zippy/samples/llm-generated/2110.10340_generated.txt

Abstract 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. Keywords: business sentiment, sentiment analysis, deep learning, text analytics Introduction In Japan, there exist business sentiment indices, such as Economy Watchers Survey1 and Short-term Economic Survey of Principal Enterprise2 conducted by the Government and the Bank of Japan, respectively. These diffusion indices (DI) play a crucial role in decision-making for governmental/monetary policies, industrial production planning, institutional/private investment, and so on. However, these DIs rely on traditional surveys, which are costly and time-consuming to conduct. For example, Economy Watchers Survey is carried out in 12 regions of Japan, where 2,050 preselected respondents who can observe the regional business/economic conditions (e.g., store owners and taxi drivers) fill out a questionnaire and then an investigative organization in each region aggregates the surveys and calculates a DI. As the survey and subsequent processes take time, the DI is published only monthly. On the other hand, so-called alternative data, including merchandise sales, news, micro-blogs, query logs, credit card transactions, GPS location information, and satellite images, are constantly generated and accumulated. The availability of such data has accelerated the development of data-driven artificial intelligence (AI) models and techniques represented by deep learning. In econometrics, there is a growing interest in future/current forecasts of economic and financial indices by using such alternative, large-scale data instead of traditional surveys (Chen et al., 2019; Jain, 2019). For example, point of sales (POS) data have been used for estimating consumer price index (CPI) (Watanabe & Watan-abe, 2014); financial and economic reports for business sentiment (Yamamoto & Matsuo, 2016); newspaper for stock prices (Li et al., 2020; Picasso et al., 2019; Yoshihara et al., 2014, 2016), socio-economic indicators (Chakraborty et al., 2016), consumer sentiment (Shapiro et al., 2020); and social media for stock prices (Bollen et al., 2011; Derakhshan & Beigy, 2019; Levenberg et al., 2014). This work focuses on textual data and uses daily newspaper articles to develop a new business sentiment index, named the S-APIR index. In addition, using the computed index, we propose an approach to temporally analyzing the influence of an arbitrary event on business sentiment. The remainder of the paper is structured as follows: Section 2 introduces the related work on sentiment analysis in general and its applications to market sentiment and business sentiment prediction. Section 3 states the research objectives pursued in the present work. Section 4 details our proposed approach to forecasting business sentiment index and describes how to temporally analyze the contribution of a given event to business sentiment index based on predicted business sentiment scores. Section 5 conducts evaluative experiments using over 12 years’ worth of newspaper articles and discusses the properties of S-APIR, in addition to word-level temporal analysis. Section 6 discusses the implications and findings of this work. Section 7 concludes with a brief summary and possible future directions. Conclusions This paper reported our work to develop a new business sentiment index, called S-APIR. The main contribution of this work is threefold: Firstly, we proposed an approach to capturing business sentiment based on news texts and empirically validated it in comparison with an existing survey-based index. Secondly, we thoroughly studied the properties of the proposed index.we illustrated how the predicted business sentiment can be used by policymakers and economists when it was broken down into individual events. The following describes, more specifically, the contribution from methodological, theoretical, and practical viewpoints. The methodological contribution is that we devised an effective framework composed of outlier detection and prediction models. The former used one-class model and the latter was a different approach based on traditional surveys. Also, the former used the survey-based model and the latter was a different approach based on traditional surveys. The latter was a little more work than the former. The difference is that the outlier detection is more effective than the traditional survey-based model. Also, the difference is that the outlier detection is much more effective than the traditional one-class one-issue-at-res. Finally, the difference is that the outlier detection is much more effective than the traditional one-class one-issue-at-res. We hope this help shows us how S-APIR can benefit economists and policymakers, and how S-APIR could benefit economists and policymakers, several billion lines of text. More specifically, we hope that this help shows us how S-APIR can be useful as a data-driven artificial intelligence (AI) model and how S-APIR could benefit economists and policymakers, several billion lines of text. Section 2 shows how to properly handle various genres of news articles. Section 3 states the research objectives pursued in the present work. Section 4 details our proposed approach and describes how to properly handle various genres of news articles. Section 5 conducts evaluative experiments using over 12 years’ worth of newspaper articles and discusses the properties of S-APIR, in addition to word-level temporal analysis. Section 6 discusses the implications and findings of this work. Section 7 concludes with a brief summary and possible future directions. Conclusions This paper reported our work to develop a new approach to capturing the sentiment of online news articles. The main contribution of this work is threefold: Firstly, we proposed an approach to capturing the sentiment of news articles and empirically validated it in comparison with an existing survey-based model. Secondly, we thoroughly studied the properties of the proposed approach. Lastly, we illustrated how the predicted business sentiment can be used by policymakers and economists when it was broken down into individual events. The following describes, more specifically, the contribution from methodological, theoretical, and practical viewpoints. The former was a little more work than the latter. The difference is that the outlier detection is much more effective than the traditional one-class one-issue-at-res. Also, the difference is that the outlier detection is much more effective than the traditional one-class one-issue-at. Also, the difference is that the outlier detection is much more effective than the traditional one-class one-issue. Finally, the difference is that the outlier detection is much more effective than the traditional one-class one-issue.. The computed business sentiment has been measured by traditional surveys and its accuracy has been measured by traditional surveys only. Our approach is in addition to looking at the properties of the proposed approach. In econometrics, there is a growing interest in future/current forecasts of economic and financial indices by using such alternative, large-scale data instead of traditional surveys.