Abstract

The analysis of social media posts is a challenging task, particularly the recognition of user emotions. Text is one of the most common mediums used by humans to express emotion, particularly on social media platforms. As emotions play a pivotal role in human interaction, the ability to recognize them by analyzing textual content has various applications in human-computer interaction (HCI) and natural language processing (NLP). Previous studies on emotion classification used bag-of-words classifiers or deep learning on static Twitter data.Our proposed model is a hybrid approach that uses a combination of keyword-based and learning-based models to perform textual emotion recognition on Twitter posts obtained in real-time. Textual feature extraction is carried out by standard Natural Language Processing (NLP) techniques such as Part-of-Speech (PoS) tagging and topic modeling along with classification done using the random forest algorithm. Results show that our proposed model performs better in comparison to the traditional Unison model with an average accuracy that approximates to 88.39%.