Determining stories of interest based on quality of unconnected content

Patent metadata

Field	Value
Publication number	US-9712578-B2
Application number	US-201414307331-A
Country	US
Kind code	B2
Filing date	Jun 17, 2014
Priority date	Jun 17, 2014
Publication date	Jul 18, 2017
Grant date	Jul 18, 2017

Abstract

A system identifies unconnected content items of high quality and provides the unconnected content items for display to a user. The method comprises receiving several content items posted on pages of a social networking system. The system then determines a subset of those content items (e.g., high quality content items). A topic is then extracted from each of the subset of content items. The topic is mapped to one or more related pages of the social networking system that represent an expanded set of pages associated with the content item. For each of the related pages, a user is identified who is connected to the related page. Finally, the content item (e.g., a high quality content item) is provided to the user for display in the user's newsfeed.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving a plurality of content items posted on pages of a social networking system;
determining, by a processor, from the plurality of content items, a subset of content items determined to be high quality content items, the determination of the high quality content items comprising:
receiving a user interaction rate associated with each of the plurality of content items posted on the social networking system;
responsive to the user interaction rate indicating a positive reaction to the content item, including the content item in the subset as a high quality content item, the user interaction rate indicated as positive reaction when the user interaction rate is higher than or equal to a threshold interaction rate; and
responsive to the user interaction rate indicating a negative reaction to the content item, excluding the content item from the subset, the user interaction rate indicated as negative reaction when the user interaction rate is lower than the threshold interaction rate; and

for each of the content items of the subset:
extracting a first topic from the content item by analyzing terms and phrases of the content item,
mapping, by the processor, the extracted first topic to one or more related pages of the social networking system, the one or more related pages include the extracted first topic, and
for each of the one or more related pages:
identifying a user of the social networking system connected to the related page, and
providing the content item in a newsfeed for display to the user.

2. The method of claim 1 , wherein the determination of the high quality content items further comprises:
computing a quality score representing a lexical quality for each of the plurality of content items and selecting the subset of content items with quality score above a threshold quality score, the quality score inversely related to a number of lexical errors in the content item.

3. The method of claim 1 , wherein the user interaction rate is associated with how often users of the social networking system share or hide the content item with other users.

4. The method of claim 2 , wherein the lexical quality comprises one or more of spelling correctness, grammatical correctness, and vocabulary choice.

5. The method of claim 1 , wherein the determination of the high quality content items further comprises performing a semantic analysis on each of the plurality of content items, the semantic analysis comprises computing a semantic quality score representing a semantic quality for each of the plurality of content items and selecting the subset of content items with semantic quality score above a threshold semantic quality score, the semantic quality score inversely related to a number of subject matter topics in the content item.

6. The method of claim 1 , wherein the determination of the high quality content items further comprises determining whether each of the plurality of content items is trending, wherein a content item is determined to be trending if the content item has an interaction rate higher than a threshold interaction rate.

7. The method of claim 1 , wherein the user is not connected to the page on which the high quality content item is posted.

8. The method of claim 1 , wherein mapping the extracted first topic to one or more related pages comprises:
identifying a hashtag comprised within the extracted first topic, the hashtag comprising a segment of text;
identifying one or more related pages that comprise the hashtag; and
associating the extracted first topic with the one or more related pages.

9. The method of claim 1 , wherein mapping the extracted first topic to one or more related pages comprises:
identifying a second user, the second user having interacted with the page to which the content item was posted;
identifying one or more related pages with which the second user has also interacted; and
associating the extracted first topic to the one or more related pages.

10. The method of claim 1 , further comprising, prior to providing the content item in the newsfeed for display to the user:
transmitting the content item to a review agent; and
receiving, from the review agent, a response indicating approval of the content item.

11. The method of claim 1 , wherein the content item associated with the related page is a high quality content item, and wherein the method further comprises:
identifying one or more additional high quality content items;
for each of the one or more additional high quality content items:
extracting a second topic from the additional high quality content item; and
determining that the extracted second topic is related to the extracted first topic; and

prior to providing the high quality content item associated with the related page for display to the user:
clustering the high quality content item with the one or more additional high quality content items, and
selecting the high quality content item as a best content item of the cluster for display to the user, the best content item comprising higher threshold number of positive quality indicators than the one or more additional high quality content items.

12. The method of claim 1 , wherein the mapping comprises a further mapping of the related pages to one or more additional pages.

13. A computer program product comprising a computer-readable storage medium containing computer program code for:
receiving a plurality of content items posted on pages of a social networking system;
determining, by a processor, from the plurality of content items, a subset of content items determined to be high quality content items, the determination of the high quality content items comprising:
receiving a user interaction rate associated with each of the plurality of content items posted on the social networking system;
responsive to the user interaction rate indicating a positive reaction to the content item, including the content item in the subset as a high quality content item, the user interaction rate indicated as positive reaction when the user interaction rate is higher than or equal to a threshold interaction rate; and
responsive to the user interaction rate indicating a negative reaction to the content item, excluding the content item from the subset, the user interaction rate indicated as negative reaction when the user interaction rate is lower than the threshold interaction rate; and

for each of the content items of the subset:
extracting a first topic from the content item by analyzing terms and phrases of the content item,
mapping, by the processor, the extracted first topic to one or more related pages of the social networking system, the one or more related pages include the extracted first topic, and

for each of the one or more related pages:
identifying a user of the social networking system connected to the related page, and
providing the content item in a newsfeed for display to the user.

14. The computer program product of claim 13 , wherein the determination of the high quality content items further comprises:
computing a quality score representing a lexical quality for each of the plurality of content items and selecting the subset of content items with quality score above a threshold quality score, the quality score inversely related to a number of lexical errors in the content item.

15. The computer program product of claim 13 , wherein the user interaction rate is associated with how often users of the social networking system share or hide the content item with other users.

Assignees

• Facebook Inc

Inventors

• Klein Gregory Joseph
• Green Bradley Ray
• Li Jun
• Sorg Jonathan Daniel

Classifications

• G06Q10/40

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

• H04L65/403 Primary

  Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15) · CPC title

• G06Q50/01

  Physics · mapped topic

• H04L67/306

  User profiles · CPC title

• G06F17/30

  Physics · mapped topic