Damping sentiment analysis in online communication : discussions, monologs and dialogs

Thelwall, Mike (Statistical Cybermetrics Research Group, University of Wolverhampton, Wolverhampton, UK) ; Buckley, Kevan (Statistical Cybermetrics Research Group, University of Wolverhampton, Wolverhampton, UK) ; Paltogloiu, George (Statistical Cybermetrics Research Group, University of Wolverhampton, Wolverhampton, UK) ; Skowron, Marcin (Austrian Research Institute for Artificial Intelligence, Vienna, Austria) ; Garcia, David (Chair of Systems Design, ETH Zurich, Zurich, Switzerland) ; Gobron, Stéphane (School of Engineering – HE-Arc Ingénierie, HES-SO // University of Applied Sciences Western Switzerland) ; Ahn, Junghyun (SCI IC RB Group, EPFL, Lausanne, Switzerland) ; Kappas, Arvid (School of Humanities and Social Sciences, Jacobs University Bremen, Bremen, Germany) ; Küster, Dennis (School of Humanities and Social Sciences, Jacobs University Bremen, Bremen, Germany) ; Holyst, Janusz A. (Center of Excellence for Complex Systems Research, Faculty of Physics, Warsaw University of Technology, Warsaw, Poland)

Sentiment analysis programs are now sometimes used to detect patterns of sentiment use over time in online communication and to help automated systems interact better with users. Nevertheless, it seems that no previous published study has assessed whether the position of individual texts within on-going communication can be exploited to help detect their sentiments. This article assesses apparent sentiment anomalies in on-going communication – texts assigned significantly different sentiment strength to the average of previous texts – to see whether their classification can be improved. The results suggest that a damping procedure to reduce sudden large changes in sentiment can improve classification accuracy but that the optimal procedure will depend on the type of texts processed.


Keywords:
Faculty:
Ingénierie et Architecture
School:
HE-Arc Ingénierie
Institute:
Aucun institut
Subject(s):
Ingénierie
Publisher:
Berlin, Heidelberg, Springer
Date:
2013-06
Berlin, Heidelberg
Springer
Pagination:
12 p.
Published in:
Computational Linguistics and Intelligent Text Processing: CICLing 2013: Lecture Notes in Computer Science
Author of the book:
Gelbukh, A. ; Editor
DOI:
ISSN:
0302-9743
ISBN:
978-3-642-37255-1
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2019-05-21, last modified 2019-06-17

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)