Systems and methods for recommending follow up content

Patent metadata

Field	Value
Publication number	US-2016179968-A1
Application number	US-201414579710-A
Country	US
Kind code	A1
Filing date	Dec 22, 2014
Priority date	Dec 22, 2014
Publication date	Jun 23, 2016
Grant date	—

Abstract

Systems, methods, and non-transitory computer readable media configured to detect access by a user to an original content item relating to a story. At least one of a comments based technique, a token based technique, and a tag based technique is performed on content items. Constraints are applied to identify at least one follow up content item from the content items relating to a development of the story.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
detecting, by a computing system, access by a user to an original content item relating to a story; performing, by the computing system, at least one of a comments based technique, a token based technique, and a tag based technique on content items; and applying, by the computing system, constraints to identify at least one follow up content item from the content items relating to a development of the story.

2 . The computer-implemented method of claim 1 , wherein the applying constraints to identify at least one follow up content item further comprises:
applying a time difference threshold between a time of the original content item and a time of the at least one follow up content item; and applying a weight value threshold to the at least one follow up content item.

3 . The computer-implemented method of claim 1 , wherein the performing a comments based technique on content items further comprises:
identifying a first posting having a first link and associated with a first time;
identifying a second posting, in response to the first posting, having a second link and associated with a second time; and
determining that the second link relates to the at least one follow up content item and that the first link relates to the original content item when the second time is subsequent to the first time.

4 . The computer-implemented method of claim 1 , wherein the performing a token based technique on content items further comprises:
tokenizing at least a portion of the original content item and at least a portion of the content items; generating representations of the original content item and the content items based on the tokenizing; comparing similarity between the original content item and the content items based on the representations; and determining that a content item of the content items is the at least one follow up content item based on the similarity between the original content item and the content item.

5 . The computer-implemented method of claim 4 , wherein the generating representations further comprises:
performing a tf-idf technique.

6 . The computer-implemented method of claim 4 , wherein the comparing similarity between the original content item and the content items further comprises:
performing cosine similarity.

7 . The computer-implemented method of claim 1 , wherein the performing a tag based technique on content items further comprises:
receiving a tag associated with the story relating to the original content item, the tag based on a category and a hierarchical level of a hierarchical index; and determining that a content item of the content items is the at least one follow up content item when the content item is labeled with the tag.

8 . The computer-implemented method of claim 1 , further comprising:
modulating the constraints to selectively increase or decrease an amount of the at least one follow up content item based on modification of at least one of a time difference threshold and a weight value threshold.

9 . The computer-implemented method of claim 1 , further comprising:
training a machine learning model to identify follow up content items in a supervised process based on user interaction with the at least one follow up content item or manual supervision of identification of the at least one follow up content item.

10 . The computer-implemented method of claim 1 , wherein a third party system distinct from a social networking system first publishes at least one of the original content item and the at least one follow up content item.

11 . A system comprising:
at least one processor; and a memory storing instructions that, when executed by the at least one processor, cause the system to perform: detecting access by a user to an original content item relating to a story; performing at least one of a comments based technique, a token based technique, and a tag based technique on content items; and applying constraints to identify at least one follow up content item from the content items relating to a development of the story.

12 . The system of claim 11 , wherein the wherein the applying constraints to identify at least one follow up content item further comprises:
applying a time difference threshold between a time of the original content item and a time of the at least one follow up content item; and applying a weight value threshold to the at least one follow up content item.

13 . The system of claim 11 , further comprising:
modulating the constraints to selectively increase or decrease an amount of the at least one follow up content item based on modification of at least one of a time difference threshold and a weight value threshold.

14 . The system of claim 11 , further comprising:
training a machine learning model to identify follow up content items in a supervised process based on user interaction with the at least one follow up content item or manual supervision of identification of the at least one follow up content item.

15 . The system of claim 11 , wherein a third party system distinct from a social networking system first publishes at least one of the original content item and the at least one follow up content item.

16 . A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
detecting access by a user to an original content item relating to a story; performing at least one of a comments based technique, a token based technique, and a tag based technique on content items; and applying constraints to identify at least one follow up content item from the content items relating to a development of the story.

17 . The non-transitory computer-readable storage medium of claim 16 , wherein the applying constraints to identify at least one follow up content item further comprises:
applying a time difference threshold between a time of the original content item and a time of the at least one follow up content item; and applying a weight value threshold to the at least one follow up content item.

18 . The non-transitory computer-readable storage medium of claim 16 , further comprising:
modulating the constraints to selectively increase or decrease an amount of the at least one follow up content item based on modification of at least one of a time difference threshold and a weight value threshold.

19 . The non-transitory computer-readable storage medium of claim 16 , further comprising:
training a machine learning model to identify follow up content items in a supervised process based on user interaction with the at least one follow up content item or manual supervision of identification of the at least one follow up content item.

20 . The non-transitory computer-readable storage medium of claim 16 , wherein a third party system distinct from a social networking system first publishes at least one of the original content item and the at least one follow up content item.

Assignees

• Facebook Inc

Inventors

• Ormseth Holly Marie
• Gerson Elad
• Dassa Guy
• El-Arini Khalid Bakry
• Shankar Gaurav
• Wang Yuanxuan
• Kacholia Varun
• Mishra Prasoon
• Vickrey David
• Hajarnis Sanjeet Uday
• Thaker Sahil P

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06F3/0482

  Interaction with lists of selectable items, e.g. menus · CPC title

• G06Q30/0251

  Targeted advertisements · CPC title

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/954 Primary

  Navigation, e.g. using categorised browsing · CPC title