# US 10,120,932 B2 · Social capture rules > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,120,932 B2 - Document ID: US10120932B2 - Status: Granted - Kind: B2 - Application number: 14/339,600 - Filed: 2014-07-24 - Published: 2016-01-28 - Granted: 2018-11-06 - Earliest claimed: 2014-07-24 - Assignees: Adobe Systems Incorporated - Applicants: Adobe Systems Incorporated - Inventors: Cory William Aitchison; Mark Lanett; Paul Jones - Web page: https://patentgrep.com/patent/US10120932B2 ## CPC - G06F 16/3329: Natural language query formulation - G06Q 10/44: Identification of trends within social networks, e.g. identification of trending topics - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - 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 ## Abstract The collection of social data from social networking services for moderation purposes is improved by analyzing social mentions captured using an initial set of capture rules. The text and/or metadata of social mentions previously captured using an initial rule set of capture rules may be analyzed to identify common text and/or common metadata amongst those social mentions. A new rule set may be generated with capture rules having criteria selected based on the identified common text and/or common metadata. The new rule set may then be applied to capture new social data. ## Claims ### Claim 1 A non-transitory computer storage medium storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform operations comprising: analyzing text and/or metadata of social mentions previously captured using an initial rule set to identify commonalities within the text and/or metadata, the social mentions having been previously captured for moderation purposes in which moderation actions are taken on certain ones of the social mentions associated with a company to manage the company's brand; selecting criteria corresponding to the commonalities identified by analyzing the text and/or metadata of the social mentions; generating an improved rule set having one or more capture rules by modifying a capture rule of the initial rule set or by adding a new capture rule to the initial rule set, the modified capture rule or added new capture rule including the criteria corresponding to the commonalities; calculating one or more accuracy metrics for the one or more capture rules, wherein the one or more accuracy metrics indicate an effectiveness of the improved rule set in capturing social mentions likely to be moderated, the effectiveness determined by identifying a percentage of previously moderated social mentions that satisfies the criteria of the improved rule set; and applying the improved rule set to capture new social mentions from one or more social networks. ### Claim 2 (depends on 1) The non-transitory computer storage medium of claim 1, wherein the text of the social mentions captured using the initial rule set is analyzed using natural language processing. ### Claim 3 (depends on 1) The non-transitory computer storage medium of claim 1, wherein the text of the social mentions captured using the initial rule set is analyzed based on a keyword specified by an initial capture rule of the initial rule set to identify one or more terms commonly used in conjunction with the keyword. ### Claim 4 (depends on 1) The non-transitory computer storage medium of claim 1, wherein the text of the social mentions captured using the initial rule set is analyzed based on a keyword specified by an initial capture rule of the initial rule set to identify one or more common topics corresponding with the keyword. ### Claim 5 (depends on 1) The non-transitory computer storage medium of claim 1, wherein generating the improved rule set comprises: generating one or more proposed capture rules for the improved rule set based on the commonalities; providing the one or more proposed capture rules for presentation to the user; receiving an acceptance of the one or more proposed capture rules from the user; and generating the improved rule set using the one or more proposed capture rules based on the acceptance. ### Claim 6 (depends on 5) The non-transitory computer storage medium of claim 5, further comprising providing the one or more accuracy metrics for presentation with the one or more proposed capture rules. ### Claim 7 (depends on 5) The non-transitory computer storage medium of claim 5, wherein generating the improved rule set further comprises receiving a user modification to at least one of the one or more proposed capture rules prior to acceptance of the one or more proposed capture rules. ### Claim 8 (depends on 1) The non-transitory computer storage medium of claim 1, further comprising: providing the criteria corresponding to the commonalities to a user; and receiving a user selection from the criteria provided to the user, wherein selecting the criteria corresponding to the commonalities identified by analyzing the text and/or metadata of the social mentions is based at least in part on the user selection. ### Claim 9 (depends on 8) The non-transitory computer storage medium of claim 8, further comprising: based selecting the criteria corresponding to the commonalities, calculating