Uncovering values: detecting latent moral content from natural languaje with explanaible and non-trained methods

Moral values as commonsense norms shape our everyday individual and community behavior. The possibility to extract moral attitude rapidly from natural language is an appealing perspective that would enable a deeper understanding of social interaction dynamics and the individual cognitive and behavioral dimension. In this work we focus on detecting moral content from natural language and we test our methods on a corpus of tweets previously labeled as containing moral values or violations, according to Moral Foundation Theory. We develop and compare two different approaches: (i) a framebased symbolic value detector based on knowledge graphs and (ii) a zero-shot machine learning model fine-tuned on a task of Natural Language Inference (NLI) and a task of emotion detection. Our approaches achieve considerable performances without the need for prior training