In the modern era, social networking platforms play a vital role in day-to-day life. It is used by personalities, bureaucrats, and common people alike. It provides a platform for everyone to express their opinions, share their experiences with their family, friends, and the world. The advent of such platforms has completely changed the outlook of the world. Sexual harassment has been a problem for a long time, but with the advancement in technology, some users have taken the harassment to the digital level. It is common these days to find users posting derogatory remarks, uploading sensual and private content of others in order to sexually harass them. This is not all. Some targeted audience might even take some wrong steps. This article presents a way to detect such derogatory and harassing remarks using Twitter as a database. The classification part is done with the help of two deep learning models, and at the end, the performance of both models is evaluated on various parameters.