[2O3-J-13] AI application: investments

[2O3-J-13-04] Construction of Causal Networks for Risk Finding Considering Word Polarities

〇Hiroaki IGARASHI Igarashi¹, Hiroki Sakaji¹, Kiyoshi Izumi¹, Takashi Shimada¹, Shintaro Suda² (1. the University of Tokyo, 2. Mitsubishi UFJ Trust Investment Technology Institute Co., Ltd.(MTEC))

Keywords:Causal relation, Text mining, Sentence polarity

In this research, we conduct an experiment of constructing a causal networks within settlement account briefs. We extracted the causal relations from settlement briefs, and construct a network by connecting them by judging similarities. For calculating the similarities, we use a word2vec model created from the Japanese Wikipedia corpus.We use a method based on a combination of idf values which representing importance of words. In addition, by giving the polarities of causal expression using a polar dictionary, and judgment of synonyms that word2vec can't detect, we define so to speak, "negative relation".