Sentiment Analysis, sometimes also referred to as Opinion Mining, is the study of the sentiments of humans and their different states of mind. It is a technique which determines whether a sentiment is good, neutral or negative. Traditionally Sentiment Analysis was frequently used to identify polarity of Textual data. Social-Media is widely used now and is a very important source of sharing your thoughts, ideas and even now is used for promoting your business. The most popular application of Sentiment Analysis can be seen in Social Media Analytics. The analysis of Social Media helps us to acquire a broad understanding of opinions made by people upon a specific topic. Since visual content such as photographs and videos is becoming a new medium for self-expression in social networks, multimedia sentiment analysis has gained a lot of attraction. In this paper we propose an way to perform sentiment analysis on videos by identifying the various facial expressions by using techniques of CNN and Deep Learning..The goal of this study is to create a system that can evaluate a video and anticipate a person's expression.

Keywords : CNN, Deep Learning, Face Emotion Recognition.