Papers - GOSHIMA Keiichi
about 11-
Otologic disease trends in Japan post-COVID-19 outbreak: A retrospective time-series analysis
Kondo, K; Honda, K; Goshima, K; Inoue, N; Shinjo, D; Tsutsumi, T; Fushimi, K
AURIS NASUS LARYNX 51 ( 3 ) 525 - 530 2024.6
Language：Japanese Publishing type：Research paper (scientific journal) Joint Work
-
Goshima, K; Ishijima, H; Shintani, M
APPLIED ECONOMICS LETTERS 31 ( 6 ) 568 - 573 2024.3
Language：Japanese Publishing type：Research paper (scientific journal) Joint Work
-
国際株式市場間の連動性の長期変遷に関する実証分析
五島 圭一
ファイナンシャル・プランニング研究 22 39 - 45 2023 [Reviewed]
Language：The in addition, foreign language Publishing type：Research paper (scientific journal) Single Work
-
五島 圭一, 八木 厚樹
証券アナリストジャーナル = Securities analysts journal 60 ( 8 ) 67 - 80 2022.8
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：東京 : 日本証券アナリスト協会 Joint Work
-
Sentiment Dictionary for Business Cycle Analysis and its Applications
Goshima Keiichi, Shintani Mototsugu, Takamura Hiroya
Journal of Natural Language Processing 29 ( 4 ) 1233 - 1253 2022
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：The Association for Natural Language Processing Joint Work
<p>In this study, we construct a sentiment dictionary for the macroeconomic domain and present its applications. Our dictionary contains words selected by several economists from a corpus of newspaper articles on topics related to the economy. This was supplemented with additional words by using supervised learning. We use our sentiment dictionary to construct a daily business cycle index designed to capture the current state of the economy in a timely manner. </p>
-
国際株式市場間の連動性の長期変遷に関する実証分析 : 学会賞
五島 圭一
ファイナンシャル・プランニング研究 / 日本FP学会「ファイナンシャル・プランニング研究」編集委員会 編 22 39 - 45 2022
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：東京 : 日本FP学会 Single Work
-
Forecasting Japanese inflation with a news-based leading indicator of economic activities
Goshima, K; Ishijima, H; Shintani, M; Yamamoto, H
STUDIES IN NONLINEAR DYNAMICS AND ECONOMETRICS 25 ( 4 ) 111 - 133 2021.9
Language：Japanese Publishing type：Research paper (scientific journal) Joint Work
-
有価証券報告書のテキスト分析 : 経営者による将来見通しの開示と将来業績
加藤 大輔, 五島 圭一
金融研究 40 ( 3 ) 45 - 75 2021.7 [Reviewed]
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：東京 : 日本銀行金融研究所 Joint Work
-
Controlling contents in data-to-document generation with human-designed topic labels
Aoki, K; Miyazawa, A; Ishigaki, T; Aoki, T; Noji, H; Goshima, K; Takamura, H; Miyao, Y; Kobayashi, I
COMPUTER SPEECH AND LANGUAGE 66 2021.3
Language：Japanese Publishing type：Research paper (scientific journal) Joint Work
-
ニュースで読み解くマクロ経済 : テキストデータを用いた分析方法
新谷 元嗣, 五島 圭一
経済セミナー = The keizai seminar ( 719 ) 34 - 39 2021
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：東京 : 日本評論社 Joint Work
-
Generating Market Comments from Stock Prices
Murakami Soichiro, Watanabe Akihiko, Miyazawa Akira, Goshima Keiichi, Yanase Toshihiko, Takamura Hi … Show more authors
Murakami Soichiro, Watanabe Akihiko, Miyazawa Akira, Goshima Keiichi, Yanase Toshihiko, Takamura Hiroya, Miyao Yusuke Hide authors
Journal of Natural Language Processing 27 ( 2 ) 299 - 328 2020.6
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：The Association for Natural Language Processing Joint Work
<p>This study tackles the task of generating market comments from stock prices. Market comments not only describe the increase and decrease of the price but also describe how the price changes compared with the previous period and contain expressions that depend on their delivery time. Additionally, market comments typically mention numerical values, such as closing prices and differences in stock prices, that need arithmetic operations such as subtraction and rounding off to derive these values. To capture these characteristics, we propose a novel encoder–decoder model to automatically generate market comments from stock prices. The model first encodes both short- and long-term series of stock prices so that it can create short- and long-term changes in stock prices. Thereafter, we feed our model with delivery time of the market comment in the decoding phase to generate time-dependent expressions. Moreover, our model can generate a numerical value by selecting an appropriate arithmetic operation, such as subtraction or rounding off, and applying it to the input stock prices. As shown in empirical experiments, our model generates high-quality market comments with fluency and informativeness in comparison with baselines. </p>