


Volume 20 No 10 (2022)
Download PDF
Emotional and Sentimental Prediction from Textual Comments Using Machine Learning Techniques
Dr.P.Chitra , Shoba L.K , Dr.E.Sujatha , S.Pushpa latha , Dr.P.Subhashini
Abstract
Emotion Analysis is a process of identifying and analyzing the underlying emotion expressed in the
textual data in the form of sentences. Sentiment analysis is a superset of Emotion Analysis. In sentiment
analysis, there are only three results such as positive, negative, and neutral, but in Emotion analysis, we
can make up to n number of results. In our Emotion Analysis, we are detecting ten Emotions.Sentiment
Analytics tries to understand the general feeling and emotion experienced by a viewer or customer.
Whereas emotional analysis uses a complex system to understand consumer responses. Unlike
sentiment analysis, emotion analysis includes the subtleties of human emotions. So, for example with
the positive spectrum, we may find emotions like happiness, contentment, love, excitement, etc.
Software products used in emotion analysis are primarily open source and free. Most of the items are
purchased online from stores like Amazon and Flipkart. Customer reviews are available for each
product, and the people usually read them before purchasing. Emotion analysis can be helpful in
determining a customer's emotion in long reviews. The main algorithm is a recurrent neural network
(RNN) that has been shown to have a better prediction rate than other algorithms. In comparison to
previous models with increased classes, this model provides better results
Keywords
Machine learning, Artificial Intelligence, Cloud servers, Emotion Analysis, Sentiment Analysis, RNN, open-source
Copyright
Copyright © Neuroquantology
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.