Detecting key topics on online social networks

• US 10,459,914 B2
• Filed: 09/18/2015
• Issued: 10/29/2019
• Est. Priority Date: 09/18/2015
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Frenkel, Daniel, Datta, Ashim, Kauder, Bryan
• Primary Examiner(s): Raab, Christopher J
• Application Number:
  US14/858,366
• Publication Number:
  US 20170083628A1
• Time in Patent Office: 1,502 Days
• Field of Search: None
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0271 Personalized advertisement
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 51/216 Handling conversation history, e.g. grouping of messages in sessions or threads
• CPC Class Codes: H04L 51/52 for supporting social networking services

Abstract

A method includes accessing a first set of content objects of an online social network posted within a predetermined timeframe, and identifying trending topics. Each object may be associated with one or more topics. The method further includes accessing a second set of content objects, and identifying a plurality of co-occurring topics associated with the second set. Each content object of the second set is associated with at least one of the identified trending topics. Then, the method includes accessing a third set of content objects, and analyzing the plurality of trending topics and co-occurring topics to detect key topics. Each content object of the third set of content objects may be associated with at least one of the identified co-occurring topics or trending topics. The key topics may be detected based on determining the co-occurring topics or trending topics that are associated with a threshold number of content objects.

Claims

1. A method comprising, by one or more computing devices of an online social network:

accessing a first set of content objects of the online social network, wherein each content object of the first set of content objects is associated with a time within a predetermined timeframe, and wherein each content object of the first set of content objects is associated with one or more topics of a plurality of topics of the online social network;

identifying, from the plurality of topics, a set of trending topics associated with the first set of content objects, wherein each topic is identified as a trending topic based on an increase in a number or frequency of content objects of the first set of content objects associated with the topic above a first predetermined threshold;

accessing, from the first set of content objects, a second set of content objects of the online social network, wherein each content object of the second set of content objects is associated with at least one of the identified trending topics;

identifying a set of co-occurring topics associated with the second set of content objects, wherein each topic is identified as a co-occurring topic based on an increase in a number or frequency of content objects of the second set of content objects associated with the topic above a second predetermined threshold;

accessing a third set of content objects of the online social network, wherein each content object of the third set of content objects is associated with at least one of the identified co-occurring topics or at least one of the identified trending topics;

identifying, from the set of trending topics or the set of co-occurring topics, a set of key topics associated with the third set of content objects, wherein each topic is identified as a key topic based on an increase in a number or frequency of content objects of the third set of content objects associated with the topic above a third predetermined threshold; and

accessing a fourth set of content objects to send to a computing device of a user of the online social network, wherein each content object of the fourth set of content objects is associated with at least one of the identified key topics.

2. The method of claim 1, further comprising, prior to identifying the set of co-occurring topics, separating the second set of content objects into a plurality of groups,

wherein each of the groups is associated with one or more user attributes, and

wherein the identifying of the set of co-occurring topics associated with the second set of content objects comprises identifying one or more co-occurring topics for each of the plurality of groups of the second set of content objects.

3. The method of claim 2, wherein the one or more user attributes comprise one or more of an age, a gender, and a sentiment associated with one or more content objects of the second set of content objects.

4. The method of claim 1, further comprising, after accessing the fourth set of content objects:

accessing a fifth set of content objects of the online social network, the fifth set of content objects comprising one or more content objects of the fourth set of content objects associated with the key topics; and

separating the fifth set of content objects into a plurality of groups,

wherein each of the groups is associated with one or more user attributes.

5. The method of claim 4, wherein the fifth set of content objects intersects with the second set of content objects with regard to at least one content object that is associated with at least one of the co-occurring topics and at least one of the key topics.

6. The method of claim 4, wherein the fifth set of content objects is a subset of the third set of content objects.

7. The method of claim 4, wherein the one or more user attributes comprise one or more of an age, a gender, and a sentiment associated with one or more content objects of the fifth set of content objects.

8. The method of claim 4, further comprising:

comparing the content objects of at least a first group of the plurality of groups with the content objects of at least a second group of the plurality of groups, the first group being different from the second group.

