Papers - Kazuhiro Seki
-
Refining Sentiment Predictions: Obtaining an Unbiased Business Sentiment Index from Japanese Newspapers Reviewed
Kazuhiro Seki
International Journal of Asian Language Processing 33 ( 2 ) 2350015 2023.12
Authorship：Lead author, Last author, Corresponding author
-
Topic-Sentiment Analysis of Central Bank Press Conferences: BOJ Case Study Reviewed
Kazuhiro Seki, Masahiko Shibamoto, and Takashi Kamihigashi
Proceedings of the 5th Financial Narrative Processing Workshop 2861 - 2865 2023.12
Authorship：Lead author, Corresponding author
-
Turning News Texts into Business Sentiment Reviewed
Proceedings of the 44th European Conference on Information Retrieval (ECIR 2022) 311 - 315 2022.4
Authorship：Lead author, Last author, Corresponding author
-
News-based business sentiment and its properties as an economic index Reviewed
Kazuhiro Seki, Yusuke Ikuta, Yoichi Matsubayashi
INFORMATION PROCESSING & MANAGEMENT 59 ( 2 ) 2022.3
Authorship：Lead author, Corresponding author Publisher：ELSEVIER SCI LTD
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.
-
Cross-lingual text similarity exploiting neural machine translation models Reviewed
Kazuhiro Seki
Journal of Information Science 47 ( 3 ) 404 - 418 2021.6
Single Work
Authorship：Lead author, Last author, Corresponding author
-
Nowcasting Business Sentiment from Economic News Articles Reviewed
62 ( 5 ) 1288 - 1297 2021.5
-
S-APIR: News-Based Business Sentiment Index Reviewed
Kazuhiro Seki, Yusuke Ikuta
Proceedings of the 24th European Conference on Advances in Databases and Information Systems 2020.8
-
ニュース記事に基づく景気指標S-APIRの開発
関和広, 生田祐介, 松林洋一
第24回人工知能学会金融情報学研究会 2020.3
-
Effectiveness and Efficiency for Document Clustering in Biomedicine Reviewed International coauthorship
Kazuhiro Seki, Michael Ortiz, Javed Mostafa
Proceedings of the 10th International Workshop on Biomedical and Health Informatics 1620 - 1623 2019.11
Joint Work
Authorship：Lead author, Corresponding author
-
Dynamic Cluster-based Retrieval and Discovery for Biomedical Literature Reviewed International coauthorship
Michael Ortiz, Heejun Kim, Mika Wang, Kazuhiro Seki, Javed Mostafa
Proceedings of the 10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB) 2019.9
Joint Work
-
Estimating Business Sentiment from News Texts Reviewed
Kazuhiro Seki, Yusuke Ikuta
Proceedings of the 2nd IEEE Artificial Intelligence and Knowledge Engineering 2019.6
Joint Work
Authorship：Lead author, Corresponding author
-
On Cross-Lingual Text Similarity Using Neural Translation Models Reviewed
Kazuhiro Seki
Journal of Information Processing 27 315 - 321 2019
Single Work
Authorship：Lead author, Last author, Corresponding author
-
Exploring Neural Translation Models for Cross-Lingual Text Similarity Reviewed
Kazuhiro Seki
Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM) 1591 - 1594 2018.10
Single Work
Authorship：Lead author, Last author, Corresponding author
-
Construction and Application of Sentiment Lexicons in Finance Invited Reviewed
Kazuhiro Seki, Masahiko Shibamoto
International Journal of Multimedia Data Engineering and Management 9 ( 1 ) 22 - 35 2018.1
Joint Work
Authorship：Lead author, Corresponding author
-
Constructing Financial Sentiment Lexicons by Integrating Textual and Time-Series Data Reviewed
Kazuhiro Seki and Masahiko Shibamoto
Proceedings of the 2017 IEEE International Conference on Information Reuse and Integration 2017.8
Joint Work
Authorship：Lead author
-
Financial Sentiment Orientation of Word Combinations Reviewed
Kazuhiro Seki
Proceedings of the 20th International Conference on Knowledge Engineering and Knowledge Management 2016.11
Single Work
Authorship：Lead author
-
Leveraging Temporal Properties of News Events for Stock Market Prediction Reviewed
Akira Yoshihara, Kazuhiro Seki, and Kuniaki Uehara
Artificial Intelligence Research 2016.1
Joint Work
-
医療用語資源の語彙拡張と診療情報抽出への応用 Reviewed
東山翔平，関和広，上原邦昭
自然言語処理 22 ( 2 ) 77 - 106 2015.6
Joint Work
-
Cost-Sensitive Structured Perceptron Incorporating Category Hierarchy for Named Entity Recognition Invited Reviewed
Shohei Higashiyama, Mathieu Blondel, Kazuhiro Seki, and Kuniaki Uehara
Journal of Information and Communication Technology 2015.5
Joint Work
-
Detecting Vital Documents Using Negative Relevance Feedback in Distributed Realtime Computation Framework Reviewed
Shun Kawahara, Kazuhiro Seki, and Kuniaki Uehara
Proceedings of the 2015 Conference of the Pacific Association for Computational Linguistics (PACLING 2015) 2015.5
Joint Work