The fake news detection system developed in this paper, TriFN considers tri-relationships between news pieces, publishers, and social network users.
… we are to our best knowledge the first to classify fake news by learning the effective news features through the tri-relationship embedding among publishers, news contents, and social engagements.
And guess what, considering publishers and users does indeed turn out to improve fake news detection! We have publishers, social network users, and news articles.
Using a vocabulary of t words, we can compute an bag-of-word feature matrix.
For the m users, we can have an m x m adjacency matrix , where is 1 if i and j are friends, and 0 otherwise.
We also know which users have shared which news pieces, this is encoded in a matrix .
The matrix similarly encodes which publishers have published which news pieces.
For some publishers, we can know their partisan bias.
In this work, bias ratings from mediabiasfactcheck.
com are used, taking just the ‘Left-Bias’, ‘Least-Bias’ (neutral) and ‘Right-Bias’ values (ignoring the intermediate left-center and right-center values) and encoding these as -1, 0, and 1 respectively in a publisher partisan label vector, .
Not every publisher will have a bias rating available.
We’d like to put ‘-’ in the entry for that publisher in but since we can’t do that, the separate vector encodes whether or not we have a bias rating available for publisher p.
There’s one last thing at our disposal: a labelled dataset for news articles telling us whether they are fake or not.
(Here we have just the news article content, not the social context).
TriFN takes all of those inputs and combines them with a fake news binary classifier.
Given lots of users and lots of news articles, we can expect some of the raw inputs to be pretty big, so the authors make heavy use of dimensionality reduction using non-negative matrix factorisation to learn latent space embeddings (more on that in a minute!) TriFN combines:Pictorially it looks like this (with apologies for the poor resolution, which is an artefact of the original):News content embeddingLet’s take a closer look at non-negative matrix factorisation (NMF) to see how this works to reduce dimensionality.
Remember the bag-of-words sketch for news articles?.That’s an n x t matrix where n is the number of news articles and t is the number of words in the vocabulary.
NMF tries to learn a latent embedding that captures the information in the matrix in a much smaller space.
In the general form NMF seeks to factor a (non-negative) matrix M into the product of two (non-negative) matrices W and H (or D and V as used in this paper).
How does that help us?.We can pick some dimension d (controlling the size of the latent space) and break down the matrix into a d-dimension representation of news articles , and a d-dimension representation of words in the vocabulary, .
That means that has shape and so ends up with the desired shape .
Once we’ve learned a good representation of news articles, we can use those as the news content embeddings within TriFN.
We’d like to get as close to as we can, and at the same time keep and ‘sensible’ to avoid over-fitting.
We can do that with a regularisation term.
So the overall optimisation problem looks like this:User embeddingFor the user embedding there’s a similar application of NMF, but in this case we’re splitting the adjacency matrix into a user latent matrix , and a user correlation matrix .
So in this case we’re using NMF to learn which has shape mxd .
dxd .
dxm, resulting in the desired mxm shape.
There’s also a user-user relation matrix which controls the contribution of .
The basic idea is that any given user will only share a small fraction of news articles, so a positive case (having shared an article) should have more weight than a negative case (not having shared).
User-news interaction embeddingFor the user-news interaction embedding we want to capture the relationship between user features and the labels of news items.
The intuition is that users with low credibility are more likely to spread fake news.
So how do we get user credibility?.Following ‘Measuring user credibility in social media’ the authors base this on similarity to other users.
First users are clustered into groups such that members of the same cluster all tend to share the same news stories.
Then each cluster is given a credibility score based on its relative size.
Users take on the credibility score of the cluster they belong to.
It all seems rather vulnerable to the creation of large numbers of fake bot accounts that collaborate to spread fake news if you ask me.
Nevertheless, assuming we have reliable credibility scores then we want to set things up such that the latent features of high-credibility users are close to true news, and the latent features of low-credibility users are close to fake news.
Publisher-news embeddingsRecall we have the matrix encoding which publishers have published which news pieces.
Let be the normalised version of the same.
We want to find , a weighting matrix mapping news publisher’s latent features to the corresponding partisan label vector .
It looks like this:Semi-supervised linear classifierUsing the labelled data available, we also learn a weighting matrix mapping news latent features to fake news labels.
Putting it all togetherThe overall objective becomes to find matrices using a weighted combination of each of the above embedding formulae, and a regularisation term combining all of the learned matrices.
It looks like this:and it’s trained like this: TriFN is evaluated against several state of the art fake news detection methods using the FakeNewsNet BuzzFeed and PolitiFact datasets.
It gives the best performance on both of them:(Enlarge) Original.
Reposted with permission.
Related: var disqus_shortname = kdnuggets; (function() { var dsq = document.
createElement(script); dsq.
type = text/javascript; dsq.
async = true; dsq.
src = https://kdnuggets.
disqus.
com/embed.
js; (document.
getElementsByTagName(head)[0] || document.
getElementsByTagName(body)[0]).
appendChild(dsq); })();.