Ideograms based on sentiment analysis

Patent metadata

Field	Value
Publication number	US-10050926-B2
Application number	US-201414173470-A
Country	US
Kind code	B2
Filing date	Feb 5, 2014
Priority date	Feb 5, 2014
Publication date	Aug 14, 2018
Grant date	Aug 14, 2018

Abstract

Particular embodiments of a method comprise analyzing a message to perform sentiment analysis with respect to at least a portion of the message. One or more sentiments associated with the at least a portion of the message may then be identified. One or more ideograms (e.g., written characters, symbols or images that represent an idea or thing), each corresponding to an identified sentiment, may then be suggested to a user for insertion into a message. Upon receiving a user selection of one or more of the ideograms in relation to some portion of the message, an association may be saved in a user-specific dictionary linking the user-selected one or more of the ideograms with the portion of the message. In particular embodiments, the sentiment analysis may incorporate social-networking information and/or historical ideogram usage information.

First claim

What is claimed is:

1. A method comprising:
by a computing device, analyzing a message to perform sentiment analysis with respect to at least a portion of the message, the message being composed by an author of the message for a recipient of the message, wherein the message is associated with a target mentioned in the message, wherein the target mentioned in the message is a person other than the recipient of the message who is mentioned in the message, and wherein the target mentioned in the message has a social relationship with the author of the message, the social relationship being determined based on a social graph comprising social-graph nodes corresponding to the author of the message and the target mentioned in the message and further comprising social-graph edges connecting the social-graph nodes;
by the computing device, identifying one or more sentiments associated with the at least a portion of the message;
by the computing device, determining one or more ideograms based on the social relationship between the author of the message and the target mentioned in the message and further based on ideogram usage history associated with the author of the message in which the author previously manually selected an ideogram other than a suggested ideogram and ideogram usage history associated with one or more other users that match profile information of the author of the message and that have a social relationship with the author, wherein each ideogram corresponds to an identified sentiment; and
by the computing device, suggesting one or more of the one or more determined ideograms.

2. The method of claim 1 , further comprising:
inserting at least one of the ideograms into the message.

3. The method of claim 2 , wherein the at least one of the ideograms comprises metadata for the at least one of the ideograms, the metadata comprising descriptive text for the ideogram, text typed by the author for which the ideogram was substituted, or data associated with the author's use of the ideogram.

4. The method of claim 1 , further comprising:
receiving a user selection of one or more of the ideograms in relation to the at least a portion of the message; and
saving, in a user-specific dictionary, an association between the user-selected one or more of the ideograms and the at least a portion of the message.

5. The method of claim 4 , wherein the saving the association comprises:
saving, together with the association, metadata for the message.

6. The method of claim 1 , wherein the sentiment analysis is further based on: social-networking information associated with an author of the message, or information associated with a social-networking relationship between an author of the message and a target of the message.

7. The method of claim 1 , wherein the identifying one or more sentiments comprises determining a score for each of the identified sentiments, wherein each of the ideograms is associated with at least one score corresponding to a sentiment, and wherein the at least one score associated with the ideogram correlates to a score for at least one of the identified sentiments within a specified tolerance.

8. The method of claim 1 , wherein the suggesting one or more ideograms comprises:
providing the one or more ideograms for selection by the user for insertion into the message; or
suggesting the one or more ideograms for substitution with respect to the at least a portion of the message.

9. The method of claim 8 , wherein the suggesting one or more ideograms comprises:
presenting the one or more ideograms sorted into an emotional range.

10. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
analyze a message to perform sentiment analysis with respect to at least a portion of the message, the message being composed by an author of the message for a recipient of the message, wherein the message is associated with a target mentioned in the message, wherein the target mentioned in the message is a person other than the recipient of the message who is mentioned in the message, and wherein the target mentioned in the message has a social relationship with the author of the message, the social relationship being determined based on a social graph comprising social-graph nodes corresponding to the author of the message and the target mentioned in the message and further comprising social-graph edges connecting the social-graph nodes;
identify one or more sentiments associated with the at least a portion of the message;
determine one or more ideograms based on the social relationship between the author of the message and the target mentioned in the message and further based on ideogram usage history associated with the author of the message in which the author previously manually selected an ideogram other than a suggested ideogram and ideogram usage history associated with one or more other users that match profile information of the author of the message and that have a social relationship with the author, wherein each ideogram corresponds to an identified sentiment; and
suggest one or more of the one or more determined ideograms.

11. The media of claim 10 , further comprising software operable when executed to:
insert at least one of the ideograms into the message.

12. The media of claim 11 , wherein the at least one of the ideograms comprises metadata for the at least one of the ideograms, the metadata comprising descriptive text for the ideogram, text typed by the author for which the ideogram was substituted, or data associated with the author's use of the ideogram.

13. The media of claim 10 , further comprising software operable when executed to:
receive a user selection of one or more of the ideograms in relation to the at least a portion of the message; and
save, in a user-specific dictionary, an association between the user-selected one or more of the ideograms and the at least a portion of the message.

14. The media of claim 13 , wherein the software operable when executed to save the association comprises software operable when executed to:
save, together with the association, metadata for the message.

15. The media of claim 10 , wherein the sentiment analysis is further based on: social-networking information associated with an author of the message, or information associated with a social-networking relationship between an author of the message and a target of the message.

16. A system comprising:
one or more processors; and
a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to:
analyze a message to perform sentiment analysis with respect to at least a portion of the message, the message being composed by an author of the message for a recipient of the message, wherein the message is associated with a target mentioned in the message, wherein the target mentioned in the message is a person other than the recipient of the message who is mentioned in the message, and wherein the target mentioned in the message has a social relationship with the author of the message, the social relationship being determined based on a social graph comprising social-graph nodes corresponding to the author of the message and the target mentioned in the message and further comprising social-graph edges connecting the social-graph nodes;
identify one or more sentiments associated with the at least a portion of the message;
determine one or more ideograms based on the social relationship between the author of the message and the targ

Assignees

• Facebook Inc

Inventors

• Ebersman David
• Lessin Samuel
• Stocky Thomas
• Vernal Michael

Classifications

• G06F40/30

  Semantic analysis · CPC title

• G06F40/274

  Converting codes to words; Guess-ahead of partial word inputs · CPC title

• G06F3/04817

  using icons (graphical or visual programming using iconic symbols G06F8/34) · CPC title

• G06F3/04886 Primary

  by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus · CPC title

• H04L51/02

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title