# US 10,482,117 B2 · Systems and methods for categorizing and moderating user-generated content in an online environment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,482,117 B2 - Document ID: US10482117B2 - Status: Granted - Kind: B2 - Application number: 15/791,099 - Filed: 2017-10-23 - Published: 2018-03-22 - Granted: 2019-11-19 - Earliest claimed: 2011-05-20 - Assignees: Oath Inc. - Applicants: Oath Inc. - Inventors: Jeffrey Revesz; Christopher Wiggins - Web page: https://patentgrep.com/patent/US10482117B2 ## CPC - G06F 16/353: into predefined classes - G06F 16/951: Indexing; Web crawling techniques - H04L 51/212: using filtering or selective blocking - H04L 51/52: for supporting social networking services - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Exemplary embodiments provide systems, devices and methods for computer-based categorization and moderation of user-generated content for publication of the content in an online environment. Exemplary embodiments automatically determine a probability value indicating that the user-generated content is either a positive example or a negative example of one or more unsuitable categories. If the user-generated content is determined to be a positive example of any of the unsuitable categories to a predefined degree of certainty, exemplary embodiments may automatically exclude the content from publication in the online environment. ## Claims ### Claim 1 An apparatus, comprising: a storage device that stores a set of instructions; and at least one processor coupled to the storage device and configured to execute the set of instructions to: receive, over a network, at least a portion of textual data input from a user interface; compute a numeric likelihood that the received portion of textual data falls into a category unsuitable for publication on a web page; determine whether to electronically publish the received portion of textual data on the web page based on a comparison of the computed numeric likelihood to a threshold value associated with the category, wherein the threshold value includes a numeric likelihood assigned to reference content suitable for publication on the web page and the comparison comprises determining whether the computed numeric likelihood exceeds the threshold value; and generate an electronic command to publish the textual data on the web page, when the computed numeric likelihood is determined not to exceed the threshold value. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein the received textual data is generated by a user, and the at least one processor is further operative with the set of instructions to assign, to the user, a value indicative of a capability of the user to generate content suitable for publication on the web page. ### Claim 3 (depends on 2) The apparatus of claim 2, wherein the at least one processor is further operative with the set of instructions to establish that the textual data is unsuitable for publication on the web page based on the assigned value indicative of a capability of the user to generate content suitable for publication on the web page. ### Claim 4 (depends on 1) The apparatus of claim 1, wherein the at least one processor is further operative with the set of instructions to, when the computed numeric likelihood is determined to exceed the threshold value, determine whether the computed numeric likelihood exceeds an additional threshold value. ### Claim 5 (depends on 4) The apparatus of claim 4, wherein the at least one processor is further operative with the set of instructions to establish that the textual data is unsuitable for publication on the web page, when the computed numeric likelihood is determined to exceed the additional threshold value. ### Claim 6 (depends on 1) The apparatus of claim 1, wherein the at least one processor is further operative with the set of instructions to: parse the textual data into a plurality of n-grams; and compute the numeric likelihood based on an application of a machine-learning algorithm to the plurality of n-grams. ### Claim 7 (depends on 1) The apparatus of claim 1, wherein: the textual data comprises a comment generated by a user for publication on the web page. ### Claim 8 A computer-implemented method, comprising: receiving, over a network, at least a portion of textual data input from a user interface; computing, using at least one processor, a numeric likelihood that textual data falls into a category unsuitable for publication on a web page; determining, using the at least one processor, whether to electronically publish the received portion of textual data on the web page based on a comparison of the computed numeric likelihood to a threshold value associated with the category, wherein the threshold value includes a numeric likelihood assigned to reference content suitable for publication on the web page and the comparison comprises determining whether the computed numeric likelihood exceeds the threshold value; and generating an electronic command to publish the textual data on the web page, when the computed numeric likelihood is determined not to exceed the threshold value. ### Claim 9 (depends on 8) The method of claim 8, wherein the received textual data is generated by a user, and the method further comprises assigning, to the user, a value indicative of a capability of the user to generate content suitable for publication on the web page. ### Claim 10 (depends on 9) The method of claim 9, further comprising: establishing that the textual data is unsuitable for publication on the web page based on the assigned value indicative of a capability of the user to generate content suitable for publication on the web page. ### Claim 11 (depends on 8) The method of claim 8, further comprising, when the computed numeric likelihood is determined to exceed the threshold value, determining whether the computed numeric likelihood exceeds an additional threshold value. ### Claim 12 (depends on 11) The method of claim 11, further comprising establishing that the textual data is unsuitable for publication on the web page, when the computed numeric likelihood is determined to exceed the additional threshold value. ### Claim 13 (depends on 8) The method of claim 8, further comprising: parsing the textual data into a plurality of n-grams; and computing the numeric likelihood based on an application of a machine-learning algorithm to the plurality of n-grams. ### Claim 14 (depends on 8) The method of claim 8, wherein: the textual data comprises a comment generated by a user for publication on the web page. ### Claim 15 A tangible, non-transitory computer-readable medium that stores a set of instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising: receiving, over a network, at least a portion of textual data input from a user interface; computing, using at least one processor, a numeric likelihood that textual data falls into a category unsuitable for publication on a web page; determining, using the at least one processor, whether to electronically publish the received portion of textual data on the web page based on a comparison of the computed numeric likelihood to a threshold value associated with the category, wherein the threshold value includes a numeric likelihood assigned to reference content suitable for publication on the web page and the comparison comprises determining whether the computed numeric likelihood exceeds the threshold value; and generating an electronic command to publish the textual data on the web page, when the computed numeric likelihood is determined not to exceed the threshold value. ### Claim 16 (depends on 15) The computer-readable medium of claim 15, wherein the received textual data is generated by a user, and the set of instructions further cause the at least one processor to assign, to the user, a value indicative of a capability of the user to generate content suitable for publication on the web pager. ### Claim 17 (depends on 16) The computer-readable medium of claim 16, wherein the set of instructions further cause the at least one processor to: establish that the textual data is unsuitable for publication on the web page based on the assigned value indicative of a capability of the user to generate content suitable for publication on the web page. ### Claim 18 (depends on 15) The computer-readable medium of claim 15, further comprising, when the computed numeric likelihood is determined to exceed the threshold value, determining whether the computed numeric likelihood exceeds an additional threshold value. ### Claim 19 (depends on 18) The computer-readable medium of claim 18, further comprising establishing that the textual data is unsuitable for publication on the web page, when the computed numeric likelihood is determined to exceed the additional threshold value. ### Claim 20 (depends on 15) The computer-readable medium of claim 15, further comprising: parsing the textual data into a plurality of n-grams; and computing the numeric likelihood based on an application of a machine-learning algorithm to the plurality of n-grams.