Sentiment based social media comment overlay on image posts

Patent metadata

Field	Value
Publication number	US-2018293468-A1
Application number	US-201816007990-A
Country	US
Kind code	A1
Filing date	Jun 13, 2018
Priority date	Aug 11, 2016
Publication date	Oct 11, 2018
Grant date	—

Abstract

By performing Natural Language Processing (NLP) on a comment to a social media post, an entity that is referenced in the comment is extracted. The entity is an object other than a human face that is depicted in an image in the post. The image is analyzed to determine whether the entity is represented in the image. When the entity is represented in the image, a sentiment value of the comment is computed relative to the entity. A value corresponding to the sentiment value is assigned to a characteristic of a graphical artifact. A position is determined relative to an area occupied by the entity in the image. The graphical artifact is caused to be overlaid on the image at the position and with the value of the characteristic.

First claim

What is claimed is:

1 . A method comprising:
extracting, using a processor and a memory to perform Natural Language Processing (NLP) on a comment to a social media post, an entity that is referenced in the comment, the entity being an object other than a human face that is depicted in an image in the post; computing a sentiment value of the comment relative to the entity; assigning, to a characteristic of a graphical artifact, a value corresponding to an overall sentiment value, the overall sentiment value comprising the sentiment value and a second sentiment value from a second comment; and causing the graphical artifact to be overlaid on the image at a position of the entity and with the value of the characteristic.

2 . The method of claim 1 , further comprising:
locating, responsive to the entity being represented in the image, an area occupied by the entity in the image, the position being relative to the area.

3 . The method of claim 2 , wherein the area comprises:
only the pixels that form the entity.

4 . The method of claim 1 , wherein the value of the characteristic is a color of the graphical artifact.

5 . The method of claim 1 , further comprising:
assigning, to a second characteristic of the graphical artifact, a second value, the second value corresponding to a number of comments in the post that refer to the entity.

6 . The method of claim 1 , further comprising:
assigning, to a second characteristic of the graphical artifact, a second value, the second value corresponding to a number of commentators who have supplied comments in the post, wherein the comments refer to the entity.

7 . The method of claim 1 , further comprising:
determining that a set of comments references the entity, the set including the comment; computing a second sentiment value of a second comment in the set of comments; and combining the sentiment value with the second sentiment value to form an overall sentiment value; and using the overall sentiment value as the sentiment value in the assigning.

8 . The method of claim 7 , further comprising:
averaging, as a part of the combining, the sentiment value and the second sentiment value.

9 . The method of claim 1 , further comprising:
performing image analysis, as a part of the determining whether the entity is represented in the image is accomplished, without relying on a keyword in a metadata of the image.

10 . The method of claim 1 , wherein the comment is an update to an existing comment.

11 . The method of claim 1 , wherein the entity is referenced in the comment indirectly without identifying the entity.

12 . A computer usable program product comprising one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices, the stored program instructions comprising:
program instructions to extract, using a processor and a memory to perform Natural Language Processing (NLP) on a comment to a social media post, an entity that is referenced in the comment, the entity being an object other than a human face that is depicted in an image in the post; program instructions to compute a sentiment value of the comment relative to the entity; program instructions to assign, to a characteristic of a graphical artifact, a value corresponding to an overall sentiment value, the overall sentiment value comprising the sentiment value and a second sentiment value from a second comment; and program instructions to cause the graphical artifact to be overlaid on the image at a position of the entity and with the value of the characteristic.

13 . The computer usable program product of claim 12 , further comprising:
program instructions to locate, responsive to the entity being represented in the image, an area occupied by the entity in the image, the position being relative to the area.

14 . The computer usable program product of claim 2 , wherein the area comprises:
only the pixels that form the entity.

15 . The computer usable program product of claim 12 , wherein the value of the characteristic is a color of the graphical artifact.

16 . The computer usable program product of claim 12 , further comprising:
program instructions to assign, to a second characteristic of the graphical artifact, a second value, the second value corresponding to a number of comments in the post that refer to the entity.

17 . The computer usable program product of claim 12 , further comprising:
program instructions to assign, to a second characteristic of the graphical artifact, a second value, the second value corresponding to a number of commentators who have supplied comments in the post, wherein the comments refer to the entity.

18 . The computer usable program product of claim 12 , wherein the computer usable code is stored in a computer readable storage device in a data processing system, and wherein the computer usable code is transferred over a network from a remote data processing system.

19 . The computer usable program product of claim 12 , wherein the computer usable code is stored in a computer readable storage device in a server data processing system, and wherein the computer usable code is downloaded over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system.

20 . A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:
program instructions to extract, using a processor and a memory to perform Natural Language Processing (NLP) on a comment to a social media post, an entity that is referenced in the comment, the entity being an object other than a human face that is depicted in an image in the post; program instructions to compute a sentiment value of the comment relative to the entity; program instructions to assign, to a characteristic of a graphical artifact, a value corresponding to an overall sentiment value, the overall sentiment value comprising the sentiment value and a second sentiment value from a second comment; and program instructions to cause the graphical artifact to be overlaid on the image at a position of the entity and with the value of the characteristic.

Assignees

• IBM

Inventors

• Greenberger Jeremy A
• Greenberger Zachary M
• Hewitt Trudy L

Classifications

• G06V30/274 Primary

  Syntactic or semantic context, e.g. balancing · CPC title

• G06T11/10

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G06Q10/40 Primary

  Business processes related to social networking or social networking services · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title

• G06T11/60

  Creating or editing images; Combining images with text · CPC title