ABSTRACT

Emotion recognition has become a challenging task in the field of natural language processing since there is a large amount of data available on the Internet. Different methods are used to recognize emotion. In this paper, CNN-LSTM and logistic regression are used to recognize emotion. Most of the work in the field of artificial intelligence focuses only on the recognition of emotions, rather than exploring the reasons why emotions are not recognized or misrecognized. The correlation between emotions leads to the failure of emotion recognition. Here, we fill the gap between emotion recognition and emotion correlation. The emotion correlation is extracted by using confusion of emotion and evolution of emotion. Emotion correlation is based on the emotion recognition results of the machine learning models by using text. Keywords: Affective computing, logistic regression, convolution neural network (CNN), long short-term memory (LSTM), deep neural networks, emotion correlation, emotion recognition, natural language processing (NLP)
Publication date: 01/11/2021

https://ijbpas.com/pdf/2021/November/MS_IJBPAS_2021_NOV_SPCL1009.pdf

Download PDF
https://doi.org/10.31032/IJBPAS/2021/10.11.1009