# US 10,482,090 B2 · Ranking and filtering comments based on feed interaction history > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,482,090 B2 - Document ID: US10482090B2 - Status: Granted - Kind: B2 - Application number: 14/942,932 - Filed: 2015-11-16 - Published: 2017-05-18 - Granted: 2019-11-19 - Earliest claimed: 2015-11-16 - Assignees: Facebook, Inc. - Applicants: Facebook, Inc. - Inventors: Allison Elaine Ball; Kaushik Mohan Iyer; Ashoat Tevosyan; Mikhail I. Okunev - Web page: https://patentgrep.com/patent/US10482090B2 ## CPC - G06F 16/24578: {using ranking} - G06F 16/248: Presentation of query results - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract In one embodiment, a method includes retrieving a set of comments associated with one or more content objects in a social-networking system, determining a score for each of the comments for a selected one of the content objects, where the score for each of the comments is based on signals associated with the comment, and the signals are related to a history of user interactions by a target user with the comments in the set, ordering the comments for the selected content object based on the respective scores, and presenting the ordered comments to the target user. The content objects may be presented in a newsfeed for the target user. The signals may be based on a history of user interactions by other users with the comments in the set, where the other users are connected to the target user in the social-networking system. ## Claims ### Claim 1 A method, comprising: by one or more computer systems, retrieving a set of comments associated with one or more content objects in a social-networking system; by the one or more computer systems, determining a score for each of the comments for a selected one of the content objects, wherein the score for each of the comments is based on one or more signals associated with the comment, and wherein the signals are related to a history of user interactions by a target user with one or more of the comments in the set, and the signals are based on likes, by one or more friends of the target user, of the comment; by the one or more computer systems, ordering the comments for the selected content object based on the respective scores; and by the one or more computer systems, presenting one or more of the ordered comments to the target user. ### Claim 2 (depends on 1) The method of claim 1, wherein the one or more content objects are presented in a newsfeed for the target user. ### Claim 3 (depends on 1) The method of claim 1, wherein the signals are based on a history of user interactions by one or more other users with one or more of the comments in the set, wherein the other users are connected to the target user in the social-networking system. ### Claim 4 (depends on 3) The method of claim 3, wherein the comments in the set comprise one or more comments made by the other users. ### Claim 5 (depends on 1) The method of claim 1, wherein the signals are based on a topic associated with the comment, wherein the topic is further associated with one or more stories previously viewed by the target user. ### Claim 6 (depends on 1) The method of claim 1, wherein the signals are based on how many times one or more friends of the target user have indicated that they like the comment. ### Claim 7 (depends on 1) The method of claim 1, wherein the user interactions by the target user with one of the comments comprise liking or commenting on the comment, or liking or commenting on the content object associated with the comment. ### Claim 8 (depends on 1) The method of claim 1, wherein the user interactions by the target user with one of the comments comprise friending another user who is related to the content object associated with the comment or to the comment. ### Claim 9 (depends on 1) The method of claim 1, wherein the user interactions by the target user with one of the comments comprise disliking or hiding the comment. ### Claim 10 (depends on 1) The method of claim 1, wherein the user interactions by the target user with one of the comments comprise disliking, hiding, or unfriending another user related to the content object associated with the comment or to the comment. ### Claim 11 (depends on 1) The method of claim 1, wherein the interactions are stored in a log of interactions associated with the target user. ### Claim 12 One or more computer-readable non-transitory storage media embodying software that is operable when executed to: retrieve a set of comments associated with one or more content objects in a social-networking system; determine a score for each of the comments for a selected one of the content objects, wherein the score for each of the comments is based on one or more signals associated with the comment, and wherein the signals are related to a history of user interactions by a target user with one or more of the comments in the set, and the signals are based on likes, by one or more friends of the target user, of the comment; order the comments for the selected content object based on the respective scores; and present one or more of the ordered comments to the target user. ### Claim 13 (depends on 12) The media of claim 12, wherein the one or more content objects are presented in a newsfeed for the target user. ### Claim 14 (depends on 12) The media of claim 12, wherein the signals are based on a history of user interactions by one or more other users with one or more of the comments in the set, wherein the other users are connected to the target user in the social-networking system. ### Claim 15 (depends on 14) The media of claim 14, wherein the comments in the set comprise one or more comments made by the other users. ### Claim 16 (depends on 12) The media of claim 12, wherein the signals are based on a topic associated with the comment, wherein the topic is further associated with one or more stories previously viewed by the target user. ### Claim 17 A system comprising; one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to: retrieve a set of comments associated with one or more content objects in a social-networking system; determine a score for each of the comments for a selected one of the content objects, wherein the score for each of the comments is based on one or more signals associated with the comment, and wherein the signals are related to a history of user interactions by a target user with one or more of the comments in the set, and the signals are based on likes, by one or more friends of the target user, of the comment; order the comments for the selected content object based on the respective scores; and present one or more of the ordered comments to the target user. ### Claim 18 (depends on 17) The system of claim 17, wherein the one or more content objects are presented in a newsfeed for the target user. ### Claim 19 (depends on 17) The system of claim 17, wherein the signals are based on a history of user interactions by one or more other users with one or more of the comments in the set, wherein the other users are connected to the target user in the social-networking system. ### Claim 20 (depends on 19) The system of claim 19, wherein the comments in the set comprise one or more comments made by the other users.