生田 祐介

This paper presents an approach to measuring business sentiment based on textual data. Business sentiment has been measured by traditional surveys, which are costly and time-consuming to conduct. To address the issues, we take advantage of daily newspaper articles and adopt a self-attention-based model to define a business sentiment index, named S-APIR, where outlier detection models are investigated to properly handle various genres of news articles. Moreover, we propose a simple approach to temporally analyzing how much any given event contributed to the predicted business sentiment index. To demonstrate the validity of the proposed approach, an extensive analysis is carried out on 12 years' worth of newspaper articles. The analysis shows that the S-APIR index is strongly and positively correlated with established survey-based index (up to correlation coefficient r = 0.937) and that the outlier detection is effective especially for a general newspaper. Also, S-APIR is compared with a variety of economic indices, revealing the properties of S-APIR that it reflects the trend of the macroeconomy as well as the economic outlook and sentiment of economic agents. Moreover, to illustrate how S-APIR could benefit economists and policymakers, several events are analyzed with respect to their impacts on business sentiment over time.

政府や中央銀行が発表する景況感指数は，金融当局の政策決定や企業の生産計画などの拠りどころとして重要な役割を担っている．しかし，これらの指数は大規模なアンケートに基づいており，その算出には大変な手間と時間がかかる．そこで本研究では，ニュース記事を再利用することで，低コストで速報性の高い，新しい景況感指数を算出する手法を提案する．具体的に，外れ値検出モデルにより経済・景気に関係が薄いと判断された記事を除外したうえで，それ以外の記事（の文）に対して景気スコアを予測する．そして，ある期間に発行された記事すべての景気スコアを統合して，その期間の景況感指数を定義する．景気スコアの予測には，近年自然言語処理タスクで広く利用されているBERTをファインチューニングして用いる．さらに，算出された景況感指数を基に，任意の概念（語句）がどのように景況感に影響を与えたのかを時間軸に沿って分析する手法を提案する．

This paper describes our work on developing a new business sentiment index using daily newspaper articles. We adopt a recurrent neural network (RNN) with Gated Recurrent Units to predict the business sentiment of a given text. An RNN is initially trained on Economy Watchers Survey and then fine-tuned on news texts for domain adaptation. Also, a one-class support vector machine is applied to filter out texts deemed irrelevant to business sentiment. Moreover, we propose a simple approach to temporally analyzing how much and when any given factor influences the predicted business sentiment. The validity and utility of the proposed approaches are empirically demonstrated through a series of experiments on Nikkei Newspaper articles published from 2013 to 2018.

Business sentiment indices play a crucial role in government's policy decisions, production planning in industries, and individual/institutional investment decisions. However, such indices require large-scale surveys, which are costly and laborious to conduct. As an alternative, this paper reports our ongoing work on estimating business sentiment based on abundant, ordinary newspaper articles. Our proposed framework is composed of a recurrent neural network for regression, a one-class support vector machine to filter out topically irrelevant articles, and fine-tuning for domain adaptation. The effectiveness of the framework is empirically demonstrated by experiments on Nikkei newspaper.