# US 10,871,877 B1 · Content-based contextual reactions for posts on a social networking system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,871,877 B1
- Document ID: US10871877B1
- Status: Granted
- Kind: B1
- Application number: 16/206,852
- Filed: 2018-11-30
- Granted: 2020-12-22
- Earliest claimed: 2018-11-30
- Assignees: Facebook, Inc.
- Applicants: Facebook, Inc.
- Inventors: Robin Maxime Clediere
- Web page: https://patentgrep.com/patent/US10871877B1

## CPC

- G06Q 10/40: Business processes related to social networking or social networking services
- G06F 3/04817: using icons (graphical or visual programming using iconic symbols G06F8/34)
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 16/9536: Search customisation based on social or collaborative filtering
- G06F 40/279: Recognition of textual entities
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A social networking system allows users to more easily and appropriately react to posts made by other users. A post—including its text, photos, and/or location—is analyzed to determine one or more contexts of the post. Supervised machine learning techniques may be employed to determine the contexts of posts. Based on the context(s) of the post, a contextual reaction icon is selected for inclusion in the options of reactions from which users can select. A post can have multiple contextual reactions. The contextual reactions for a post may change over time as comments are made to the post or the content of the post is otherwise altered.

## Claims

### Claim 1

A computer-implemented method for making available contextual reactions for a social networking post, the computer-implemented method comprising:
receiving, by a social networking system, a post by a user of the social networking system, the post including one or more images and text provided by the user;
receiving a comment on the post from other users of the social networking system;
storing in a data structure, by the social networking system, data associated with the post, the data comprising the text and the one or more images of the post, the received comment, stored context associated with the post, and data associated with contextual reactions previously made to the post including user information associated with users who previously reacted to the post and reactions that the users previously made;
analyzing the stored data associated with the post;
based at least in part on the analysis, determining a plurality of contexts of the post, wherein each context of the plurality of contexts indicates a topic of the post, and wherein the contexts are arranged within a hierarchy in which contexts on a lower level represent more specific topics than the topics of contexts that are on a higher level;
based at least in part on the plurality of contexts, selecting, from a plurality of different levels of the hierarchy, a plurality of contextual reaction icons for the post wherein the plurality of contextual reaction icons include features that illustrate the plurality of contexts, and are different for different levels of contexts from the hierarchy;
storing the determined plurality of contexts of the post and the selected plurality of contextual reaction icons in the data structure associated with the post;
providing the post for display to other users of the social networking system, the post displayed with a plurality of reaction icons from which users can select, the plurality of reaction icons displayed outside of the text of the post, the reaction icons including the plurality of contextual reaction icons selected from the plurality of different levels of the hierarchy;
providing the comment for display with a plurality of contextual reaction icons from which users can select, the contextual reaction icons determined based on analysis of content of the comment;
receiving a selection of at least one of the other users of one of the plurality of the contextual reaction icons for the post, the selected contextual reaction icon recorded for the at least one of the other users as a reaction to the post; and
receiving a selection of at least one of the plurality of the contextual reaction icons for the comment.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the post is associated with a location, and wherein determining the context of the post is based at least in part on the location.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the post further is associated with an event, and wherein determining the context of the post is based at least in part on the event.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the analyzing comprises at least one of: computer vision, object recognition, or text mining.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein each context of the hierarchy is mapped to one or more contextual reaction icons.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the determining of the context of the post is performed using a machine learned model, the machine learning comprising:
receiving a training set that contains a set of posts for which a user has already specified a contextual reaction icon;
determining the contexts of the posts based on the specified contextual reaction icons; and
training the machine learned model by supplying the posts of the training set, and the determined contexts of the posts, as input to a supervised machine learning algorithm.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, further comprising:
receiving a comment associated with the post from another user of the social networking system;
determining an updated context of the post based at least in part on the comment, the updated context of the post different from the context of the post previously determined; and
providing the post for display to other users of the social networking system, the plurality of reaction icons from which users can select including the updated contextual reaction icon.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the contextual reaction icon is selected based at least in part on a user to whom the post is provided.

