Computer implemented methods and apparatus for providing near real-time predicted engagement level feedback to a user composing a social media message

• US 9,264,391 B2
• Filed: 12/28/2012
• Issued: 02/16/2016
• Est. Priority Date: 11/01/2012
• Status: Active Grant

• Current Assignee: Salesforce.com, Inc.
• Original Assignee: Salesforce.com, Inc.
• Inventors: Daily, Camden K., Jaynes, Christopher A., Santos, Katrina L., Castera, Richard P. J.
• Primary Examiner(s): Parry, Chris
• Assistant Examiner(s): JAHNIGE, CAROLINE H
• Application Number:
  US13/729,509
• Publication Number:
  US 20140122622A1
• Time in Patent Office: 1,145 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]
• CPC Class Codes: H04L 51/42 Mailbox-related aspects, e.g. synchronisation of mailboxes
• CPC Class Codes: H04L 51/52 for supporting social networking services

Abstract

Disclosed are methods, apparatus, systems, and computer readable storage media for providing near real-time feedback when a user is composing a social media message. The feedback can indicate a predicted level of engagement with the social media message by other users of a social networking system. In some implementations, a prediction model is used to determine a predicted engagement score, which is an approximation of the predicted level of engagement with the social media message by the other users. A computing device can be configured to display a graphical representation of the predicted engagement score in a user interface at which the social media message is being composed.

Claims

1. A computer implemented method for providing near real-time feedback to a first user of a social networking system when the first user is composing a social media message, the feedback indicating a predicted level of engagement with the social media message by a second one or more users of the social networking system, the method comprising:

receiving, at a server, message information regarding the social media message being composed by the first user at a computing device;

determining, using a prediction model, a predicted engagement score based on the message information, the predicted engagement score being an approximation of the predicted level of engagement with the social media message by the second one or more users of the social networking system; and

sending data representing the predicted engagement score to the computing device to display a presentation in a user interface at which the social media message is being composed, the presentation including a graphical representation of the predicted engagement score and a graph presenting one or more previous predicted engagement scores for the social media message, the graphical representation including a graphical indicator proximate a region of the user interface at which the social media message is being composed, the graphical indicator configured to indicate at least a positive or a negative change to the predicted engagement score in response to a change to content of the social media message being composed.

2. The method of claim 1, wherein the message information includes one or more message information attributes, including:

content of the social media message, a length of the social media message, a type of the social media message, an attachment of the social media message, a timestamp of the social media message, a scheduled date or time for sending the social media message, a link in the social media message, a number of links in the social media message, an identity of the first user, an identity of a recipient user, and subject matter of the social media message.

3. The method of claim 1, wherein the prediction model determines the predicted engagement score by:

identifying, based on previous social media messages and monitored engagement levels of the previous social media messages, one or more common message information attributes having a predicted impact on engagement, each common message information attribute having a weight value assigned by the prediction model corresponding to the respective predicted impact; and

calculating the predicted engagement score based on a measure of the one or more common message information attributes in the message information of the social media message being composed.

4. The method of claim 3, wherein the monitored engagement level of a previous social media message is determined by one or more of:

a number of likes, a number of dislikes, a number of shares, a number of comments, and a number of views.

5. The method of claim 3, wherein the prediction model is configured to:

monitor the engagement levels of the previous social media messages, and adjust the weight values of the one or more common message information attributes identified by the prediction model.

6. The method of claim 1, wherein the predicted engagement score is a numerical approximation.

7. The method of claim 1, wherein the graphical indicator includes an arrow or a line indicating whether a most recent change to the content of the social media message increased or decreased the predicted level of engagement.

8. The method of claim 1, wherein the graphical indicator includes a positive number or a negative number indicating a numerical change to the predicted engagement score in response to a most recent change to the content of the social media message.

