Analyzing, classifying, and restricting user-defined annotations
The present disclosure relates to systems, non-transitory computer-readable media, and methods for customizing a set of restrictions for a hashtag or other user-defined annotation that violates guidelines or rules of an online resource based on automated and manual review. In particular, in one or more embodiments, the disclosed systems trigger manual review of user-defined annotations in a social networking system, determine various metrics based on both manual and automated review of content including a particular user-defined annotation, and generate a customized set of restrictions for the user-defined annotation based on those metrics. More specifically, the system can generate and utilize various manual review metrics and a moderated media metric to generate a custom set of restrictions for a user-defined annotation.
1. A computerized method comprising:
triggering, based on user reports associated with a user-defined annotation, a manual review of media associated with the user-defined annotation via a review system, wherein the user-defined annotation comprises a hashtag;
generating, based on user interaction with content associated with the user-defined annotation, a representative set of content items associated with the user-defined annotation for presentation to an administrator device for manual review, wherein the representative set of content items comprises a plurality of content items;
generating, via the review system a review graphical user interface comprising an organization of the representative set of content items by:
determining, via the review system and from the representative set of content items, a first plurality of content items that include the user-defined annotation and have top numbers of user engagements;
determining, via the review system and from the representative set of content items, a second plurality of content items that include the user-defined annotation were posted most recently; and
providing the first plurality of content items and the second plurality of content items together with the review graphical user interface;
generating, based on the manual review of the representative set of content items associated with the user-defined annotation via the review graphical user interface, one or more manual review metrics;
analyzing media moderation associated with the user-defined annotation to determine a moderated media metric associated with the user-defined annotation; and
utilizing the one or more manual review metrics and the moderated media metric to customize a set of restrictions for the user-defined annotation.
2. The computerized method of claim 1 , wherein utilizing the one or more manual review metrics and the moderated media metric comprises comparing the one or more manual review metrics to one or more manual review thresholds and comparing the moderated media metric to a moderated media threshold.
3. The computerized method of claim 1 , wherein generating the one or more manual review metrics comprises utilizing the representative set of content items to generate at least one of a violation percentage for top media associated with the user-defined annotation, a violation percentage for recent media associated with the user-defined annotation, or an overall violation percentage for media associated with the user-defined annotation.
4. The computerized method of claim 1 , further comprising identifying, for the user-defined annotation, a classification, wherein the classification is selected from a plurality of classifications comprising a positive classification, a neutral classification, and a negative classification.
5. The computerized method of claim 4 , further comprising:
determining a prior classification associated with the user-defined annotation; and
customizing the manual review based on the prior classification.
6. The computerized method of claim 1 , wherein analyzing the media moderation comprises determining a percent of media comprising the user-defined annotation deleted for violating one or more guidelines, terms, and/or conditions of a social networking system.
7. The computerized method of claim 1 , wherein utilizing the one or more manual review metrics and the moderated media metric to select a restriction level comprises:
determining that a total violation score reflecting a total percentage of violation of the media from the manual review for the user-defined annotation is above a total violation threshold;
determining that a recent violation score reflecting a percentage of violation of recent media from the manual review for the user-defined annotation is above a recent violation threshold;
determining that the moderated media metric is above a moderated media threshold; and
selecting a block restriction for the user-defined annotation.
8. The computerized method of claim 1 , wherein utilizing the one or more manual review metrics and the moderated media metric to select a restriction level comprises:
determining that a total violation score reflecting a total percentage of violation of the media from the manual review for the user-defined annotation is above a total violation threshold;
determining that a recent violation score reflecting a percentage of violation of recent media from the manual review for the user-defined annotation is below a recent violation threshold;
determining that the moderated media metric is below a moderated media threshold; and
selecting a modified content page restriction for the user-defined annotation, wherein the modified content page restriction comprises an expiration.
9. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computer system to:
trigger, based on user reports associated with a user-defined annotation, a manual review of media associated with the user-defined annotation via a review system, wherein the user-defined annotation comprises a hashtag;
generate, based on user interaction with content associated with the user-defined annotation, a representative set of content items associated with the user-defined annotation for presentation to an administrator device for manual review, wherein the representative set of content items comprises a plurality of content items;
generate, via the review system a review graphical user interface comprising an organization of the representative set of content items by:
determine, via the review system and from the representative set of content items, a first plurality of content items that include the user-defined annotation and have top numbers of user engagements;
determine, via the review system and from the representative set of content items, a second plurality of content items that include the user-defined annotation were posted most recently; and
provide the first plurality of content items and the second plurality of content items together with the review graphical user interface;
generate, based on the manual review of the representative set of content items associated with the user-defined annotation via the review graphical user interface, one or more manual review metrics;
analyze media moderation associated with the user-defined annotation to determine a moderated media metric associated with the user-defined annotation; and
utilize the one or more manual review metrics and the moderated media metric to customize a set of restrictions for the user-defined annotation.
10. The computer-readable medium of claim 9 , wherein utilizing the one or more manual review metrics and the moderated media metric comprises comparing the one or more manual review metrics to one or more manual review thresholds and comparing the moderated media metric to a moderated media threshold.
11. The computer-readable medium of claim 9 , wherein generating the one or more manual review metrics comprises utilizing the representative set of content items to generate at least one of a violation percentage for top media associated with the user-defined annotation, a violation percentage for recent media associated with the user-defined annotation, or an overall violation percentage for media associated with the user-defined annotation.
12. The computer-readable medium of claim 9 , further comprising instructions that, when executed by the at least one processor, cause the computer system to identify, for the user-defined annotation, a classification, wherein the classification is selected from a plurality of classifications comprising a positive classification, a neutral classification, and a negative classification.
13. The computer-readable medium of claim 9 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:
determine a prior classification associated with the user-defined annotation; and
customize a manual review based on the prior classification.
14. The computer-readable medium of claim 9 , wherein analyzing the media moderation comprises determining a percent of media comprising the user-defined annotation deleted for violating one or more guidelines, terms, and/or conditions of a social networking system.
15. A system comprising:
at least one processor; and
at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to:
trigger, based on user reports associated with a user-defined annotation, a manual review of media associated with the user-defined annotation via a review system, wherein the user-defined annotation comprises a hashtag;
generate, based on user interaction with content associated with the user-defined annotation, a representative set of content items associated with the user-defined annotation for presentation to an administrator device for manual review, wherein the representative set of content items comprises a plurality of content items;
generate, via the review system a review graphical user interface comprising an organization of the representative set of content items by:
determine, via the review system and from the representative set of content items, a first plurality of content items that include the user-defined annotation and have top numbers of user engagements;
determine, via the review system and from the representative set of content items, a second plurality of content items that include the user-defined annotation were posted most recently; and
provide the first plurality of content items and the second plurality of content items together with the review graphical user interface;
generate, based on the manual review of the representative set of content items associated with the user-defined annotation via the review graphical user interface, one or more manual review metrics;
analyze media moderation associated with the user-defined annotation to determine a moderated media metric associated with the user-defined annotation; and
utilize the one or more manual review metrics and the moderated media metric to customize a set of restrictions for the user-defined annotation.
16. The system of claim 15 , wherein utilizing the one or more manual review metrics and the moderated media metric comprises comparing the one or more manual review metrics to one or more manual review thresholds and comparing the moderated media metric to a moderated media threshold.
17. The system of claim 15 , wherein generating the one or more manual review metrics comprises utilizing the representative set of content items to generate at least one of a violation percentage for top media associated with the user-defined annotation, a violation percentage for recent media associated with the user-defined annotation, or an overall violation percentage for media associated with the user-defined annotation.
18. The system of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to identify, for the user-defined annotation, a classification, wherein the classification is selected from a plurality of classifications comprising a positive classification, a neutral classification, and a negative classification.
19. The system of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to:
determine a prior classification associated with the user-defined annotation; and
customize the manual review based on the prior classification.
20. The system of claim 15 , wherein analyzing the media moderation comprises determining a percent of media comprising the user-defined annotation deleted for violating one or more guidelines, terms, and/or conditions of a social networking system.