System and Method for Detecting Misinformation and Fake News via Network Analysis

Abstract

A method for detection of misinformation (HINTS) without the need to analyze any articles that includes forming a mixed graph containing at least two different node types, such as users and articles with edges between users and articles with user weights for user nodes and article weights for article nodes. Seed nodes are planted at least one user node and at least one article node. User weights and article weights are manually assigned to the seed nodes, then neighborhoods are defined for the seed nodes. A HITS-like algorithm is then run for a predetermined number of rounds updating both people and articles while keeping the weights of the seed nodes constant to converge the graph for the weights of articles and users. Finally, a set of highest weights for users and/or articles is outputted and possible remedial action can be taken.

1 . A method for detection of misinformation without need to analyze articles comprising:
 forming a mixed graph containing at least two different node types, users and articles with edges between users and articles, with user weights for user nodes and article weights for article nodes;   planting at least one seed user node and at least one seed article node into said mixed graph;   manually assigning user weights and article weights to the seed nodes;   defining neighborhoods of the seed nodes;   running a HITS-like algorithm for a predetermined number of rounds updating both people and articles while keeping the weights of the seed nodes constant to converge the mixed graph for the weights of articles and users;   outputting a set of highest weights for users and/or articles.   
     
     
         2 . The method of  claim 1  further comprising updating a first side of the mixed graph faster than a second side of the mixed graph. 
     
     
         3 . The method of  claim 2  wherein the first side of the mixed graph is articles, and the second side of the mixed graph is users. 
     
     
         4 . The method of  claim 1  wherein user weights are only updated when a new user appears. 
     
     
         5 . The method of  claim 1  wherein no article is analyzed. 
     
     
         6 . The method of  claim 1  wherein user weights are determined by comparison with a control group. 
     
     
         7 . The method of  claim 1  wherein article weights are determined by user input. 
     
     
         8 . The method of  claim 1  wherein propagation is stopped based on interaction with specific predetermined users. 
     
     
         9 . The method of  claim 1  further comprising assigning negative links between users and articles that represent a lack of an expected association between a particular user and a particular article. 
     
     
         10 . The method of  claim 1  further comprising normalization and fixed values in the mixed graph taken from manual input. 
     
     
         11 . The method of  claim 1  wherein the mixed graph has more than two node types. 
     
     
         12 . The method of  claim 1  further comprising using implicit human interactions to propagate labels. 
     
     
         13 . The method of  claim 1  further comprising aggregation of inputs from multiple users to generate labels. 
     
     
         14 . The method of  claim 13  wherein the labels are aggregated non linearly. 
     
     
         15 . The method of clam  13  wherein the labels are of trustworthiness metrics. 
     
     
         16 . The A method of  claim 1 ,
 wherein articles may be updated more often than users.   
     
     
         17 . (canceled) 
     
     
         18 . (canceled) 
     
     
         19 . (canceled) 
     
     
         20 . (canceled) 
     
     
         21 . (canceled) 
     
     
         22 . A method for detection of misinformation comprising using non-intentional human interactions to rate content for a property of interest. 
     
     
         23 . (canceled) 
     
     
         24 . The method of  claim 22  wherein the interactions are in a graph. 
     
     
         25 . The method of  claim 22  wherein multiple people are utilized to get a ranking. 
     
     
         26 . (canceled) 
     
     
         27 . (canceled) 
     
     
         28 . (canceled) 
     
     
         29 . (canceled) 
     
     
         30 . (canceled) 
     
     
         31 . (canceled) 
     
     
         32 . (canceled) 
     
     
         33 . (canceled) 
     
     
         34 . (canceled) 
     
     
         35 . (canceled) 
     
     
         36 . (canceled) 
     
     
         37 . (canceled) 
     
     
         38 . (canceled) 
     
     
         39 . (canceled) 
     
     
         40 . (canceled) 
     
     
         41 . (canceled) 
     
     
         42 . A computer program product comprising a non-transitory computer readable medium:
   a first computer instruction forming a mixed graph containing at least two different node types, users and articles with edges between users and articles, with user weights for user nodes and article weights for article nodes;   a second computer instruction planting at least one seed user node and at least one seed article node into said mixed graph;   a third computer instruction manually assigning user weights and article weights to the seed nodes;   a fourth computer instruction defining neighborhoods of the seed nodes;   a fifth computer instruction running a HITS-like algorithm for a predetermined number of rounds updating both people and articles while keeping the weights of the seed nodes constant to converge the mixed graph for the weights of articles and users;   a sixth computer instruction outputting a set of highest weights for users and/or articles;     wherein, said first, second, third, fourth, fifth and sixth program instructions are stored on said non-transitory computer readable medium and executed on a computing device.