Suspicious Online Forum Data Detection

Anant Chourasia
2020 Bioscience Biotechnology Research Communications  
The exponential growth seen in the past few years of internet users and its easy access through handy available devices, As a result of which the size of digital content has been growing very rapidly in recent years through messaging applications, posts on social networking sites, vlogs, blogs, online forums and other internet platforms. With the advancement of social media sites over the internet, one's post can be reached all over the world which means it can be used to influence people in
more » ... h good and bad ways. Although social media has many advantages,people misuse social media to exploit other people. The anonymity offered by internet and flexibility afforded has made it convenient for users to socialize in an aggressive and disrespectful manner over the internet. Text contents are mostly used to perform suspicious activities. Hate speech is currently an interest in the domain of social media. So, one of the most difficult issues for NLP researchers and programmers is to develop an algorithm that can detect text with hate speech automatically and efficiently from its specific contents. So here, a classification based Machine Learning model is proposed to efficiently and automatically classify text into non-suspicious and suspicious categories based on its contents.
doi:10.21786/bbrc/13.14/6 fatcat:pz42wnryb5d5lnlf6knvqtgvrq