Happy Together: Learning and Understanding Appraisal From Natural Language
This work addresses the incremental task of understanding emotional appraisal in natural language processing for applications in psychology or sentiment analysis.
The paper tackled the problem of learning appraisal components (agency and sociality) from happy language using the HappyDB dataset, achieving 87.97% accuracy on agency and 93.13% accuracy on sociality with deep neural network models.
In this paper, we explore various approaches for learning two types of appraisal components from happy language. We focus on 'agency' of the author and the 'sociality' involved in happy moments based on the HappyDB dataset. We develop models based on deep neural networks for the task, including uni- and bi-directional long short-term memory networks, with and without attention. We also experiment with a number of novel embedding methods, such as embedding from neural machine translation (as in CoVe) and embedding from language models (as in ELMo). We compare our results to those acquired by several traditional machine learning methods. Our best models achieve 87.97% accuracy on agency and 93.13% accuracy on sociality, both of which are significantly higher than our baselines.