An Event Based Topic Learning Pipeline for Neuroimaging Literature Mining

Abstract Neuroimaging text mining extracts knowledge from neuroimaging text and has received widespread attention. Topic learning is an important research focus of neuroimaging text mining. However, current neuroimaging topic learning researches mainly use traditional probability topic models to extract topics from literature and cannot obtain high-quality neuroimaging topics. The existing topic learning methods cannot meet the requirements of topic learning oriented to full-text neuroimaging literature. In this paper, three types of neuroimaging research topic events are defined to describe the process and result of neuroimaging research. An event based topic learning pipeline, called neuroimaging Event-BTM, is proposed to realize knowledge extraction from full-text neuroimaging literature. The experimental results on the PLoS One data set show that the accuracy and completeness of proposed method are significantly better than the existing main topic learning methods.