Analyzing Sentiment while Accounting for Negation Scope and Strength

Alexander Hogenboom; P v. Iterson; BMWT Heerschop; Flavius Frasincar; U Kaymak

Analyzing Sentiment while Accounting for Negation Scope and Strength

Alexander Hogenboom, P v. Iterson, BMWT Heerschop, Flavius Frasincar, U Kaymak

Research output: Contribution to conference › Poster › Academic

Abstract

Recent developments in automated sentiment analysis show a tendency of accounting for various aspects other than word frequencies. One of these aspects is negation. We compare several approaches to accounting for negation in sentiment analysis, differing in their methods of determining the scope of influence of a negation keyword. On a set of English movie review sentences, the best approach turns out to be to consider the first two words, following a negation keyword, to be negated by that keyword. Additionally, we propose to optimize the sentiment modification in case of negation to a value of -1.27 rather than -1

Original language	English
Pages	395-396
Number of pages	2
Publication status	Published - 3 Nov 2011
Event	Twenty-Third Benelux Conference on Artificial Intelligence (BNAIC 2011) - Ghent, Belgium Duration: 3 Nov 2011 → 4 Nov 2011

Conference

Conference	Twenty-Third Benelux Conference on Artificial Intelligence (BNAIC 2011)
City	Ghent, Belgium
Period	3/11/11 → 4/11/11

Bibliographical note

geen doi

Research programs

EUR ESE 32

Cite this

@conference{23dbbcd0e89d47b8b716c4425ff5c3ff,

title = "Analyzing Sentiment while Accounting for Negation Scope and Strength",

abstract = "Recent developments in automated sentiment analysis show a tendency of accounting for various aspects other than word frequencies. One of these aspects is negation. We compare several approaches to accounting for negation in sentiment analysis, differing in their methods of determining the scope of influence of a negation keyword. On a set of English movie review sentences, the best approach turns out to be to consider the first two words, following a negation keyword, to be negated by that keyword. Additionally, we propose to optimize the sentiment modification in case of negation to a value of -1.27 rather than -1",

author = "Alexander Hogenboom and {v. Iterson}, P and BMWT Heerschop and Flavius Frasincar and U Kaymak",

note = "geen doi; Twenty-Third Benelux Conference on Artificial Intelligence (BNAIC 2011) ; Conference date: 03-11-2011 Through 04-11-2011",

year = "2011",

month = nov,

day = "3",

language = "English",

pages = "395--396",

}

TY - CONF

T1 - Analyzing Sentiment while Accounting for Negation Scope and Strength

AU - Hogenboom, Alexander

AU - v. Iterson, P

AU - Heerschop, BMWT

AU - Frasincar, Flavius

AU - Kaymak, U

N1 - geen doi

PY - 2011/11/3

Y1 - 2011/11/3

N2 - Recent developments in automated sentiment analysis show a tendency of accounting for various aspects other than word frequencies. One of these aspects is negation. We compare several approaches to accounting for negation in sentiment analysis, differing in their methods of determining the scope of influence of a negation keyword. On a set of English movie review sentences, the best approach turns out to be to consider the first two words, following a negation keyword, to be negated by that keyword. Additionally, we propose to optimize the sentiment modification in case of negation to a value of -1.27 rather than -1

AB - Recent developments in automated sentiment analysis show a tendency of accounting for various aspects other than word frequencies. One of these aspects is negation. We compare several approaches to accounting for negation in sentiment analysis, differing in their methods of determining the scope of influence of a negation keyword. On a set of English movie review sentences, the best approach turns out to be to consider the first two words, following a negation keyword, to be negated by that keyword. Additionally, we propose to optimize the sentiment modification in case of negation to a value of -1.27 rather than -1

M3 - Poster

SP - 395

EP - 396

T2 - Twenty-Third Benelux Conference on Artificial Intelligence (BNAIC 2011)

Y2 - 3 November 2011 through 4 November 2011

ER -

Analyzing Sentiment while Accounting for Negation Scope and Strength

Abstract

Conference

Bibliographical note

Research programs

Fingerprint

Cite this