A deep learning-based sports player evaluation model based on game statistics and news articles

Young Joon Park, Hyung Seok Kim, Donghwa Kim, Hankyu Lee, Seoung Bum Kim, Pilsung Kang

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Player evaluation is a key component of the question-answering (QA) system in sports. Since existing player evaluation methods heavily rely on game statistics, they cannot capture the qualitative impact of each player during a game, which can be exploited using news articles after the game. In this paper, we propose a deep learning-based player evaluation model by combining both quantitative game statistics and the qualitative analyses provided by news articles. Players are classified as positive or negative based on their performance during certain periods, and news articles in the same period are annotated using the player's class. Then, the relationship between news articles and the annotated polarity is investigated by a deep neural network, which can deal with the high dimensionality of the text data. Since there is no explicit polarity label for news articles, we use the change in game statistics in target periods to annotate related sentences. The proposed system is applied to a Korean professional baseball league (KBO) and it is shown to be capable of understanding the sentence polarity of news articles on player performances.

Original languageEnglish
JournalKnowledge-Based Systems
DOIs
Publication statusAccepted/In press - 2017

Fingerprint

Sports
Statistics
Labels
Deep learning
Evaluation model
News

Keywords

  • Baseball
  • Deep neural network
  • Sentence polarity
  • Sports player evaluation

ASJC Scopus subject areas

  • Software
  • Management Information Systems
  • Information Systems and Management
  • Artificial Intelligence

Cite this

A deep learning-based sports player evaluation model based on game statistics and news articles. / Park, Young Joon; Kim, Hyung Seok; Kim, Donghwa; Lee, Hankyu; Kim, Seoung Bum; Kang, Pilsung.

In: Knowledge-Based Systems, 2017.

Research output: Contribution to journalArticle

@article{cd909af37cb8459fb99d001150b0e233,
title = "A deep learning-based sports player evaluation model based on game statistics and news articles",
abstract = "Player evaluation is a key component of the question-answering (QA) system in sports. Since existing player evaluation methods heavily rely on game statistics, they cannot capture the qualitative impact of each player during a game, which can be exploited using news articles after the game. In this paper, we propose a deep learning-based player evaluation model by combining both quantitative game statistics and the qualitative analyses provided by news articles. Players are classified as positive or negative based on their performance during certain periods, and news articles in the same period are annotated using the player's class. Then, the relationship between news articles and the annotated polarity is investigated by a deep neural network, which can deal with the high dimensionality of the text data. Since there is no explicit polarity label for news articles, we use the change in game statistics in target periods to annotate related sentences. The proposed system is applied to a Korean professional baseball league (KBO) and it is shown to be capable of understanding the sentence polarity of news articles on player performances.",
keywords = "Baseball, Deep neural network, Sentence polarity, Sports player evaluation",
author = "Park, {Young Joon} and Kim, {Hyung Seok} and Donghwa Kim and Hankyu Lee and Kim, {Seoung Bum} and Pilsung Kang",
year = "2017",
doi = "10.1016/j.knosys.2017.09.028",
language = "English",
journal = "Knowledge-Based Systems",
issn = "0950-7051",
publisher = "Elsevier",

}

TY - JOUR

T1 - A deep learning-based sports player evaluation model based on game statistics and news articles

AU - Park, Young Joon

AU - Kim, Hyung Seok

AU - Kim, Donghwa

AU - Lee, Hankyu

AU - Kim, Seoung Bum

AU - Kang, Pilsung

PY - 2017

Y1 - 2017

N2 - Player evaluation is a key component of the question-answering (QA) system in sports. Since existing player evaluation methods heavily rely on game statistics, they cannot capture the qualitative impact of each player during a game, which can be exploited using news articles after the game. In this paper, we propose a deep learning-based player evaluation model by combining both quantitative game statistics and the qualitative analyses provided by news articles. Players are classified as positive or negative based on their performance during certain periods, and news articles in the same period are annotated using the player's class. Then, the relationship between news articles and the annotated polarity is investigated by a deep neural network, which can deal with the high dimensionality of the text data. Since there is no explicit polarity label for news articles, we use the change in game statistics in target periods to annotate related sentences. The proposed system is applied to a Korean professional baseball league (KBO) and it is shown to be capable of understanding the sentence polarity of news articles on player performances.

AB - Player evaluation is a key component of the question-answering (QA) system in sports. Since existing player evaluation methods heavily rely on game statistics, they cannot capture the qualitative impact of each player during a game, which can be exploited using news articles after the game. In this paper, we propose a deep learning-based player evaluation model by combining both quantitative game statistics and the qualitative analyses provided by news articles. Players are classified as positive or negative based on their performance during certain periods, and news articles in the same period are annotated using the player's class. Then, the relationship between news articles and the annotated polarity is investigated by a deep neural network, which can deal with the high dimensionality of the text data. Since there is no explicit polarity label for news articles, we use the change in game statistics in target periods to annotate related sentences. The proposed system is applied to a Korean professional baseball league (KBO) and it is shown to be capable of understanding the sentence polarity of news articles on player performances.

KW - Baseball

KW - Deep neural network

KW - Sentence polarity

KW - Sports player evaluation

UR - http://www.scopus.com/inward/record.url?scp=85031092498&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031092498&partnerID=8YFLogxK

U2 - 10.1016/j.knosys.2017.09.028

DO - 10.1016/j.knosys.2017.09.028

M3 - Article

AN - SCOPUS:85031092498

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

ER -