Emotion Detection from Textual Data Using Supervised Machine Learning Models

Emotion detection and recognition from text is a recent field of research that is closely related to Sentiment analysis. Many people express themselves using text, photographs, music, and video. Text communication using web-based networking platforms, however, could be a little overwhelming. Every second, a substantial amount of unstructured data is produced on the Internet as a result of social media sites. This is where sentiment analysis, which recognises polarity in texts, can be useful. It assesses the author’s attitude towards a specific object, administration, person, or location and concludes if it is positive, negative, or neutral. In some cases, sentiment analysis is inadequate, necessitating emotion detection, which precisely ascertains a person’s mental/emotional state. The development of a text-based emotion detection and prediction model is the primary goal of this work. The development of emotion analysis is confronting several market hurdles, with accuracy being the key one. As a result, the Decision Trees, Naive Bayes, Support Vector Machine, Logistic Regression, k-Nearest Neighbors and Random Forest, supervised machine learning classification algorithms were examined. The six main emotions recognized by Ekman are joy, fear, anger, love, surprise, and sadness, these were the foundation through which the model was constructed. strategies for preprocessing data containing stemming, stop-words, numerals, and punctuation marks removal, tokenization, and spelling correction were implemented. This review paper delves into the degrees of several emotion models as well as the technique of emotion detection from text.