DETECTING CONTROVERSIAL EVENTS

• US 20120136985A1
• Filed: 11/29/2010
• Published: 05/31/2012
• Est. Priority Date: 11/29/2010
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Popescu, Ana-Maria, Pennacchiotti, Marco
• Granted Patent: US 9,105,008 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A method, device, and computer-readable storage medium storing instructions are provided for detecting controversial events that are reflected in user-generated content items. In a single-step approach, user-generated content items are received and analyzed by a controversial event detection module, which determines the likelihood that sets of content items reflect controversial events. In one example, public posts by users of a social networking service are grouped into snapshots of posts that are associated with an entity and were generated during a window of time. An event detection module may determine the likelihood that snapshots reflect events. In a two-step approach, event snapshots are provided to a controversy detection module, which determines the likelihood that event snapshots are controversial. In a blended approach, snapshots are provided to a controversy detection module, which determines the likelihood that snapshots are controversial events based in part on the event score.

Claims

1. A method comprising:

receiving a plurality of items of user-generated content;

based at least in part on the user-generated content of two or more items in the plurality of items, determining that a set of items including the two or more items reflects a controversial event related to an entity of a plurality of entities, wherein at least one other set of items of the plurality of items refers to another entity of the plurality of entities;

wherein the method is performed by one or more special-purpose computing devices.

2. The method of claim 1, wherein the plurality of items of user-generated content include public posts by users of a social networking service, and wherein the entity is referenced using one or more terms in the set of items.

3. The method of claim 1, wherein the set of items comprises items that refer to the entity and were generated during a window of time, further comprising determining a number of references to the entity in the set, and wherein determining that the set reflects the controversial event is based at least in part on the number of references to the entity in the set and an expected number of references to the entity in the set, wherein the expected number of references to the entity accounts for sets of items that refer to the entity and were generated during other windows of time.

4. The method of claim 1, wherein the set of items comprises items that refer to the entity and were generated during a window of time, further comprising:

determining a number of references to the entity by other content sources during the window of time;

wherein determining that the set reflects the controversial event is further based at least in part on the number of references to the entity by other content sources during the window of time and an expected number of references to the entity by the other content sources during the window of time;

wherein the expected number of references accounts for references to the entity by the other content sources during other windows of time;

wherein the plurality of items of user-generated content include posts that are less than 160 characters in length by users of a social networking service, and wherein the references to the entity by other content sources during the window of time and during the other windows of time include references in articles that are more than 160 characters in length from a reporting service that reports a plurality of articles.

5. The method of claim 1, further comprising:

determining that one or more items in the set of items also refer to one or more other entities;

determining a controversy score for the one or more other entities; and

wherein determining that the set reflects the controversial event is based at least in part on the controversy score for the one or more other entities.

6. The method of claim 1, further comprising determining a number of items that include controversial terms in the set, and wherein determining that the set reflects the controversial event is further based at least in part on the number of controversial terms in the set.

7. The method of claim 1, further comprising determining a first number of items in the set that have a positive sentiment and a second number of items in the set that have a negative sentiment, and wherein determining that the set of items reflects the controversial event is further based at least in part on the first number of items in the set that have a positive sentiment and the second number of items in the set that have a negative sentiment.

8. The method of claim 1, further comprising determining a number of items that contain at least one question in the set, and wherein determining that the set of items reflects the controversial event is further based at least in part on the number of items that contain at least one question in the set.

9. The method of claim 1, further comprising determining a number of unique marked tags in the set, and wherein determining that the set of items reflects the controversial event is further based at least in part on the number of unique marked tags in the set.

10. The method of claim 1, further comprising determining a number of items in the set that contain a verb for which the entity is a subject or an object, and wherein determining that the set of items reflects the controversial event is further based at least in part on the number of items in the set that contain a verb for which the entity is a subject or an object.

11. One or more non-transitory storage media storing instructions which, when executed by one or more computing devices, cause performance of:

receiving a plurality of items of user-generated content;

based at least in part on the user-generated content of two or more items in the plurality of items, determining that a set of items including the two or more items reflects a controversial event related to an entity of a plurality of entities, wherein at least one other set of items of the plurality of items refers to another entity of the plurality of entities;

wherein the method is performed by one or more special-purpose computing devices.

12. One or more non-transitory storage media as recited in claim 11, wherein the plurality of items of user-generated content include public posts by users of a social networking service, and wherein the entity is referenced using one or more terms in the set of items.

13. One or more non-transitory storage media as recited in claim 11, wherein the set of items comprises items that refer to the entity and were generated during a window of time, wherein the instructions, when executed by the one or more computing devices, further cause performance of:

determining a number of references to the entity in the set;

wherein determining that the set reflects the controversial event is based at least in part on the number of references to the entity in the set and an expected number of references to the entity in the set;

wherein the expected number of references to the entity accounts for sets of items that refer to the entity and were generated during other windows of time.

14. One or more non-transitory storage media as recited in claim 11, wherein the set of items comprises items that refer to the entity and were generated during a window of time, wherein the instructions, when executed by the one or more computing devices, further cause performance of:

determining a number of references to the entity by other content sources during the window of time;

wherein determining that the set reflects the controversial event is further based at least in part on the number of references to the entity by other content sources during the window of time and an expected number of references to the entity by the other content sources during the window of time;

wherein the expected number of references accounts for references to the entity by the other content sources during other windows of time;

wherein the plurality of items of user-generated content include posts that are less than 160 characters in length by users of a social networking service, and wherein the references to the entity by other content sources during the window of time and during the other windows of time include references in articles that are more than 160 characters in length from a reporting service that reports a plurality of articles.

15. One or more non-transitory storage media as recited in claim 11, wherein the instructions, when executed by the one or more computing devices, further cause performance of:

determining that one or more items in the set of items also refer to one or more other entities;

determining a controversy score for the one or more other entities; and

wherein determining that the set reflects the controversial event is based at least in part on the controversy score for the one or more other entities.

16. One or more non-transitory storage media as recited in claim 11, wherein the instructions, when executed by the one or more computing devices, further cause performance of:

determining a number of items that include controversial terms in the set, and wherein determining that the set reflects the controversial event is further based at least in part on the number of controversial terms in the set.

17. One or more non-transitory storage media as recited in claim 11, wherein the instructions, when executed by the one or more computing devices, further cause performance of:

determining a first number of items in the set that have a positive sentiment and a second number of items in the set that have a negative sentiment, and wherein determining that the set of items reflects the controversial event is further based at least in part on the first number of items in the set that have a positive sentiment and the second number of items in the set that have a negative sentiment.

18. One or more non-transitory storage media as recited in claim 11, wherein the instructions, when executed by the one or more computing devices, further cause performance of:

determining a number of items that contain at least one question in the set, and wherein determining that the set of items reflects the controversial event is further based at least in part on the number of items that contain at least one question in the set.

19. One or more non-transitory storage media as recited in claim 11, wherein the instructions, when executed by the one or more computing devices, further cause performance of:

determining a number of unique marked tags in the set, and wherein determining that the set of items reflects the controversial event is further based at least in part on the number of unique marked tags in the set.

20. One or more non-transitory storage media as recited in claim 11, wherein the instructions, when executed by the one or more computing devices, further cause performance of:

determining a number of items in the set that contain a verb for which the entity is a subject or an object, and wherein determining that the set of items reflects the controversial event is further based at least in part on the number of items in the set that contain a verb for which the entity is a subject or an object.