Published Paper Details:

Due to the immense use of social media and online news media there has been a large surge of fake news in recent times. Spreading fake news has become much easier. Such spreading of fake news may have a severe effect. Hence it is extremely essential that certain measures should be taken in order to reduce or distinguish between real and fake news. Information overload and a general absence of comprehension about how the web functions by individuals have additionally added to an expansion in fake news or hoax stories. Social media sites can have a major influence in expanding the span of this kind of story. Fake news is a news created to intentionally misguide or mislead readers. Fake news is spread mainly for gaining political or financial incentives. They submit this well-crafted news stories and also recruit social bots or paid scammers to spread the news more rapidly and different approaches using text-based analysis for detecting fake news. Ever since the birth of social media and online news media, the spread of fake news has increased drastically. Social media sites such as Facebook, Google Plus etc are one of the biggest sources of spreading fake news. As the spread of such fake news can be intentional or unintentional but this affects society. Thus, an increasing number of fake news has to be controlled by using the computational tool which predicts such misleading information as if it is fake or real. Here we have focused on developing such computational tool to help classify news using machine learning algorithm. Which helps the model to be more trustworthy. Which describes the pre-processing, feature extraction, classification and prediction process in detail. We've used Logistic Regression to classify fake news. The pre-processing functions perform some operations like tokenizing, lemmatization and exploratory data analysis like response variable distribution and data quality check (i.e., null or missing values). Simple Count Vectorization, TF-IDF is used as feature extraction techniques. The logistic regression is used as a classifier for fake news detection with a probability of truth.