1 further comprising receiving flagged information from a user, wherein the flagged information is fact checked.

15. The method of claim 1 wherein indicating the status comprises sending the status to a television from the device.

16. The method of claim 1 wherein the device is a mobile device.

17. The method of claim 1 wherein the source information comprises a plurality of sources and each source is classified in a political classification, and further wherein fact checking comprises determining bias.

18. The method of claim 1 wherein the device is a broadcaster'"'"'s device.

19. A method of automatically fact checking a discussion involving a host and a guest providing political commentary, the method programmed in a memory of a device, the method comprising:

a. monitoring the discussion;

b. processing the discussion including converting the discussion into searchable information and parsing the searchable information into fact checkable portions;

c. fact checking with the device the fact checkable portions by comparing the fact checkable portions with source information; and

d. indicating a status of discussion portions in real-time based on a result of the comparison of the fact checkable portions with the source information, including prompting the host with a follow-up question to ask the guest, if the guest provides questionable information.

20. A device comprising:

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

i. monitoring television broadcast information and determining if the television broadcast information is fact checkable;

ii. converting the television broadcast information into parsable text information;

iii. parsing out a fact checkable portion from the parsable text information;

iv. fact checking the fact checkable portion by comparing the fact checkable portion with source information from a plurality of web page sources to determine validity of the fact checkable portion, wherein each web page source of the plurality of web page sources has a reliability rating; and

v. indicating a status of the television broadcast information in real-time based on a result of the comparison of the fact checkable portion with the source information, wherein indicating the status of the television broadcast information includes displaying the fact checkable portion in a first color when the result is true and a second color when the result is false; and

b. a processor for processing the application.