Ensemble Learning for Assessing Degree of Humor
Jianfan Chen, Zekai Li, Shaoheng Qin · 2022 International Conference on Big Data, Information and Computer Network (BDICN) · 2022
Sentiment analysis has always been a major research area for natural language processing, which aims at computing people’s opinions, attitudes, and emotions toward an entity. Benefiting from the development of deep convolution neural networks, the performance of sentiment analysis has made a breakthrough. However, existing sentiment analysis methods often fluctuate greatly in different sentiment analysis tasks. In this paper, to solve this problem, we introduce ensemble learning on a variant of deep learning models to gain a better score on sentiment analysis tasks. Ensemble learning is one of the most efficient methods for improving representation ability on many tasks. Comprehensive experiments on benchmark dataset demonstrate that the ensemble method greatly improves the performance of the model through combining the advantages of the different previous and current state-of-the-art. Also, we carried out experiment to compare different type of ensemble methods to further enhance model performance.