Sentiment Analysis with the Use of Transformers and BERT

Elisavet Douka, Isidoros Perikos, Ioannis Hatzilygeroudis

Abstract: Recognizing the emotional content of natural language sentences can improve the way humans communicate with a computer system by enabling them to recognize and imitate emotional expressions. The field of emotion recognition occupies an important place in the applications of artificial intelligence. The rapid increase in the popularity of social media has created the need to study and document their use. In this paper, both classical classification algorithms and various neural network architectures were tested. In the context of this paper, we designed and developed deep learning methods and BERT-based implementations for recognizing emotional content in user-generated data. Extensive experiments were conducted using these models on a variety of textual data and all the designed methods were evaluated.