9. The method of claim 1, further comprising:

receiving user input data from the computing device, the user input requesting from the server previous predicted engagement scores for the social media message; and

sending the previous predicted engagement scores to the computing device, the graph indicating previous changes made to the message information and respective previous predicted engagement scores.

10. A computing system for providing near real-time feedback to a first user of a social networking system when the first user is composing a social media message, the feedback indicating a predicted level of engagement with the social media message by a second one or more users of the social networking system, the computing system comprising:

one or more processors operable to execute one or more instructions configured to cause;

processing message information received at a server regarding the social media message being composed by the first user at a computing device;

determining, using a prediction model, a predicted engagement score based on the message information, the predicted engagement score being an approximation of the predicted level of engagement with the social media message by the second one or more users of the social networking system; and

sending data representing the predicted engagement score to the computing device to display a presentation in a user interface at which the social media message is being composed, the presentation including a graphical representation of the predicted engagement score and a graph presenting one or more previous predicted engagement scores for the social media message, the graphical representation including a graphical indicator proximate a region of the user interface at which the social media message is being composed, the graphical indicator configured to indicate at least a positive or a negative change to the predicted engagement score in response to a change to content of the social media message being composed.

11. The computing system of claim 10, the one or more processors further operable to execute one or more instructions configured to cause:

identifying, based on previous social media messages and monitored engagement levels of the previous social media messages, one or more common message information attributes having a predicted impact on engagement, each common message information attribute having a weight value assigned by the prediction model corresponding to the respective predicted impact; and

calculating the predicted engagement score based on a measure of the one or more common message information attributes in the message information of the social media message being composed.

12. The computing system of claim 11, wherein the prediction model is configured to:

monitor the engagement levels of the previous social media messages, and adjust the weight values of the one or more common message information attributes identified by the prediction model.

13. The computing system of claim 10, the one or more processors further operable to execute one or more instructions configured to cause:

receiving user input data from the computing device, the user input requesting from the server previous predicted engagement scores for the social media message; and

sending the previous predicted engagement scores to the computing device, the graph indicating previous changes made to the message information and respective previous predicted engagement scores.

14. A non-transitory tangible computer-readable storage medium storing instructions executable by a server to cause a method to be performed for providing near real-time feedback to a first user of a social networking system when the first user is composing a social media message, the feedback indicating a predicted level of engagement with the social media message by a second one or more users of the social networking system, the method comprising:

receiving, at a server, message information regarding the social media message being composed by the first user at a computing device;

determining, using a prediction model, a predicted engagement score based on the message information, the predicted engagement score being an approximation of the predicted level of engagement with the social media message by the second one or more users of the social networking system; and

sending data representing the predicted engagement score to the computing device to display a presentation in a user interface at which the social media message is being composed, the presentation including a graphical representation of the predicted engagement score and a graph presenting one or more previous predicted engagement scores for the social media message, the graphical representation including a graphical indicator proximate a region of the user interface at which the social media message is being composed, the graphical indicator configured to indicate at least a positive or a negative change to the predicted engagement score in response to a change to content of the social media message being composed.

15. The non-transitory tangible computer-readable storage medium of claim 14, wherein the server determines the predicted engagement score by:

identifying, based on previous social media messages and monitored engagement levels of the previous social media messages, one or more common message information attributes having a predicted impact on engagement, each common message information attribute having a weight value assigned by the prediction model corresponding to the respective predicted impact; and

calculating the predicted engagement score based on a measure of the one or more common message information attributes in the message information of the social media message being composed.

16. The non-transitory tangible computer-readable storage medium of claim 15, wherein the prediction model is configured to:

monitor the engagement levels of the previous social media messages, and adjust the weight values of the one or more common message information attributes identified by the prediction model.

17. The non-transitory tangible computer-readable storage medium of claim 14, the method further comprising:

receiving user input data from the computing device, the user input requesting from the server previous predicted engagement scores for the social media message; and

sending the previous predicted engagement scores to the computing device, the graph indicating previous changes made to the message information and respective previous predicted engagement scores.