Article,
Recognition of Sentiment using Deep Neural Network
INTERNATIONAL JOURNAL OF TREND IN SCIENTIFIC RESEARCH AND DEVELOPMENT, 7 (1): 896-903 (February 2023)
Abstract
Emotion is one of the maximum essential details which determines in predicting the human nature and information the human behaviour. Though it is an easy task for human being for recognizing human’s emotion but it is not the same for a computer to understand. And so let research is being conducted to predict the behaviour correctly with higher precision and accuracy.This paper demonstrates the real time facial emotion recognition in one of the seven categories o emotion that are angry, disgust, fear, happy, neutral, sad and surprise. We are using a simple 4 layer Convolution Neural Network CNN . We also have implemented various filter and pre processing to remove the noise and also have taken care of over fitting the curve. We have tried to improve the accuracy o model by applying various filters and optimizing the data for feature extraction and obtaining the accurate data prediction. The dataset used for testing and training is FER2013 and the proposed trained model gives an accuracy of about 73 . Keyword Emotion Recognition, Convolution Neural Network CNN , pre processing, Over fitting, Optimization, features extraction. Amit Yadav | Anand Gupta | Ms. Aarushi Thusu "Recognition of Sentiment using Deep Neural Network" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-7 | Issue-1 , February 2023, URL: https://www.ijtsrd.com/papers/ijtsrd52797.pdf Paper URL: https://www.ijtsrd.com/computer-science/artificial-intelligence/52797/recognition-of-sentiment-using-deep-neural-network/amit-yadav
