Social networking services were designed to
bring individuals from all over the world together and
provide them a place to express their views and opinions.
However, since their inception, social media platforms
such as Facebook, Instagram, and Twitter have been
misused for harmful purposes including publishing
inaccurate information and promoting fake news.
Surprisingly, due to its accessibility and wide range of
topics, more individuals are turning to social media to
consume news, rather than conventional news sources like
newspapers and television. Recently, classification of fake
news has caught the attention of many researchers, and
there is an increasing demand for controlling the spread of
fake news among these networking sites. In this
manuscript, we have presented a method for classifying
false information using TF-IDF vectorizer and Natural
Language Processing. For training and evaluating the
performance of the model we have used a dataset from
Kaggle and Buzzfeed News. Our model shows promising
results.
Keywords :
Fake News, Machine Learning, Term Frequency, Inverse Document Frequency, Vectorizer, Natural Language Processing.)