Meta-learning ensemble for emotion detection in conversational text

Abstract Advances in Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) are enabling machines to emulate human-like behaviors. In the context of social computing, lifelike characters are crucial as they facilitate natural and intuitive interactions between humans and computers. Chatbots, a key application of such technologies, are computer programs that use Natural Language Processing (NLP) to engage in text-based conversations. They are widely used in customer service and other domains, but the challenge lies in designing chatbots that feel more human to enhance user engagement. Research has shown that incorporating emotions into chatbots is critical for achieving this goal. Effective emotion recognition systems must be able to process real-time text interactions, understand users’ sentiments on various topics, address their concerns, and respond appropriately based on the detected emotions. This paper proposes a meta-learning ensemble approach for text-based emotion detection in conversational data. The proposed method combines the outputs of multiple well-established machine learning algorithms to improve accuracy in recognizing emotions in text. A comparative analysis was conducted on two conversational datasets, demonstrating that the meta-learning ensemble method outperforms individual machine learning algorithms on both datasets. The proposed approach achieved 73% classification accuracy on the Empathetic Dialogues dataset, while on the EmoContext dataset, it achieved 95.1% classification accuracy, significantly outperforming results over individual machine learning algorithms. The conclusions demonstrate that utilizing a meta-learner for model fusion successfully leverages the advantages of separate algorithms while alleviating their intrinsic shortcomings, resulting in enhanced overall performance.