Sentiment polarity for users of a social networking system

Abstract

A social networking system infers a sentiment polarity of a user toward content of a page. The sentiment polarity of the user is inferred based on received information about an interaction between the user and the page (e.g., like, report, etc.), and may be based on analysis of a topic extracted from text on the page. The system infers a positive or negative sentiment polarity of the user toward the content of the page, and that sentiment polarity then may be associated with any second or subsequent interaction from the user related to the page content. The system may identify a set of trusted users with strong sentiment polarities toward the content of a page or topic, and may use the trusted user data as training data for a machine learning model, which can be used to more accurately infer sentiment polarity of users as new data is received.

1 - 25 . (canceled) 
     
     
         26 . A system, comprising:
 a processor; and   a memory storing instructions, which when executed by the processor, causes the processor to:
 identify a topic from digital content of a page; 
 determine a sentiment of a user toward the digital content of the page based on information about a first interaction between the user and the page; 
 determine that the user has a sentiment polarity toward the topic based on the information about the first interaction, wherein the sentiment polarity is indicative of a positive or negative sentiment of the user toward the topic; and 
 using the sentiment polarity to identify additional digital content to present to the user or other users associated with the user. 
   
     
     
         27 . The system of  claim 26 , wherein the processor is further caused to:
 store, in a data store, the sentiment polarity of the user toward the topic based on the second sentiment.   
     
     
         28 . The system of  claim 26 , wherein the processor is further caused to:
 determine a second sentiment of the user toward digital content based on information about a second interaction between the user and the page; and   update the sentiment polarity of the user toward the topic based on the second sentiment.   
     
     
         29 . The system of  claim 26 , wherein the digital content comprises at least one of textual content, visual content, or audio content. 
     
     
         30 . The system of  claim 26 , wherein the digital content comprises at least one of a post or a comment. 
     
     
         31 . The system of  claim 26 , wherein the topic is extracted from the text content using at least one of computer vision, natural language processing (NLP), or lexicon-based analysis. 
     
     
         32 . The system of  claim 26 , wherein the processor is further caused to:
 determine sentiments of other users toward digital content based on information about other interactions between the other users and the page, the other users associated with the user; and   update the sentiment polarity of the user toward the topic based on the sentiments of the other users toward the digital content.   
     
     
         33 . The system of  claim 26 , wherein the processor is further caused to:
 add the sentiment polarity to an insight page, the insight page comprising:
 statistical analytics on the page; and 
 insight for predicting future trends of the user or other users based on the statistical analytics. 
   
     
     
         34 . The system of  claim 33 , wherein the processor is further caused to:
 identifying a consistent trend of the user's sentiment polarity toward the content of the page based on the insight page;   determining whether the sentiment polarity follows the consistent trend; and   identifying that the sentiment polarity is:
 a correct entry in the event it is determined that the sentiment polarity follows the consistent trend; 
 an aberrant entry in the event it is determined that the sentiment polarity does not follow the consistent trend; and 
 a correct entry in the event it is determined that the sentiment polarity does not follow the consistent trend based on a determination that the user's sentiment has switched from a positive sentiment polarity to a negative sentiment polarity or a negative sentiment polarity to a positive sentiment polarity. 
   
     
     
         35 . A method, comprising:
 identifying, by a processor of a computing device, a topic from digital content of a page;   determine a sentiment of a user toward the digital content of the page based on information about a first interaction between the user and the page;   determine that the user has a sentiment polarity toward the topic based on the information about the first interaction, wherein the sentiment polarity is indicative of a positive or negative sentiment of the user toward the topic; and   using the sentiment polarity to identify additional digital content to present to the user or other users associated with the user.   
     
     
         36 . The method of  claim 35 , further comprising:
 storing, in a data store, the sentiment polarity of the user toward the topic based on the second sentiment.   
     
     
         37 . The method of  claim 35 , further comprising:
 determining a second sentiment of the user toward digital content based on information about a second interaction between the user and the page; and   updating the sentiment polarity of the user toward the topic based on the second sentiment.   
     
     
         38 . The method of  claim 35 , wherein the digital content comprises at least one of textual content, visual content, or audio content. 
     
     
         39 . The method of  claim 35 , wherein the digital content comprises at least one of a post or a comment. 
     
     
         40 . The method of  claim 35 , wherein the topic is extracted from the text content using at least one of computer vision, natural language processing (NLP), or lexicon-based analysis. 
     
     
         41 . The method of  claim 35 , further comprising:
 determining sentiments of other users toward digital content based on information about other interactions between the other users and the page, the other users associated with the user; and   updating the sentiment polarity of the user toward the topic based on the sentiments of the other users toward the digital content.   
     
     
         42 . The method of  claim 35 , further comprising:
 adding the sentiment polarity to an insight page, the insight page comprising:
 statistical analytics on the page; and 
 insight for predicting future trends of the user or other users based on the statistical analytics. 
   
     
     
         43 . The method of  claim 42 , further comprising:
 identifying a consistent trend of the user's sentiment polarity toward the content of the page based on the insight page;   determining whether the sentiment polarity follows the consistent trend; and   identifying that the sentiment polarity is:
 a correct entry in the event it is determined that the sentiment polarity follows the consistent trend; 
 an aberrant entry in the event it is determined that the sentiment polarity does not follow the consistent trend; and 
 a correct entry in the event it is determined that the sentiment polarity does not follow the consistent trend based on a determination that the user's sentiment has switched from a positive sentiment polarity to a negative sentiment polarity or a negative sentiment polarity to a positive sentiment polarity. 
   
     
     
         44 . A non-transitory computer-readable storage medium having an executable stored thereon, which when executed, instructs a processor to:
 identify a topic from digital content of a page;   determine a sentiment of a user toward the digital content of the page based on information about a first interaction between the user and the page;   determine that the user has a sentiment polarity toward the topic based on the information about the first interaction, wherein the sentiment polarity is indicative of a positive or negative sentiment of the user toward the topic; and   using the sentiment polarity to identify additional digital content to present to the user or other users associated with the user.   
     
     
         45 . The non-transitory computer-readable storage medium of  claim 44 , further comprising:
 determining a second sentiment of the user toward digital content based on information about a second interaction between the user and the page;   updating the sentiment polarity of the user toward the topic based on the second sentiment;   determining sentiments of other users toward digital content based on information about other interactions between the other users and the page, the other users associated with the user; and   
       updating the sentiment polarity of the user toward the topic based on the sentiments of the other users toward the digital content.