one or more accuracy metrics for the improved rule set; and receiving an acceptance of the improved rule based a least in part on the one or more accuracy metrics. ### Claim 10 A computer-implemented method comprising: analyzing, by a computing device, text and/or metadata of social mentions previously captured using an initial rule set to identify commonalities within the text and/or metadata, the social mentions having been previously captured for moderation purposes in which moderation actions are taken on certain ones of the social mentions associated with a company to manage the company's brand; determining criteria corresponding to the commonalities identified by analyzing the text and/or metadata of the social mentions; receiving a specified accuracy metric for an improved rule set, the specified accuracy metric indicating an effectiveness of the improved rule set in capturing social mentions likely to be moderated, the effectiveness determined by identifying a percentage of previously moderated social mentions that satisfies the criteria of the improved rule set; based on the specified accuracy metric, selecting criteria from the determined criteria corresponding to the commonalities; generating the improved rule set having one or more capture rules based on the initial rule set and the selected criteria, wherein the improved rule set satisfies the specified accuracy metric; and employing the improved rule set to capture new social data from one or more social networks for presentation in a moderation user interface. ### Claim 11 (depends on 10) The computer-implemented method of claim 10, wherein the text of the social mentions captured using the initial rule set is analyzed using natural language processing. ### Claim 12 (depends on 10) The computer-implemented method of claim 10, wherein the text of the social mentions captured using the initial rule set is analyzed based on a keyword specified by an initial capture rule of the initial rule set to identify one or more terms commonly used in conjunction with the keyword. ### Claim 13 (depends on 10) The computer-implemented method of claim 10, wherein the text of the social mentions captured using the initial rule set is analyzed based on a keyword specified by an initial capture rule of the initial rule set to identify one or more common topics corresponding with the keyword. ### Claim 14 (depends on 10) The computer-implemented method of claim 10, wherein the improved rule set is generated by modifying the initial rule set. ### Claim 15 (depends on 10) The computer-implemented method of claim 10, wherein the improved rule set is generated by generating a new set of one or more capture rules. ### Claim 16 (depends on 10) The computer-implemented method of claim 10, wherein generating the improved rule set comprises: generating one or more proposed capture rules for the improved rule set based on the commonalities; providing the one or more proposed capture rules for presentation to a user; receiving an acceptance of the one or more proposed capture rules from the user; and generating the improved rule set using the one or more proposed capture rules based on the acceptance. ### Claim 17 (depends on 16) The computer-implemented method of claim 16, wherein generating the improved rule set further comprises providing the one or more accuracy metrics for presentation with the one or more proposed capture rules. ### Claim 18 (depends on 16) The computer-implemented method of claim 16, wherein generating the improved rule set further comprises receiving a user modification to at least one of the one or more proposed capture rules prior to acceptance of the one or more proposed capture rules. ### Claim 19 A computerized system comprising: one or more processors; and one or more computer storage media storing computer-useable instructions that, when used by the one or more processors, cause the one or more processors to: analyze social mentions previously captured using an initial rule set to identify text in the social mentions that commonly appears in association with a keyword specified by a capture rule from the initial rule set, the social mentions having been previously captured for moderation purposes in which moderation actions are taken on certain ones of the social mentions associated with a company to manage the company's brand; select criteria based on the text identified by analyzing the social mentions; generate an improved rule set having one or more capture rules based on the initial rule set and the criteria selected based on the text, wherein the improved rule set is generated by modifying at least one rule of the initial rule set with the selected criteria; calculating one or more accuracy metrics for the one or more capture rules, wherein the one or more accuracy metrics indicate an effectiveness of the improved rule set in capturing social mentions likely to be moderated, the effectiveness determined by identifying a percentage of previously moderated social mentions that satisfies the criteria of the improved rule set; and apply the improved rule set to capture social mentions from one or more social networking services.