There are many limitations in online learning process where communication effect student productivity, such as interpretation in the delivery of information can be different if it is in text form . The unstable internet network in some parts of Indonesia is also an obstacle in the learning process. Emotional factors are very influential on student motivation in learning, in online learning emotions can be read from textual dialogue in providing responses. We propose trainable model capable of identifying the tendency of emotions / responses felt by students. With using natural language processing we can extract information and insights contained in conversations from WhatsApp, then organize them into their respective categories. The selection of the RNN algorithm can increase the accuracy by 75% in analyzing student emotions in online learning.
Copyrights © 2021