The rapid rise of information online has made it almost impossible to decipher the truth from the false which has led to the problem of fake news. This research paper considers old and new methods of fake news detection in textual formats and includes a discussion on Linguistic Cue and Network analysis approaches. The researcher proposes a three-part method using Naive Bayes Classifier, Support Vector Machines, and Semantic analysis as an accurate way to detect fake news on social media.
Highlights:
- The biggest reason fake news thrives is because humans fall victim to Truth-Bias, Naive Realism and Confirmation Bias. Humans are very poor lie detectors and lack the realisation that there is possibility of being led to.
- Social media users tend to let their guard down and absorb false information as the truth. Most users are aware of the mechanics of information manipulation. People tend to believe that their own views are correct and those who disagree are "uninformed, irrational, biased". Users also tend to consume media which caters to the political or personal bias.
- Social bots, trolls and cyborg users are the biggest contributors of fake news. The two main categories for detecting false information are the Linguistic Cue and Network Analysis approaches.
- The other methods of fake news detection which need to be further explored are the Naive Bayes classifier, Support Vector Machine, and semantic analysis. The proposed method described in the paper is an idea for a more accurate fake news algorithm with further research on the other methods listed formerly.
- The paper highlights the need to have some mechanism for detecting fake news and a minimum awareness that not everything you read on social media is true.