# US 2020/0401635 A1 · Analyzing, classifying, and restricting user-defined annotations > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0401635 A1 - Document ID: US20200401635A1 - Status: Published application - Kind: A1 - Application number: 16/813,463 - Filed: 2020-03-09 - Published: 2020-12-24 - Earliest claimed: 2019-06-24 - Assignees: Facebook, Inc. - Applicants: Facebook, Inc. - Inventors: Nikhil Singhal; Roy Koonammave Jose; Anders Skog; Leonard Chang - Web page: https://patentgrep.com/patent/US20200401635A1 ## CPC - G06Q 10/40: Business processes related to social networking or social networking services - G06F 16/48: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually - G06F 16/958: Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking - G06F 18/24: Classification techniques - G06F 40/169: Annotation, e.g. comment data or footnotes - G06Q 10/44: Identification of trends within social networks, e.g. identification of trending topics - G06V 10/7788: {the supervisor being a human, e.g. interactive learning with a human teacher} - G06V 20/30: in albums, collections or shared content, e.g. social network photos or video - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract 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. ## Claims ### Claim 1 A method comprising: triggering, based on information associated with a user-defined annotation, a manual review of media associated with the user-defined annotation; generating, based on the manual review of the media associated with the user-defined annotation, 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 manual review metrics and the moderated media metric to customize a set of restrictions for the user-defined annotation. ### Claim 2 (depends on 1) The method of claim 1, wherein utilizing the manual review metrics and the moderated media metric comprises comparing the manual review metrics to one or more manual review thresholds and comparing the moderated media metric to a moderated media threshold. ### Claim 3 (depends on 1) The method of claim 1, wherein generating the one or more manual review metrics comprises generating 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. ### Claim 4 (depends on 1) The 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. ### Claim 5 (depends on 4) The method of claim 4, further comprising: determining a prior classification associated with the user-defined annotation; and customizing a manual review based on the prior classification. ### Claim 6 (depends on 1) The 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. ### Claim 7 (depends on 1) The method of claim 1, wherein utilizing the manual review metrics and the moderated media metric to select a restriction level comprises: determining that a total violation score for the user-defined annotation is above a total violation threshold; determining that a recent violation score 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. ### Claim 8 (depends on 1) The method of claim 1, wherein utilizing the manual review metrics and the moderated media metric to select a restriction level comprises: determining that a total violation score for the user-defined annotation is above a total violation threshold; determining that a recent violation score for the user-defined annotation is below a recent violation threshold; determining that the moderated media metric is below a moderated media threshold; and based on the plurality of determinations, selecting a modified content page restriction for the user-defined annotation, wherein the modified content page restriction comprises an expiration. ### Claim 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 information associated with a user-defined annotation, a manual review of media associated with the user-defined annotation; generate, based on the manual review of the media associated with the user-defined annotation, 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 manual review metrics and the moderated media metric to customize a set of restrictions for the user-defined annotation. ### Claim 10 (depends on 9) The computer-readable medium of claim 9, wherein utilizing the manual review metrics and the moderated media metric comprises comparing the manual review metrics to one or more manual review thresholds and comparing the moderated media metric to a moderated media threshold. ### Claim 11 (depends on 9) The computer-readable medium of claim 9, wherein generating the one or more manual review metrics comprises generating 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. ### Claim 12 (depends on 9) 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. ### Claim 13 (depends on 9) 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. ### Claim 14 (depends on 9) 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. ### Claim 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 information associated with a user-defined annotation, a manual review of media associated with the user-defined annotation; generate, based on the manual review of the media associated with the user-defined annotation, 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 manual review metrics and the moderated media metric to customize a set of restrictions for the user-defined annotation. ### Claim 16 (depends on 15) The system of claim 15, wherein utilizing the manual review metrics and the moderated media metric comprises comparing the manual review metrics to one or more manual review thresholds and comparing the moderated media metric to a moderated media threshold. ### Claim 17 (depends on 15) The system of claim 15, wherein generating the one or more manual review metrics comprises generating 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. ### Claim 18 (depends on 15) 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. ### Claim 19 (depends on 15) 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 a manual review based on the prior classification. ### Claim 20 (depends on 15) 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.