Analyzing quality of applications linked to an online system

Patent metadata

Field	Value
Publication number	US-10083401-B2
Application number	US-201715406521-A
Country	US
Kind code	B2
Filing date	Jan 13, 2017
Priority date	Dec 11, 2014
Publication date	Sep 25, 2018
Grant date	Sep 25, 2018

Abstract

An online system extracts features from an application linked to the online system. The application is used by users of the online system and posts content to the online system. A trained model is applied to the extracted features to generate a quality score for the application. The trained model is trained using features extracted from a set of training applications and quality scores manually assigned to the training applications, wherein the manually assigned quality scores indicate whether each training application satisfies a set of criteria and the generated quality score represents a probability of the application satisfying the set of criteria. Based on the quality score, content provided by the application is ranked for presentation to a user of the online system in relation to other content of the online system. The online system presents the content provided by the application to the user according to the ranking.

First claim

What is claimed is:

1. A method comprising:
extracting, by a social networking system, features from an application of a plurality of applications linked to the social networking system, the plurality of applications operate independently of and external to the social networking system, are used by users of the social networking system, are configured to post content to the social networking system on behalf of the users of the social networking system, and each correspond to software that can be installed on a client device of a user of the social networking system that uses data from the social networking system to provide at least one of a service or functionality to the user;
identifying, by the social networking system, a set of features from a set of training applications from the plurality of applications, a quality score is manually assigned to each application of the set of training applications and indicating whether each training application satisfies one or more of a set of criteria;
comparing, by the social networking system, the features extracted from the application to the identified set of features from the set of training applications; and
generating, by the social networking system, an application quality score for the application based on a degree of similarity of the features extracted from the application to the identified set of features from the set of training applications and the quality scores assigned to the set of training applications, the generated application quality score representing a probability of the application satisfying the set of criteria.

2. The method of claim 1 , further comprising:
ranking for presentation to a user of the social networking system, content provided by the application in relation to other content of the social networking system based on the generated quality score;
generating a quality score for each of a plurality of other applications linked to the social networking system; and
ranking the content provided by the application in relation to content provided by the plurality of other applications based on the quality score of the application and the quality scores of each of the plurality of other applications.

3. The method of claim 2 , further comprising:
presenting one or more of the application and the plurality of other applications as a recommendation to the user of the social networking system.

4. The method of claim 2 , further comprising:
selecting a threshold number of the plurality of other applications to appear an application center or application store featured in the social networking system.

5. The method of claim 1 , further comprising:
responsive to the quality score for the application being below a threshold score, identifying the application for policy compliance review, the quality score for the application being below the threshold score indicating a violation of one or more policies of the social networking system.

6. The method of claim 1 , further comprising:
ranking for presentation to a user of the social networking system, content provided by the application in relation to other content of the social networking system based on the generated quality score; and
presenting the content provided by the application to the user of the social networking system according to the ranking as one or more stories in a newsfeed.

7. The method of claim 6 , wherein presenting the content as one or more stories in the newsfeed comprises:
presenting the one or more stories at a lower position in the newsfeed relative to stories associated with the other content of the social networking system responsive to the quality score being below a threshold.

8. The method of claim 6 , wherein presenting the content as one or more stories in the newsfeed comprises:
responsive to the quality score being below a threshold, presenting the one or more stories less frequently in the newsfeed than stories associated with the other content of the social networking system.

9. The method of claim 1 , wherein the extracted features comprise one or more of user feedback on the application, usage of the application, business value of the application, and configuration of the application.

10. The method of claim 1 , wherein the manually assigned quality scores are binary scores assigned to the applications in the training set, and wherein a high quality score is assigned to a training application satisfying the set of criteria and a low quality score is assigned to a training application not satisfying one or more of the criteria.

11. A method comprising:
extracting, by a social networking system, features from an application linked to the social networking system, the application operates independently of and external to the social networking system, is used by users of the social networking system, and is configured to post content to the social networking system on behalf of the users of the social networking system, and each correspond to software that can be installed on a client device of a user of the social networking system that uses data from the social networking system to provide at least one of a service or functionality to the user;
applying, by the social networking system, a trained model to the extracted features of the application to generate a quality score for the application, the trained model being generated by:
manually assigning quality scores to each of a set of training applications, the manually assigned quality scores indicating whether each training application satisfies one or more of a set of criteria; and

generating an application quality score for the application based on a degree of similarity of the features extracted from the application to a set of features from the set of training applications and the quality scores assigned to the set of training applications, the generated application quality score representing a probability of the application satisfying the set of criteria.

12. The method of claim 11 , further comprising:
ranking for presentation to a user of the social networking system, content provided by the application in relation to other content of the social networking system based on the generated quality score;
generating a quality score for each of a plurality of other applications linked to the social networking system; and
ranking the content provided by the application in relation to content provided by the plurality of other applications based on the quality score of the application and the quality scores of each of the plurality of other applications.

13. The method of claim 12 , further comprising:
presenting one or more of the application and the plurality of other applications as a recommendation to the user of the social networking system.

14. The method of claim 12 , further comprising:
selecting a threshold number of the plurality of other applications to appear in an application center or application store featured in the social networking system.

15. A non-transitory computer-readable storage medium including instructions that, when executed by a processor, cause the processor to:
extract features from an application of a plurality of applications linked to a social networking system, the plurality of applications operate independently of and external to the social networking system, are used by users of the social networking system, are configured to post content to the social networking system on behalf of the users of the social networking system, and each correspond to software that can be installed on a client device of a user of the social networking system that uses data

Assignees

• Facebook Inc

Inventors

• Gross Jonathan J
• Liao Yihua
• Krivoshein Joshua Luke
• Bickert Monika Leigh
• Zarakhovsky Eugene

Classifications

• G06Q10/40

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

• G06N7/01 Primary

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• H04L67/306

  User profiles · CPC title

• H04L67/22

  Electricity · mapped topic

• G06N7/005 Primary

  Physics · mapped topic