SELECTIVE FACT CHECKING METHOD AND SYSTEM

• US 20130198196A1
• Filed: 02/11/2013
• Published: 08/01/2013
• 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.
• Granted Patent: US 9,176,957 B2
• Time in Patent Office: Days
• US Class Current: 707/740
• CPC Class Codes: G06F 16/43 Querying
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A fact checking system is able to verify the correctness of information and/or characterize 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. The fact checking system is able to operate selectively, for example, only fact checking information after detecting a trigger.

Claims

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

a. automatically monitoring broadcast information;

b. automatically detecting a trigger within the broadcast information;

c. automatically fact checking the broadcast information related to the trigger by comparing the broadcast information related to the trigger with source information; and

d. automatically indicating a status of the broadcast information based on a result of the comparison of the broadcast information related to the trigger with the source information in real-time.

2. The method of claim 1 wherein the trigger comprises a keyword.

3. The method of claim 1 wherein the trigger comprises an event, a network, a channel, a show, a commentator, a guest, a topic, a characterization, a recent news story, a popular item, a recent purchase by a user, a recent search by the user, social network information, a controversy, and/or a controversial comment.

4. The method of claim 1 wherein the trigger comprises an entity with a validity rating below a threshold.

5. The method of claim 1 wherein the trigger comprises an item related to a user'"'"'s importance rating, wherein the user'"'"'s importance rating is determined by:

i. analyzing the broadcast information;

ii. classifying the broadcast information into a classification;

iii. comparing the classification with an importance selection; and

iv. generating the importance rating based on the comparison of the classification and the importance selection.

6. The method of claim 1 wherein the trigger comprises a user-specified trigger.

7. The method of claim 6 wherein the user-specified trigger comprises information flagged by a user.

8. The method of claim 1 wherein the trigger is stored in a database.

9. The method of claim 1 wherein the broadcast information related to the trigger includes a phrase the trigger is contained in.

10. The method of claim 1 wherein the broadcast information related to the trigger includes several seconds of the broadcast information before and after the trigger is detected.

11. The method of claim 1 wherein the broadcast information related to the trigger includes temporally or spatially proximate information.

12. The method of claim 1 wherein the broadcast information is fact checked only if a number of triggers detected exceeds a threshold.

13. The method of claim 1 further comprising automatically computing a quantity of inaccuracies of the broadcast information based on the fact checking, and if the quantity of inaccuracies equals or is below a first quantity threshold, the status is indicated in a first manner, and if the quantity of inaccuracies exceeds the first quantity threshold, the status is indicated in a second manner.

14. The method of claim 13 wherein if the quantity of inaccuracies exceeds the first quantity threshold, a channel change suggestion is presented.

15. The method of claim 14 wherein the channel change suggestion comprises a channel that is more factually accurate than the broadcast information.

16. The method of claim 1 further comprising automatically computing a quantity of inaccuracies of the broadcast information based on the fact checking, and wherein a plurality of quantity thresholds are implemented, and after each threshold is exceeded, an effect applied to the status of the broadcast information is modified.

17. The method of claim 16 wherein a severity of the effect increases as a number of quantity thresholds exceeded increases, including changing a message and a presentation of the message.

18. The method of claim 16 wherein the quantity of inaccuracies is based on a per show basis, a per day basis, a per week basis, a per month basis, a per year basis, or starting from 0 and not resetting.

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

a. automatically monitoring broadcast information;

b. automatically detecting, with the device, a keyword within the broadcast information; and

c. automatically indicating in real-time a fact checking result based on a comparison of the broadcast information related to the keyword with the source information.

20. A device comprising:

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

i. monitoring broadcast information;

ii. detecting a keyword within the broadcast information;

iii. fact checking the broadcast information related to the keyword by comparing the broadcast information related to the keyword with source information; and

iv. indicating a status of the broadcast information based on a result of the comparison of the broadcast information with the source information in real-time; and

b. a processor for processing the application.