企業の決算短信ＰＤＦから抽出した業績要因への極性付与

抄録

In this paper, we propose a method of assigning polarity to causal information extracted from PDF ?les of the summary of ?nancial statements of companies. Our method assigns polarity (positive or negative) to causal information in accordance with business performance, e.g. "Orders of semiconductor manufacturing equipments were strong". (The polarity positive is assigned in this example.) First, we assigns polarity to clue expressions to be used to extract causal information. Using them, our method assigns polarity (positive or negative) to causal information. We evaluated our method and con?rmed that it attained 88.4% precision and 84.2% recall of assigning polarity positive, and 91.4% precision and 74.5% recall of assigning polarity negative, respectively.