An Aspect Based Sentimental Analysis Approach Using Convolutional Neural Networks and Recognizing Audience Feedback through Facial Expression to Analyze the Sentiments in Presentations

Abstract

Audience feedback is a key factor in evaluating the effectiveness of a conference, summit, or meeting. Capturing consistent, high-quality feedback from audience members, however, is a challenge. Long-used tools such as surveys fail to gauge the actual emotion of audience members accurately. Surveys suffer from low response rates, delayed responses, and participant bias. So to remove or reduce these fallacies, we use face detection and emotion recognition algorithms to measure the overall feedback of the audience. The proposed system can extract data from live video footage, recorded video or static images. From the extracted data, the software recognizes faces and analyzes emotions conveyed through facial expressions. The emotions are then classified as positive, negative or neutral and the system outputs the observed sentiment data graphically.