Bootstrapping Yahoo! Finance by Wikipedia for Competitor Mining

Tong Ruan; Lijuan Xue; Haofen Wang; Jeff Z. Pan

doi:10.1007/978-3-319-31676-5_8

Bootstrapping Yahoo! Finance by Wikipedia for Competitor Mining

Tong Ruan, Lijuan Xue, Haofen Wang, Jeff Z. Pan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Competitive intelligence, one of the key factors of enterprise risk management and decision support, depends on knowledge bases that contain a large amount of competitive information. A variety of finance websites have collected competitive information manually, which can be used as knowledge bases. Yahoo! Finance is one of the largest and most successful finance websites among them. However, they have problems of incompleteness, lack of competitive domain, and not-in-time updating. Wikipedia, which was built with collective wisdom and contains plenty of useful information in various forms, can solve the above-mentioned problems effectively, thus helping build a more comprehensive knowledge base. In this paper, we propose a novel semi-supervised approach to identify competitor information and competitive domain from Wikipedia based on a multi-strategy learning algorithm. More precisely, we leverage seeds of competition between companies and competition between products to distantly supervise the learning process to find text patterns in free texts. Considering that competitive information can be inferred from events, we design a learning-based method to determine event description sentences. The whole process is iteratively performed. The experimental results show the effectiveness of our approach. Moreover, the results extracted from Wikipedia supplement 14,000 competitor pairs and 8,000 competitive domains between rival companies to Yahoo! Finance.

Original language	English
Title of host publication	Semantic Technology
Subtitle of host publication	5th Joint International Conference, JIST 2015, Yichang, China, November 11-13, 2015, Revised Selected Papers
Editors	Guilin Qi, Kouji Kozaki, Jeff Z. Pan, Siwei Yu
Place of Publication	Cham
Publisher	Springer International Publishing
Pages	108-126
Number of pages	19
ISBN (Electronic)	978-3-319-31676-5
ISBN (Print)	978-3-319-31675-8
DOIs	https://doi.org/10.1007/978-3-319-31676-5_8
Publication status	Published - 20 Mar 2016
Event	5th Joint International Semantic Technology Conference - Yichang, China Duration: 11 Nov 2015 → 13 Nov 2015 http://www.jist2015.org/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer, Cham
Volume	9544
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	5th Joint International Semantic Technology Conference
Abbreviated title	JIST 2015
Country/Territory	China
City	Yichang
Period	11/11/15 → 13/11/15
Internet address	http://www.jist2015.org/

Keywords

Competitor mining
Multi-strategy learning
Distant supervision
Relation reasoning

Access to Document

10.1007/978-3-319-31676-5_8Licence: All Rights Reserved

https://link.springer.com/chapter/10.1007/978-3-319-31676-5_8Licence: All Rights Reserved

Cite this

Ruan, T., Xue, L., Wang, H., & Pan, J. Z. (2016). Bootstrapping Yahoo! Finance by Wikipedia for Competitor Mining. In G. Qi, K. Kozaki, J. Z. Pan, & S. Yu (Eds.), Semantic Technology: 5th Joint International Conference, JIST 2015, Yichang, China, November 11-13, 2015, Revised Selected Papers (pp. 108-126). (Lecture Notes in Computer Science; Vol. 9544). Springer International Publishing. https://doi.org/10.1007/978-3-319-31676-5_8

Ruan, Tong ; Xue, Lijuan ; Wang, Haofen et al. / Bootstrapping Yahoo! Finance by Wikipedia for Competitor Mining. Semantic Technology: 5th Joint International Conference, JIST 2015, Yichang, China, November 11-13, 2015, Revised Selected Papers. editor / Guilin Qi ; Kouji Kozaki ; Jeff Z. Pan ; Siwei Yu. Cham : Springer International Publishing, 2016. pp. 108-126 (Lecture Notes in Computer Science).

@inproceedings{492bd14a7a66433691a0f8946067f56b,

title = "Bootstrapping Yahoo! Finance by Wikipedia for Competitor Mining",

abstract = "Competitive intelligence, one of the key factors of enterprise risk management and decision support, depends on knowledge bases that contain a large amount of competitive information. A variety of finance websites have collected competitive information manually, which can be used as knowledge bases. Yahoo! Finance is one of the largest and most successful finance websites among them. However, they have problems of incompleteness, lack of competitive domain, and not-in-time updating. Wikipedia, which was built with collective wisdom and contains plenty of useful information in various forms, can solve the above-mentioned problems effectively, thus helping build a more comprehensive knowledge base. In this paper, we propose a novel semi-supervised approach to identify competitor information and competitive domain from Wikipedia based on a multi-strategy learning algorithm. More precisely, we leverage seeds of competition between companies and competition between products to distantly supervise the learning process to find text patterns in free texts. Considering that competitive information can be inferred from events, we design a learning-based method to determine event description sentences. The whole process is iteratively performed. The experimental results show the effectiveness of our approach. Moreover, the results extracted from Wikipedia supplement 14,000 competitor pairs and 8,000 competitive domains between rival companies to Yahoo! Finance.",

keywords = "Competitor mining, Multi-strategy learning, Distant supervision, Relation reasoning",

