Economic Activity Recognition

Nuno Miguel Cavalheiro Marques

Economic Activity Recognition

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

Abstract

The identification of the economic activities performed by a company and its recognition from the text in the company’s web site, is a task that has not yet received much attention in text mining and business intelligence applications. In this paper, we present a system de- signed for recognizing economic activities performed by companies from text obtained from their websites. The applied strategy makes use of the composition of an economic activity, which reduces the size of the required gazetteers. The system achieved a recall of 63%, a precision of 61%, and an F1-measure of 62%.

Original language	Unknown
Title of host publication	EPIA LOCAL Proceedings - Advances In Artificial Intelligence
Publisher	APPIA - Associação Portuguesa para a Inteligência Artificial
Pages	332-343
ISBN (Print)	978-989-95489-1-6
Publication status	Published - 1 Jan 2013
Event	EPIA - XVI Portuguese Conference on Artificial Intelligence - Duration: 1 Jan 2013 → …

Conference

Conference	EPIA - XVI Portuguese Conference on Artificial Intelligence
Period	1/01/13 → …

Cite this

@inproceedings{5d8e3a17b1e140928f3c8b406a63241a,

title = "Economic Activity Recognition",

abstract = "The identification of the economic activities performed by a company and its recognition from the text in the company{\textquoteright}s web site, is a task that has not yet received much attention in text mining and business intelligence applications. In this paper, we present a system de- signed for recognizing economic activities performed by companies from text obtained from their websites. The applied strategy makes use of the composition of an economic activity, which reduces the size of the required gazetteers. The system achieved a recall of 63%, a precision of 61%, and an F1-measure of 62%.",

keywords = "business intelligence, information extraction, activity recognition",

author = "{Cavalheiro Marques}, {Nuno Miguel}",

year = "2013",

month = jan,

day = "1",

language = "Unknown",

isbn = "978-989-95489-1-6",

pages = "332--343",

booktitle = "EPIA LOCAL Proceedings - Advances In Artificial Intelligence",

publisher = "APPIA - Associa{\c c}{\~a}o Portuguesa para a Intelig{\^e}ncia Artificial",

note = "EPIA - XVI Portuguese Conference on Artificial Intelligence ; Conference date: 01-01-2013",

}

TY - GEN

T1 - Economic Activity Recognition

AU - Cavalheiro Marques, Nuno Miguel

PY - 2013/1/1

Y1 - 2013/1/1

N2 - The identification of the economic activities performed by a company and its recognition from the text in the company’s web site, is a task that has not yet received much attention in text mining and business intelligence applications. In this paper, we present a system de- signed for recognizing economic activities performed by companies from text obtained from their websites. The applied strategy makes use of the composition of an economic activity, which reduces the size of the required gazetteers. The system achieved a recall of 63%, a precision of 61%, and an F1-measure of 62%.

AB - The identification of the economic activities performed by a company and its recognition from the text in the company’s web site, is a task that has not yet received much attention in text mining and business intelligence applications. In this paper, we present a system de- signed for recognizing economic activities performed by companies from text obtained from their websites. The applied strategy makes use of the composition of an economic activity, which reduces the size of the required gazetteers. The system achieved a recall of 63%, a precision of 61%, and an F1-measure of 62%.

KW - business intelligence

KW - information extraction

KW - activity recognition

M3 - Conference contribution

SN - 978-989-95489-1-6

SP - 332

EP - 343

BT - EPIA LOCAL Proceedings - Advances In Artificial Intelligence

PB - APPIA - Associação Portuguesa para a Inteligência Artificial

T2 - EPIA - XVI Portuguese Conference on Artificial Intelligence

Y2 - 1 January 2013

ER -