Systems and methods for demotion of content items in a feed

Abstract

Systems, methods, and non-transitory computer readable media configured to determine a value associated with at least one signal indicative of objectionable material in a content item. The value associated with the at least one signal indicative of objectionable material can be compared with a threshold value associated with the at least one signal. A demotion value can be determined in response to satisfaction of the threshold value associated with the at least one signal.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 determining, by a computing system, a demotion value associated with a likelihood that a content item contains objectionable material based on responses to the content item that include one or more of predetermined keywords;   reducing, by the computing system, the demotion value to generate a reduced demotion value based on a determination that the content item contains one or more of the predetermined keywords; and   adjusting, by the computing system, a rank value associated with presentation of the content item in a news feed based on the reduced demotion value.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the predetermined keywords comprise at least one of “fake”, “hoax”, “scam”, or “fraud”. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the reduced demotion value has a value less than the demotion value or a value of zero. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein the content item is identified as legitimate. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein a user with access to the content item has a subscription to a domain that provided the content item, and the demotion value is reduced based further on the subscription. 
     
     
         6 . The computer-implemented method of  claim 1 , wherein the content item comprises at least one of text, an image, a video, or audio. 
     
     
         7 . The computer-implemented method of  claim 1 , further comprising determining a value based on a number of the responses to the content item that include one or more of predetermined keywords with a threshold value. 
     
     
         8 . The computer-implemented method of  claim 7 , wherein the demotion value is determined in response to satisfaction of the threshold value by the value. 
     
     
         9 . The computer-implemented method of  claim 8 , wherein the demotion value is proportional to the value. 
     
     
         10 . The computer-implemented method of  claim 1 , wherein the responses to the content item comprise a comment posted in response to the content item. 
     
     
         11 . A system comprising:
 at least one processor; and   a memory storing instructions that, when executed by the at least one processor, cause the system to perform:   determining a demotion value associated with a likelihood that a content item contains objectionable material based on responses to the content item that include one or more of predetermined keywords;   reducing the demotion value to generate a reduced demotion value based on a determination that the content item contains one or more of the predetermined keywords; and   adjusting a rank value associated with presentation of the content item in a news feed based on the reduced demotion value.   
     
     
         12 . The system of  claim 11 , wherein the predetermined keywords comprise at least one of “fake”, “hoax”, “scam”, or “fraud”. 
     
     
         13 . The system of  claim 11 , wherein the reduced demotion value has a value less than the demotion value or a value of zero. 
     
     
         14 . The system of  claim 11 , wherein the content item is identified as legitimate. 
     
     
         15 . The system of  claim 11 , wherein a user with access to the content item has a subscription to a domain that provided the content item, and the demotion value is reduced based further on the subscription. 
     
     
         16 . A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
 determining a demotion value associated with a likelihood that a content item contains objectionable material based on responses to the content item that include one or more of predetermined keywords;   reducing the demotion value to generate a reduced demotion value based on a determination that the content item contains one or more of the predetermined keywords; and   adjusting a rank value associated with presentation of the content item in a news feed based on the reduced demotion value.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 16 , wherein the predetermined keywords comprise at least one of “fake”, “hoax”, “scam”, or “fraud”. 
     
     
         18 . The non-transitory computer-readable storage medium of  claim 16 , wherein the reduced demotion value has a value less than the demotion value or a value of zero. 
     
     
         19 . The non-transitory computer-readable storage medium of  claim 16 , wherein the content item is identified as legitimate. 
     
     
         20 . The non-transitory computer-readable storage medium of  claim 16 , wherein a user with access to the content item has a subscription to a domain that provided the content item, and the demotion value is reduced based further on the subscription.