### Claim 9

A non-transitory computer-readable storage medium storing instructions for execution on a computer processor, the instructions when executed performing actions comprising:
receiving, by a social networking system, a post by a user of the social networking system, the post including one or more images and text provided by the user;
receiving a comment on the post from other users of the social networking system;
storing in a data structure, by the social networking system, data associated with the post, the data comprising the text and the one or more images of the post, the received comment, stored context associated with the post, and data associated with contextual reactions previously made to the post including user information associated with users who previously reacted to the post and reactions that the users previously made;
analyzing the stored data associated with the post;
based at least in part on the analysis, determining a plurality of contexts of the post, wherein each context of the plurality of contexts indicates a topic of the post, and wherein the contexts are arranged within a hierarchy in which contexts on a lower level represent more specific topics than the topics of contexts that are on a higher level;
based at least in part on the plurality of contexts, selecting, from a plurality of different levels of the hierarchy, a plurality of contextual reaction icons for the post wherein the plurality of contextual reaction icons include features that illustrate the plurality of contexts, and are different for different levels of contexts from the hierarchy;
storing the determined plurality of contexts of the post and the selected plurality of contextual reaction icons in the data structure associated with the post;
providing the post for display to other users of the social networking system, the post displayed with a plurality of reaction icons from which users can select, the plurality of reaction icons displayed outside of the text of the post, the reaction icons including the plurality of contextual reaction icons selected from the plurality of different levels of the hierarchy;
providing the comment for display with a plurality of contextual reaction icons from which users can select, the contextual reaction icons determined based on analysis of content of the comment;
receiving a selection of at least one of the other users of one of the plurality of the contextual reaction icons for the post, the selected contextual reaction icon recorded for the at least one of the other users as a reaction to the post; and
receiving a selection of at least one of the plurality of the contextual reaction icons for the comment.

### Claim 10 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the post is associated with a location, and wherein determining the context of the post is based at least in part on the location.

### Claim 11 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the post further is associated with an event, and wherein determining the context of the post is based at least in part on the event.

### Claim 12 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the analyzing comprises at least one of: computer vision, object recognition, or text mining.

### Claim 13 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein each context of the hierarchy is mapped to one or more contextual reaction icons.

### Claim 14 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the determining of the context of the post is performed using a machine learned model, the machine learning comprising:
receiving a training set that contains a set of posts for which a user has already specified a contextual reaction icon;
determining the contexts of the posts based on the specified contextual reaction icons; and
training the machine learned model by supplying the posts of the training set, and the determined contexts of the posts, as input to a supervised machine learning algorithm.

### Claim 15 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, the actions further comprising:
receiving a comment associated with the post from another user of the social networking system;
determining an updated context of the post based at least in part on the comment, the updated context of the post different from the context of the post previously determined; and
providing the post for display to other users of the social networking system, the plurality of reaction icons from which users can select including the updated contextual reaction icon.

### Claim 16 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the contextual reaction icon is selected based at least in part on a user to whom the post is provided.

### Claim 17

A computer system comprising:
a computer processor; and
a non-transitory computer-readable storage medium storing instructions that when executed by the computer processor perform actions comprising:
receiving, by a social networking system, a post by a user of the social networking system, the post including one or more images and text provided by the user;
receiving a comment on the post from other users of the social networking system;
storing in a data structure, by the social networking system, data associated with the post, the data comprising the text and the one or more images of the post, the received comment, stored context associated with the post, and data associated with contextual reactions previously made to the post including user information associated with users who previously reacted to the post and reactions that the users previously made;
analyzing the stored data associated with the post;
based at least in part on the analysis, determining a plurality of contexts of the post, wherein each context of the plurality of contexts indicates a topic of the post, and wherein the contexts are arranged within a hierarchy in which contexts on a lower level represent more specific topics than the topics of contexts that are on a higher level;
based at least in part on the plurality of contexts, selecting, from a plurality of different levels of the hierarchy, a plurality of contextual reaction icons for the post wherein the plurality of contextual reaction icons include features that illustrate the plurality of contexts, and are different for different levels of contexts from the hierarchy;
storing the determined plurality of contexts of the post and the selected plurality of contextual reaction icons in the data structure associated with the post;
providing the post for display to other users of the social networking system, the post displayed with a plurality of reaction icons from which users can select, the plurality of reaction icons displayed outside of the text of the post, the reaction icons including the plurality of contextual reaction icons selected from the plurality of different levels of the hierarchy;
providing the comment for display with a plurality of contextual reaction icons from which users can select, the contextual reaction icons determined based on analysis of content of the comment;
receiving a selection of at least one of the other users of one of the plurality of the contextual reaction icons for the post, the selected contextual reaction icon recorded for the at least one of the other users as a reaction to the post; and
receiving a selection of at least one of the plurality of the contextual reaction icons for the comment.

### Claim 18 (depends on 17)

The computer system of claim 17, the actions further comprising:
receiving a comment associated with the post from another user of the social networking system;
determining an updated context of the post based at least in part on the comment, the updated context of the post different from the context of the post previously determined; and
providing the post for display to other users of the social networking system, the plurality of reaction icons from which users can select including the updated contextual reaction icon.