Real time sentiment analysis of natural language using multimedia input

Semantics and Sentiments are parts of our daily speech and expressions that helps to convey the message in the tone intended. The accurate interpretation of emotions and actions is prudent as it expresses the true meaning of the message. This interpretation has been studied extensively in the past two decades, where professionals from various disciplines have pondered this question. Every action and expression-whether it's in a speech, in a video or through some written material-helps the recipient understand the intent behind the message. The primary motive in these studies has been to automate the analysis of these sentiments by teaching the computers to do so, using the audio, video and text-based data that has been collected so far. Machine Learning (ML) and Deep Learning (DL) is the discipline that can help us tackle such a problem which requires analysis and recognition of copious amounts of data. Classification based on these multi-media inputs has seen the application of several common and uncommon ML techniques such as Support Vector Machines (SVMs), Bayesian Networks (BNs), Decision Trees (DTs), Convolutional Neural Networks (CNNs) and K-Means Clustering. These techniques, to a certain level of accuracy, can classify a certain part of a message into a different emotion. Through this research, firstly, a comparison is represented between the previously conducted studies and secondly, a system is developed of our own that enables Real Time Sentiment Analysis and helps a user assess his/her day-to-day attitude and get appropriate recommendations for the same.