Personalised Emotion Detection from Text Using Machine Learning

This research discusses an emotion recognition system, which is an important component of many effective computing technologies for natural language processing, based on open-source platforms with automatic speech recognition (ASR) and text analysis, and which is used for user-based customised sentiment analysis. PocketSphinx as ASR and Word2vec model, K-means clustering, and TfidfVectoriser for text automatic analysis are used to design the proposed framework. Further, the dataset that is used for testing and training the model is from International Survey on Emotion Antecedents and Reactions (ISEAR). This research yields a user-dependent system that will function as a tailored assistant for identifying emotional responses and discovering innovative applications. The suggested model greatly outperforms the prior models, with an efficiency of 81% and an f-measure of 89%.