author = "Tong Ruan and Lijuan Xue and Haofen Wang and Pan, {Jeff Z.}",

year = "2016",

month = mar,

day = "20",

doi = "10.1007/978-3-319-31676-5_8",

language = "English",

isbn = "978-3-319-31675-8",

series = "Lecture Notes in Computer Science",

publisher = "Springer International Publishing",

pages = "108--126",

editor = "Guilin Qi and Kouji Kozaki and Pan, {Jeff Z.} and Siwei Yu",

booktitle = "Semantic Technology",

note = "5th Joint International Semantic Technology Conference, JIST 2015 ; Conference date: 11-11-2015 Through 13-11-2015",

url = "http://www.jist2015.org/",

}

Ruan, T, Xue, L, Wang, H & Pan, JZ 2016, Bootstrapping Yahoo! Finance by Wikipedia for Competitor Mining. in G Qi, K Kozaki, JZ Pan & S Yu (eds), Semantic Technology: 5th Joint International Conference, JIST 2015, Yichang, China, November 11-13, 2015, Revised Selected Papers. Lecture Notes in Computer Science, vol. 9544, Springer International Publishing, Cham, pp. 108-126, 5th Joint International Semantic Technology Conference, Yichang, China, 11/11/15. https://doi.org/10.1007/978-3-319-31676-5_8

Bootstrapping Yahoo! Finance by Wikipedia for Competitor Mining. / Ruan, Tong; Xue, Lijuan; Wang, Haofen et al.

Semantic Technology: 5th Joint International Conference, JIST 2015, Yichang, China, November 11-13, 2015, Revised Selected Papers. ed. / Guilin Qi; Kouji Kozaki; Jeff Z. Pan; Siwei Yu. Cham : Springer International Publishing, 2016. p. 108-126 (Lecture Notes in Computer Science; Vol. 9544).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Bootstrapping Yahoo! Finance by Wikipedia for Competitor Mining

AU - Ruan, Tong

AU - Xue, Lijuan

AU - Wang, Haofen

AU - Pan, Jeff Z.

PY - 2016/3/20

Y1 - 2016/3/20

N2 - Competitive intelligence, one of the key factors of enterprise risk management and decision support, depends on knowledge bases that contain a large amount of competitive information. A variety of finance websites have collected competitive information manually, which can be used as knowledge bases. Yahoo! Finance is one of the largest and most successful finance websites among them. However, they have problems of incompleteness, lack of competitive domain, and not-in-time updating. Wikipedia, which was built with collective wisdom and contains plenty of useful information in various forms, can solve the above-mentioned problems effectively, thus helping build a more comprehensive knowledge base. In this paper, we propose a novel semi-supervised approach to identify competitor information and competitive domain from Wikipedia based on a multi-strategy learning algorithm. More precisely, we leverage seeds of competition between companies and competition between products to distantly supervise the learning process to find text patterns in free texts. Considering that competitive information can be inferred from events, we design a learning-based method to determine event description sentences. The whole process is iteratively performed. The experimental results show the effectiveness of our approach. Moreover, the results extracted from Wikipedia supplement 14,000 competitor pairs and 8,000 competitive domains between rival companies to Yahoo! Finance.

AB - Competitive intelligence, one of the key factors of enterprise risk management and decision support, depends on knowledge bases that contain a large amount of competitive information. A variety of finance websites have collected competitive information manually, which can be used as knowledge bases. Yahoo! Finance is one of the largest and most successful finance websites among them. However, they have problems of incompleteness, lack of competitive domain, and not-in-time updating. Wikipedia, which was built with collective wisdom and contains plenty of useful information in various forms, can solve the above-mentioned problems effectively, thus helping build a more comprehensive knowledge base. In this paper, we propose a novel semi-supervised approach to identify competitor information and competitive domain from Wikipedia based on a multi-strategy learning algorithm. More precisely, we leverage seeds of competition between companies and competition between products to distantly supervise the learning process to find text patterns in free texts. Considering that competitive information can be inferred from events, we design a learning-based method to determine event description sentences. The whole process is iteratively performed. The experimental results show the effectiveness of our approach. Moreover, the results extracted from Wikipedia supplement 14,000 competitor pairs and 8,000 competitive domains between rival companies to Yahoo! Finance.

KW - Competitor mining

KW - Multi-strategy learning

KW - Distant supervision

KW - Relation reasoning

U2 - 10.1007/978-3-319-31676-5_8

DO - 10.1007/978-3-319-31676-5_8

M3 - Conference contribution

SN - 978-3-319-31675-8

T3 - Lecture Notes in Computer Science

SP - 108

EP - 126

BT - Semantic Technology

A2 - Qi, Guilin

A2 - Kozaki, Kouji

A2 - Pan, Jeff Z.

A2 - Yu, Siwei

PB - Springer International Publishing

CY - Cham

T2 - 5th Joint International Semantic Technology Conference

Y2 - 11 November 2015 through 13 November 2015

ER -

Ruan T, Xue L, Wang H, Pan JZ. Bootstrapping Yahoo! Finance by Wikipedia for Competitor Mining. In Qi G, Kozaki K, Pan JZ, Yu S, editors, Semantic Technology: 5th Joint International Conference, JIST 2015, Yichang, China, November 11-13, 2015, Revised Selected Papers. Cham: Springer International Publishing. 2016. p. 108-126. (Lecture Notes in Computer Science). doi: 10.1007/978-3-319-31676-5_8

Bootstrapping Yahoo! Finance by Wikipedia for Competitor Mining

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this