Fake News Detection Technique Using Tfidfvectorizer and Passiveaggressive Classifier in Python
For news consumption, social media could be an uncertain weapon. On the one hand, people use social media to find and consume news because of its low cost, easy access, and rapid transmission of information. On the other hand, it allows for the widespread dissemination of fake news, i.e. inferiority news based on intentionally inaccurate information. The widespread dissemination of fake news has the potential to have disastrous consequences for people and society. As a result, spotting false news on social media has recently been a popular topic that has gotten a lot of press. Pretending that news detection on social media has unique traits and obstacles that render existing detection algorithms from traditional journalism ineffective or not applicable. First, fake news is intended to induce readers to accept misleading information, making it difficult and time-consuming to spot supported news content. As a result, we'd like to include auxiliary data, such as user social media engagements on social media, to aid in making a decision. Second, utilising this auxiliary data is difficult in and of itself, as users' social interactions with fictitious news produce huge, incomplete, unstructured, and noisy data. Because the challenge of detecting fake news on social media is both challenging and relevant, we've decided to conduct this poll to aid in the investigation.We will provide a full evaluation of police investigation, fake news on social media, as well as fake news characterizations on scientific disciplines and social theories, existing algorithms from a knowledge mining perspective, analysis metrics, and representative datasets during this survey. We'll also talk about related research topics, unresolved questions, and future research paths for detecting fake news on social media.
Keywords - Fake News Detection, TFIDFVectorizer, PassiveAggressive Classifier, Python.