The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Nous proposons une méthode d'attribution de polarité aux informations causales extraites d'articles financiers japonais concernant la performance commerciale des entreprises. Notre méthode attribue une polarité (positive ou négative) aux informations causales en fonction de la performance de l'entreprise, par exemple "zidousya no uriage ga koutyou: (Les ventes de voitures sont bonnes)" (La polarité positive est attribuée dans cet exemple). Nous pouvons utiliser des expressions causales assignées à la polarité par notre méthode, par exemple, pour analyser de manière circonstancielle le contenu des articles concernant les performances commerciales. Premièrement, notre méthode classe les articles concernant performances commerciales en articles positifs et articles négatifs. En les utilisant, notre méthode attribue une polarité (positive ou négative) aux informations causales extraites de l'ensemble des articles concernant les performances commerciales, bien que notre méthode nécessite un ensemble de données de formation pour classer les articles concernant les performances commerciales en positifs et négatifs. Ainsi, même s'il existe des informations causales n'apparaissant pas dans l'ensemble de données de formation pour classer les articles concernant les performances de l'entreprise en positifs et négatifs, notre méthode est capable de lui attribuer une polarité. en utilisant les informations statistiques de cet ensemble d'articles classifiés. Nous avons évalué notre méthode et confirmé qu'elle atteignait respectivement 74.4 % de précision et 50.4 % de rappel de l'attribution de la polarité positive, et 76.8 % de précision et 61.5 % de rappel de l'attribution de la polarité négative.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Hiroyuki SAKAI, Shigeru MASUYAMA, "Assigning Polarity to Causal Information in Financial Articles on Business Performance of Companies" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 12, pp. 2341-2350, December 2009, doi: 10.1587/transinf.E92.D.2341.
Abstract: We propose a method of assigning polarity to causal information extracted from Japanese financial articles concerning business performance of companies. Our method assigns polarity (positive or negative) to causal information in accordance with business performance, e.g. "zidousya no uriage ga koutyou: (Sales of cars are good)" (The polarity positive is assigned in this example). We may use causal expressions assigned polarity by our method, e.g., to analyze content of articles concerning business performance circumstantially. First, our method classifies articles concerning business performance into positive articles and negative articles. Using them, our method assigns polarity (positive or negative) to causal information extracted from the set of articles concerning business performance. Although our method needs training dataset for classifying articles concerning business performance into positive and negative ones, our method does not need a training dataset for assigning polarity to causal information. Hence, even if causal information not appearing in the training dataset for classifying articles concerning business performance into positive and negative ones exist, our method is able to assign it polarity by using statistical information of this classified sets of articles. We evaluated our method and confirmed that it attained 74.4% precision and 50.4% recall of assigning polarity positive, and 76.8% precision and 61.5% recall of assigning polarity negative, respectively.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.2341/_p
Copier
@ARTICLE{e92-d_12_2341,
author={Hiroyuki SAKAI, Shigeru MASUYAMA, },
journal={IEICE TRANSACTIONS on Information},
title={Assigning Polarity to Causal Information in Financial Articles on Business Performance of Companies},
year={2009},
volume={E92-D},
number={12},
pages={2341-2350},
abstract={We propose a method of assigning polarity to causal information extracted from Japanese financial articles concerning business performance of companies. Our method assigns polarity (positive or negative) to causal information in accordance with business performance, e.g. "zidousya no uriage ga koutyou: (Sales of cars are good)" (The polarity positive is assigned in this example). We may use causal expressions assigned polarity by our method, e.g., to analyze content of articles concerning business performance circumstantially. First, our method classifies articles concerning business performance into positive articles and negative articles. Using them, our method assigns polarity (positive or negative) to causal information extracted from the set of articles concerning business performance. Although our method needs training dataset for classifying articles concerning business performance into positive and negative ones, our method does not need a training dataset for assigning polarity to causal information. Hence, even if causal information not appearing in the training dataset for classifying articles concerning business performance into positive and negative ones exist, our method is able to assign it polarity by using statistical information of this classified sets of articles. We evaluated our method and confirmed that it attained 74.4% precision and 50.4% recall of assigning polarity positive, and 76.8% precision and 61.5% recall of assigning polarity negative, respectively.},
keywords={},
doi={10.1587/transinf.E92.D.2341},
ISSN={1745-1361},
month={December},}
Copier
TY - JOUR
TI - Assigning Polarity to Causal Information in Financial Articles on Business Performance of Companies
T2 - IEICE TRANSACTIONS on Information
SP - 2341
EP - 2350
AU - Hiroyuki SAKAI
AU - Shigeru MASUYAMA
PY - 2009
DO - 10.1587/transinf.E92.D.2341
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2009
AB - We propose a method of assigning polarity to causal information extracted from Japanese financial articles concerning business performance of companies. Our method assigns polarity (positive or negative) to causal information in accordance with business performance, e.g. "zidousya no uriage ga koutyou: (Sales of cars are good)" (The polarity positive is assigned in this example). We may use causal expressions assigned polarity by our method, e.g., to analyze content of articles concerning business performance circumstantially. First, our method classifies articles concerning business performance into positive articles and negative articles. Using them, our method assigns polarity (positive or negative) to causal information extracted from the set of articles concerning business performance. Although our method needs training dataset for classifying articles concerning business performance into positive and negative ones, our method does not need a training dataset for assigning polarity to causal information. Hence, even if causal information not appearing in the training dataset for classifying articles concerning business performance into positive and negative ones exist, our method is able to assign it polarity by using statistical information of this classified sets of articles. We evaluated our method and confirmed that it attained 74.4% precision and 50.4% recall of assigning polarity positive, and 76.8% precision and 61.5% recall of assigning polarity negative, respectively.
ER -