Methods for emotion classification in text

Patent metadata

Field	Value
Publication number	US-12112134-B2
Application number	US-202217582206-A
Country	US
Kind code	B2
Filing date	Jan 24, 2022
Priority date	Mar 15, 2021
Publication date	Oct 8, 2024
Grant date	Oct 8, 2024

Abstract

The technology relates to methods for detecting and classifying emotions in textual communication, and using this information to suggest graphical indicia such as emoji, stickers or GIFs to a user. Two main types of models are fully supervised models and few-shot models. In addition to fully supervised and few-shot models, other types of models focusing on the back-end (server) side or client (on-device) side may also be employed. Server-side models are larger-scale models that can enable higher degrees of accuracy, such as for use cases where models can be hosted on cloud servers where computational and storage resources are relatively abundant. On-device models are smaller-scale models, which enable use on resource-constrained devices such as mobile phones, smart watches or other wearables (e.g., head mounted displays), in-home devices, embedded devices, etc.

First claim

The invention claimed is:

1. A method of training a computer-implemented emotion classification model, the method comprising:
retrieving, from a database, training data for a text-based application;
extracting from the training data, by one or more processors, a set of phrases that are associated with a set of taxonomy concepts;
extracting from the set of phrases, by the one or more processors, a set of emotion examples based on emotion-bearing phrases in the set of phrases; and
training, by the one or more processors, the emotion classification model based on a set of emotion-bearing phrases, wherein the trained emotion classification model associates one or more graphical indicia with at least one of a sender or a recipient of the text-based application.

2. The method of claim 1 , wherein the training data includes one or more of corpus-based phrases, manually selected phrases, crowdsourced phrases, or tenor phrases.

3. The method of claim 1 , wherein extracting the set of emotion examples includes performing at least one of exact matching, partial matching, or evaluating a semantic distance of a textual fragment with the set of phrases associated with the set of taxonomy concepts.

4. The method of claim 1 , wherein training the emotion classification model based on the set of emotion-bearing phrases includes evaluating emotion-neutral statements.

5. The method of claim 1 , wherein training the emotion classification model comprises training a few-shot classifier, and the method further comprises:
labeling a full corpus based on the trained few-shot classifier; and
training a supervised classifier over the full corpus.

6. The method of claim 1 , wherein extracting the set of phrases includes extracting only phrases with a least a threshold pointwise mutual information (PMI) value.

7. The method of claim 1 , wherein the one or more graphical indicia comprise at least one of a set of emoji, a set of stickers, or a set of GIFs.

8. The method of claim 1 , wherein the text-based application is one of a chat, a text chain, a videoconferencing application, a commenting platform, an automated help feature of an on-line application, or an assistant feature of a client computing device.

9. The method of claim 1 , wherein training the emotion classification model based on the set of emotion-bearing phrases includes incorporating a sentiment signal during the training to obtain a joint emotion and sentiment model.

10. The method of claim 1 , wherein training the emotion classification model based on the set of emotion-bearing phrases excludes predicting emotions for non-emotional text.

11. The method of claim 1 , wherein training the emotion classification model based on the set of emotion-bearing phrases includes providing a multi-label classification that supports more than one expressive concept per graphical indicia.

12. The method of claim 1 , wherein the method further includes performing down-sampling the set of taxonomy concepts.

13. The method of claim 1 , wherein the method further includes applying one or more user interface normalizers associated with visual elements of a given user interface.

14. The method of claim 1 , wherein the one or more graphical indicia includes multiple graphical indicia associated with different classes, and the method includes mapping each class to a particular emotional or non-emotional concept in a set of concepts.

15. The method of claim 14 , wherein one or more concepts in the set of concepts are extracted as keywords that appear in a vicinity of a corresponding one of the multiple graphical indicia in the text-based application.

16. The method of claim 15 , wherein the keywords are used for direct token replacement in a keyboard model.

17. The method of claim 14 , wherein the emotion classification model is configured to predict an emotion of a user based on one or more messages sent in a conversation using the text-based application.

18. The method of claim 1 , wherein the emotion classification model is configured to predict a list of concepts for an input message of the text-based application.

19. The method of claim 1 , wherein the emotion classification model is configured to suggest a particular graphical indicia.

20. The method of claim 1 , wherein the emotion classification model is configured for use with the text-based application to support customizing or changing a graphical user interface based on a detected emotion.

Assignees

• Google Llc

Inventors

• Movshovitz-Attias Dana
• Mcgregor Jr John Patrick
• Nemade Gaurav
• Ravi Sujith
• Ko Jeongwoo
• Demszky Dora

Classifications

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F40/289 Primary

  Phrasal analysis, e.g. finite state techniques or chunking · CPC title