Automatic Extraction of Relationships among Motivations, Emotions and Actions from Natural Language Texts
This addresses the challenge of understanding human behavior from text for applications in psychology or NLP, but it is incremental as it builds on existing graph-based and LLM methods.
The authors tackled the problem of automatically extracting relationships among motivations, emotions, and actions from natural language texts, achieving a result where 63% of the 92,990 generated graphs made logical sense.
We propose a new graph-based framework to reveal relationships among motivations, emotions and actions explicitly given natural language texts. A directed acyclic graph is designed to describe human's nature. Nurture beliefs are incorporated to connect outside events and the human's nature graph. No annotation resources are required due to the power of large language models. Amazon Fine Foods Reviews dataset is used as corpus and food-related motivations are focused. Totally 92,990 relationship graphs are generated, of which 63% make logical sense. We make further analysis to investigate error types for optimization direction in future research.