Human beings commune with each other to convey thoughts, expressions, experiences and so on to the people around them. But this case is not the same when it comes to the deaf and mute people. Sign language paves the way for people with such difficulties to communicate with one another. The aim of this paper is to facilitate easy and accurate communication between people who have hearing and speaking disabilities, and those who do not. This paper shows how the communication gap can be bridged using sign language to text and audio converter with the help of Feature Extractor and Posenet with an accuracy of 92%. A webcam is used to capture the sign language shown by a person. Posenet with Artificial Neural Network is used to classify essential words used in day to day life. Various parts of the body are tracked by the webcam and then converted to text and audio to convey what the person is trying to express in real time.

Cyberbullying is the use of technology to harass, threaten or target another individual. Online bullying can be particularly damaging and upsetting since it is usually anonymous and it's often hard to trace the bully. Sometimes cyberbullying can lead to issues like anxiety, depression, shame, suicide, etc. Most of the cyberbullying cases are not revealed to the public and the number of cases reported to the legal system is only few. Certain victims do not reveal their bully experiences out of shame or due to difficult procedures for reporting to the legal system. Our cyberbullying detection system aims to bring cases involving cyberbullying under control by detecting and warning the bully. Such cases are also reported to appropriate authorities, which can then be verified and necessary actions can be taken depending on the situation. The technology stack used for implementation include Flask, Scikit learn, Chat application APIs, Firebase, HTML, Javascript and CSS. The model was tested on classifiers like SVM, KNN, Logistic regression and Random Forest. F1 score was used as a metric to assess the four models. While analyzing the performances of these models, it was observed that Random Forest Classifier outperformed all the models. F1 score of 93.48% was achieved using the Random Forest Classifier.