"AffectAlchemy": An Affective Dataset Based on Plutchik’s Psychological Model for Text-Based Emotion Recognition and its Analysis Using ML Techniques

A technique to identify people's attitudes, and sentiments towards specified targets such as things, services, and subjects, is called sentiment analysis. As a dedicated subset of NLP, it deals with predicting specific reactions broadly characterizing sentiments as positive, negative, or neutral. However, the accuracy and depth vary since there are a variety of human emotions that exist rather than just positive, negative, and neutral. In the past few decades, the term affective computing has become well-liked which involves the use of AI for identifying, interpreting, and responding to human emotions. A part of it called text-based affective systems are artificial emotional intelligent systems that often categorize the text into core wide range of emotions like fear, sadness, anger, and happiness. These affective systems use various psychological models for emotion recognition. Our study incorporates the development of a dataset based on Robert Plutchik's psychological model of emotions, which sets forth eight primary emotions which are combined to form more complex emotions, resulting in a total of 24 secondary emotions resulting total of 32 variety of emotions. The work introduces the "AffectAlchemy" dataset which is validated using multiclass classification machine learning techniques. This dataset can contribute to the field of affective computing for the development of models that can do enhanced emotion recognition, and improved emotional context understanding to develop emotion-aware applications and facilitating research in affective systems.