Facial Emotion Recognition from Video using Transfer Learning to differentiate Emotion and Expression of Presenter

Our study offers a thorough investigation of Facial Emotion Recognition (FER) for content moderation in the dynamic digital environment. An advanced mosaic of emotions and expressions has been made possible by the quick expansion of online information in the form of films, photos, and live camera feeds. With the help of the MobileNetV2 pre-trained model and transfer learning techniques, we use the FER 2013 dataset to address the complex problem of content moderation in this situation. Our main objective is to create a tool that encourages safer and more compassionate online interactions by alerting people when there is a contradiction between their spoken words and the emotions shown on their faces. The range of human emotions included in the study's focus on emotions includes anger, sadness, disgust, fear, surprise, neutrality, and happiness. We explore the confluence of cutting-edge technology, data analytics, and emotional intelligence in this comprehensive investigation. We hope to create a digital environment that is more sensitive to human emotions by linking these realms. Our initiative aims to provide users with a virtual environment where they may communicate while feeling more at ease, empathic, and understanding. By doing this, we hope to contribute to the ongoing transformation of the digital environment into an area where content and interactions are more emotionally intelligent and in tune with one another.