Review On Using Machine Learning and Deep Learning Algorithms for Emotion Analysis

Abstract

Nowadays, sharing moments on social networks has turned out to be something widespread. Sharing ideas, thoughts, and precise recollections to explicit our feelings through text without the use of loads of words. As a result, social media text data analysis is becoming increasingly important, as it contains the most up-to-date information on what people are thinking. For example, Twitter is a rich source of data that organizations can use to analyze people’s opinions, sentiments, and emotions. Emotion analysis usually provides a more comprehensive picture of an author’s feelings. Organizations and individuals are also interested in using social media to analyze people’s opinions and extract feelings and emotions, which thus leads to knowing people’s orientation on a specific topic. Emotion detection gets extraordinarily little attention. Very little research so far has tested the class of feelings in text, especially Arabic written content. unbalanced data that contains Arabic texts affects the performance of the classification process. Therefore, text-based emotion Analysis has gained a lot of attention in recent times. The paper presents a systematic literature review of the existing literature in Text-Based Emotion Analysis (TBEA). To answer the main research issues, this study has carefully looked at over 60 research publications. Additionally, it goes over the numerous TBEA methodologies used in different study disciplines. A summary of several emotion models and methods.