ORGANIZING SOCIAL NETWORK MESSAGES BASED ON TEMPORAL CHARACTERISTICS

• US 20150312201A1
• Filed: 03/18/2015
• Published: 10/29/2015
• Est. Priority Date: 04/25/2014
• Status: Active Grant

• Current Assignee: AirBNB Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Bastide, Paul R., DeLuca, Lisa Seacat, Do, Lydia M.
• Granted Patent: US 9,560,005 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: H04L 51/52 for supporting social networking services

Abstract

A method for organizing messages may include detecting, by a processor, receipt of each new message of an activity stream comprising a group of messages and determining, by the processor, a tense associated with each new message. The method may also include associating, by the processor, the tense with each new message. At least the tense may be used for organizing the group of messages of the activity stream. The method may additionally include adding, by the processor, each new message and the associated tense of the message to the activity stream.

Claims

1. A method for organizing messages, comprising:

detecting, by a processor, receipt of each new message of an activity stream comprising a group of messages;

determining, by the processor, a tense associated with each new message;

associating, by the processor, the tense with each new message, at least the tense being used for organizing the group of messages of the activity stream; and

adding, by the processor, each new message and the associated tense of the message to the activity stream.

2. The method of claim 1, wherein determining the tense associated with each new message comprises using natural language processing to determine at least one of a past tense, a present tense, and a future tense associated with each new message.

3. The method of claim 2, wherein determining the tense associated with each new message comprises determining any nuances based on a language of each new message.

4. The method of claim 3, wherein determining any nuances based on the language of each new message comprises determining any derivations of the tense associated with each new message based on the language of each new message by translating each new message using a classifier-based tense model for statistical machine translation of each new message.

5. The method of claim 1, further comprising:

determining an immediacy associated with each new message; and

associating an indication of the immediacy with each new message.

6. The method of claim 5, wherein determining the immediacy associated with each new message comprises:

detecting in each new message a description comprising at least one of a request for performance of a task and an event scheduled to occur at a future time;

detecting in each new message at least one of a due date for completion of the task and a date for occurrence of the event; and

assigning to a particular new message a default due date for determining the immediacy in response the particular new message not including the due date for completion of the task.

7. The method of claim 5, further comprising:

determining for each new message, at least one of a time the message is posted to a social network and a time the message is first viewed by a member of the social network; and

associating, with each new message, a decay function based on at least one of the time the message is posted to the social network and the time the message is first viewed by the member of the social network.

8. The method of claim 7, wherein associating the decay function to the message comprises one of invalidating or changing the tense of the message based on a duration of time from at least one of when the message was posted to the social network and when the message was first viewed by the member of the social network.

9. The method of claim 7, further comprising organizing the group of messages in the activity stream based on at least one of the tense, immediacy and decay function associated with each message in the activity stream in response to a user selecting an organization feature.

10. The method of claim 9, presenting the activity stream including the organized messages based on at least one of the tense, immediacy and the decay associated with each message.

11. The method of claim 10, further comprising applying a temporal characteristic to each message in the activity stream to limit a number of messages being presented, wherein the temporal characteristic comprises a predetermined time period since the message was posted to the social network.

12. The method of claim 9, wherein organizing the plurality of messages comprises sorting a particular message comprising more than one tense by each of the tenses.

13-20. -20. (canceled)