9. The method of claim 8, wherein the first group is associated with one or more first user attributes and the second group is associated with one or more second user attributes, and wherein at least one of the one or more first user attributes is different from at least one of the one or more second user attributes.

10. The method of claim 1, wherein the set of key topics are ranked based on a user-specified metric.

11. The method of claim 1, wherein the first set of content objects comprises all content uploaded to the online social network within the predetermined timeframe.

12. The method of claim 1, wherein the content objects comprise one or more of an original post, a comment of a post, a reshare of a post, and a like-indication associated with a post.

13. The method of claim 1, wherein identifying the set of trending topics from the plurality of topics is based on an increase in a number or frequency of posts, comments, like-indications, or reshares on the online social network that are associated with the trending topic within the predetermined timeframe.

14. The method of claim 1, wherein the fourth set of content objects is a subset of the first set of content objects.

15. The method of claim 1, wherein the second set of content objects intersects with the fourth set of content objects with regard to at least one content object that is associated with at least one of the co-occurring topics and at least one of the trending topics.

16. The method of claim 1, wherein the second set of content objects is a subset of the fourth set of content objects.

17. The method of claim 1, wherein identifying the set of co-occurring topics associated with the second set of content objects is based on an increase in a number or frequency of posts, comments, like-indications, or reshares on the online social network that are associated with the co-occurring topic within the predetermined timeframe.

18. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

access a first set of content objects of the online social network, wherein each content object of the first set of content objects is associated with a time within a predetermined timeframe, and wherein each content object of the first set of content objects is associated with one or more topics of a plurality of topics of an online social network;

identify, from the plurality of topics, a set of trending topics associated with the first set of content objects, wherein each topic is identified as a trending topic based on an increase in a number or frequency of content objects of the first set of content objects associated with the topic above a first predetermined threshold;

access, from the first set of content objects, a second set of content objects of the online social network, wherein each content object of the second set of content objects is associated with at least one of the identified trending topics;

identify a set of co-occurring topics associated with the second set of content objects, wherein each topic is identified as a co-occurring topic based on an increase in a number or frequency of content objects of the second set of content objects associated with the topic above a second predetermined threshold;

access a third set of content objects of the online social network, wherein each content object of the third set of content objects is associated with at least one of the identified co-occurring topics or at least one of the identified trending topics;

identify, from the set of trending topics or the set of co-occurring topics, a set of key topics associated with the third set of content objects, wherein each topic is identified as a key topic based on an increase in a number or frequency of content objects of the third set of content objects associated with the topic above a third predetermined threshold; and

access a fourth set of content objects to send to a computing device of a user of the online social network, wherein each content object of the fourth set of content objects is associated with at least one of the identified key topics.

19. A system comprising:

one or more processors; and

a memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to;

access a first set of content objects of the online social network, wherein each content object of the first set of content objects is associated with a time within a predetermined timeframe, and wherein each content object of the first set of content objects is associated with one or more topics of a plurality of topics of an online social network;

identify, from the plurality of topics, a set of trending topics associated with the first set of content objects, wherein each topic is identified as a trending topic based on an increase in a number or frequency of content objects of the first set of content objects associated with the topic above a first predetermined threshold;

access, from the first set of content objects, a second set of content objects of the online social network, wherein each content object of the second set of content objects is associated with at least one of the identified trending topics;

identify a set of co-occurring topics associated with the second set of content objects, wherein each topic is identified as a co-occurring topic based on an increase in a number or frequency of content objects of the second set of content objects associated with the topic above a second predetermined threshold;

access a third set of content objects of the online social network, wherein each content object of the third set of content objects is associated with at least one of the identified co-occurring topics or at least one of the identified trending topics;

identify, from the set of trending topics or the set of and co-occurring topics, a set of key topics associated with the third set of content objects, wherein each topic is identified as a key topic based on an increase in a number or frequency of content objects of the third set of content objects associated with the topic above a third predetermined threshold; and

access a fourth set of content objects to send to a computing device of a user of the online social network, wherein each content object of the fourth set of content objects is associated with at least one of the identified key topics.