IP Library › Granted Patent US 10,698,942
Granted Patent B2
US 10,698,942 · App. 16/259,709 · Granted Jun 30, 2020

Sentiment-based classification of media content

Inventor: Stacey Kuznetsov (Pittsburgh, PA)
Assignee: Google LLC
G06F16/435G06F16/248G06F16/24578G06F16/313G06F16/438G06F16/48
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 10,698,942
App. No.
16/259,709
Granted
Jun 30, 2020
Kind
B2
Abstract

A set of comments associated with an item of media content is identified. A set of sentiment scores associated with the set of comments is generated, wherein each sentiment score indicates a type of sentiment expressed in a comment. The sentiment profile is generated responsive at least in part to the set of sentiment scores, the sentiment profile indicating the types of sentiment expressed in comments associated with the item of media content and stored in association with the item of media content.

Claims (53)

1. A computer-implemented method for presenting sentiment information, the method comprising:

causing, using a hardware processor, a media content item to be presented;

retrieving, using the hardware processor, individual sentiment scores associated with portions of the media content item;

determining, using the hardware processor, an aggregate score for a portion of the media content item based on the individual sentiment scores associated with that portion of the media content item; and

in response to presenting the portion of the media content item, presenting, using the hardware processor, a sentiment plot representation that indicates a type of sentiment being expressed based on the aggregate score of the portion of the media content item on a temporal axis of the media content item, wherein the sentiment plot representation is a line plot corresponding to a single sentiment.

2. The method of claim 1 , further comprising:

identifying comments associated with a first portion of the media content item; and

generating, for each of the plurality of comments, a sentiment score indicating a likelihood that the comment expresses the type of sentiment, wherein the aggregate score is determined for the first portion of the media content item based on the sentiment score for the comments.

3. The method of claim 2 , wherein the sentiment plot representation is presented along with at least a portion of the comments associated with a corresponding portion of the media content item being presented.

4. The method of claim 2 , wherein the sentiment plot representation is presented along with one or more related media content items associated with the type of sentiment being expressed in the media content item.

5. The method of claim 2 , further comprising:

identifying a second plurality of comments associated with a second portion of the media content item; and

generating the sentiment score for each of the second plurality of comments and determining the aggregate score for the second portion of the media content item based on the sentiment score for the second plurality of comments.

6. The method of claim 5 , further comprising modifying the sentiment plot representation to indicate the type of sentiment being expressed based on the aggregate score of the first portion of the media content item and the aggregate score of the second portion of the media content item, wherein the at least a portion of the comments is modified based on the corresponding portion of the media content item being presented and wherein the one or more related media content items is modified based on the type of sentiment being expressed in the media content item.

7. The method of claim 1 , wherein the sentiment plot representation indicates whether a first sentiment is being expressed or a second sentiment based on the aggregate score is being expressed over the temporal axis of the media content item.

8. The method of claim 1 , further comprising:

receiving a request for media content;

in response to receiving the request for media content, selecting a second media content item based on the aggregate score indicating that comments associated with the media content item express the type of sentiment; and

responsive to selecting the second media content item, presenting an identifier associated with the second media content item concurrently with the sentiment plot representation.

9. The method of claim 1 , further comprising:

receiving a search query for media content associated with the type of sentiment; and

determining that the media content item is to be included in search results for the search query based on the aggregate score indicating that comments associated with the media content item express the type of sentiment.

10. The method of claim 1 , wherein the aggregate score indicates a magnitude of the type of sentiment expressed in the portion of the media content item and wherein the aggregate score is an average of the individual sentiment scores associated with the portion of the media content item.

11. A computer-implemented system for presenting sentiment information, the system comprising:

a memory; and

a hardware processor that, when executing computer-executable instructions stored in the memory, is configured to:

cause a media content item to be presented;

retrieve individual sentiment scores associated with portions of the media content item;

determine an aggregate score for a portion of the media content item based on the individual sentiment scores associated with that portion of the media content item; and

in response to presenting the portion of the media content item, present a sentiment plot representation that indicates a type of sentiment being expressed based on the aggregate score of the portion of the media content item on a temporal axis of the media content item, wherein the sentiment plot representation is a line plot corresponding to a single sentiment.

12. The system of claim 11 , wherein the hardware processor is further configured to:

identify comments associated with a first portion of the media content item; and

generate, for each of the plurality of comments, a sentiment score indicating a likelihood that the comment expresses the type of sentiment, wherein the aggregate score is determined for the first portion of the media content item based on the sentiment score for the comments.

13. The system of claim 12 , wherein the sentiment plot representation is presented along with at least a portion of the comments associated with a corresponding portion of the media content item being presented.

14. The system of claim 12 , wherein the sentiment plot representation is presented along with one or more related media content items associated with the type of sentiment being expressed in the media content item.

15. The system of claim 12 , wherein the hardware processor is further configured to:

identify a second plurality of comments associated with a second portion of the media content item; and

generate the sentiment score for each of the second plurality of comments and determining the aggregate score for the second portion of the media content item based on the sentiment score for the second plurality of comments.

16. The system of claim 15 , wherein the hardware processor is further configured to modify the sentiment plot representation to indicate the type of sentiment being expressed based on the aggregate score of the first portion of the media content item and the aggregate score of the second portion of the media content item, wherein the at least a portion of the comments is modified based on the corresponding portion of the media content item being presented and wherein the one or more related media content items is modified based on the type of sentiment being expressed in the media content item.

17. The system of claim 11 , wherein the sentiment plot representation indicates whether a first sentiment is being expressed or a second sentiment based on the aggregate score is being expressed over the temporal axis of the media content item.

18. The system of claim 11 , wherein the hardware processor is further configured to:

receive a request for media content;

in response to receiving the request for media content, select a second media content item based on the aggregate score indicating that comments associated with the media content item express the type of sentiment; and

responsive to selecting the second media content item, present an identifier associated with the second media content item concurrently with the sentiment plot representation.

19. The system of claim 11 , wherein the hardware processor is further configured to:

receive a search query for media content associated with the type of sentiment; and

determine that the media content item is to be included in search results for the search query based on the aggregate score indicating that comments associated with the media content item express the type of sentiment.

20. The system of claim 11 , wherein the aggregate score indicates a magnitude of the type of sentiment expressed in the portion of the media content item and wherein the aggregate score is an average of the individual sentiment scores associated with the portion of the media content item.

21. A non-transitory computer-readable medium containing computer-executable instructions that, when executed by a processor, cause the processor to perform a method for presenting sentiment information, the method comprising:

causing a media content item to be presented;

retrieving individual sentiment scores associated with portions of the media content item;

determining an aggregate score for a portion of the media content item based on the individual sentiment scores associated with that portion of the media content item; and

in response to presenting the portion of the media content item, presenting a sentiment plot representation that indicates a type of sentiment being expressed based on the aggregate score of the portion of the media content item on a temporal axis of the media content item, wherein the sentiment plot representation is a line plot corresponding to a single sentiment.

Continuity (5)
Continuation 15851159 · Dec 21, 2017
Continuation 15287635 · Oct 6, 2016
Continuation 14827181 · Aug 14, 2015
Division 12268324 · Nov 10, 2008
Related Publication 20190155832A1 · May 23, 2019
Cited By (1)
US 12,363,376