Wang, Bo, Liakata, Maria, Zubiaga, Arkaitz, Procter, Rob and Jensen, Eric (2016) SMILE : Twitter emotion classification using domain adaptation. In: 4th Workshop on Sentiment Analysis where AI meets Psychology (SAAIP 2016), New York, 10 Jul 2016. Published in: CEUR Workshop Proceedings, 1619 pp. 15-21. ISSN 1613-0073.

Preview

PDF WRAP_Chen_paper3.pdf - Published Version - Requires a PDF viewer. Download (999Kb) | Preview

Request Changes to record.

Abstract

Despite the widely spread research interest in social media sentiment analysis, sentiment and emotion classification across different domains and on Twitter data remains a challenging task. Here we set out to find an effective approach for tackling a cross-domain emotion classification task on a set of Twitter data involving social media discourse around arts and cultural experiences, in the context of museums. While most existing work in domain adaptation has focused on feature-based or/and instance-based adaptation methods, in this work we study a model-based adaptive SVM approach as we believe its flexibility and efficiency is more suitable for the task at hand. We conduct a series of experiments and compare our system with a set of baseline methods. Our results not only show a superior performance in terms of accuracy and computational efficiency compared to the baselines, but also shed light on how different ratios of labelled target-domain data used for adaptation can affect classification performance.

Item Type:	Conference Item (Paper)
Subjects:	A General Works > AM Museums (General). Collectors and collecting (General) H Social Sciences > HM Sociology
Divisions:	Faculty of Science > Computer Science
Library of Congress Subject Headings (LCSH):	Online social networks, Museums -- Social aspects, Emotions -- Classification
Journal or Publication Title:	CEUR Workshop Proceedings
Publisher:	Sun SITE Central Europe
ISSN:	1613-0073
Official Date:	July 2016
Dates:	Date Event July 2016 Available
Date of first compliant deposit:	19 July 2016
Volume:	1619
Page Range:	pp. 15-21
Status:	Peer Reviewed
Publication Status:	Published
Funder:	Arts & Humanities Research Council (Great Britain) (AHRC)
Conference Paper Type:	Paper
Title of Event:	4th Workshop on Sentiment Analysis where AI meets Psychology (SAAIP 2016)
Type of Event:	Conference
Location of Event:	New York
Date(s) of Event:	10 Jul 2016
Related URLs:	Organisation

Request changes or add full text files to a record

Repository staff actions (login required)

View Item

Downloads