Call for Papers

Sentiment and Subjectivity in Text

Workshop at the Annual Meeting of the Association of Computational
Linguistics (COLING-ACL 2006)

Sydney, Australia 


** Submission Deadline: April 7, 2006 **


Sentiment and subjectivity in text constitute a problem that is
orthogonal to typical topic detection tasks in text
classification. Despite the lack of a precise definition of sentiment
or subjectivity, headway has been made in matching human judgments by
automatic means. Such systems can prove useful in a variety of
contexts. In many applications it is important to distinguish what an
author is talking about from his or her subjective stance towards the
topic. If the writing is highly subjective, as for example in an
editorial text or comment, the text should be treated differently than
if it were a mostly objective presentation of facts, as for example in
a newswire. Information extraction, summarization, and question
answering can benefit from an accurate separation of subjective
content from objective content. Furthermore, the particular sentiment
expressed by an author towards a topic is important for "opinion
mining", i.e. the extraction of prevalent opinions about topics or
items from a collection of texts. Similarly, in business intelligence
it is important to automatically extract positive and negative
perceptions about features of a product or service.
Over the past several years, there has been an increasing number of
publications focused on the detection and classification of sentiment
and subjectivity in text.

The purpose of this workshop is to bring together researchers to share
recent work in this area.

Workshop participants and contributors are expected to come from
various areas of research: Information Retrieval, Question Answering,
Text Categorization, Machine Learning, etc.

Topics of interest include, but are not limited to:
*      relevance of sentiment and subjectivity detection for question
answering, information retrieval, and opinion mining
*	   detection of sentiment strength
*	   supervised, weakly supervised and unsupervised learning
techniques for sentiment and subjectivity detection
*	   automatic and semi-automatic discovery of subjectivity and
sentiment indicators
*	  feature analysis and feature selection for sentiment and
subjectivity detection: bag-of-words approaches and beyond
*	     topic-independent subjectivity and sentiment
identification
*	identification of the target of subjective and sentiment
expressions
*	attribution of opinion and sentiment
*	sentiment/subjectivity corpora and annotation
*	sentiment lexica
*	discourse analysis and subjectivity/sentiment
*       applications of sentiment and subjectivity analysis, such as 
		     * text filtering
		       * tracking public opinion over time
			 * analysis of survey responses
			   * automated chat systems (chatbots) and
			   responsive characters in software games
				      * customer relation management
					* summarization of reviews 



IMPORTANT DATES AND DEADLINES

Paper submission deadline: April 7, 2006
Notification of acceptance: May 15, 2006
Camera ready copy: June 6, 2006


SUBMISSION INFORMATION

The language of the workshop is English.
All submissions will be reviewed anonymously. All accepted papers will
be presented in oral sessions of the workshop and collected in the
printed proceedings. 



ORGANIZERS
Michael Gamon (Microsoft Research)
Anthony Aue (Microsoft Research)

CONTACT
For questions, comments, etc. please send email to mgamon AT microsoft
Dot com.

Program Committee:
Shlomo Argamon (Illinois Institute of Technology)
Claire Cardie (Cornell University) 
Graeme Hirst (University of Toronto) 
Eduard Hovy (USC Information Sciences Institute) 
Aravind Joshi (University of Pennsylvania) 
Jussi Karlgren (Swedish Institute of Computer Science) 
Roy Lipski 
Ana-Maria Popescu (University of Washington) 
Dragomir Radev (University of Michigan) 
Maarten de Rijke (University of Amsterdam)
Marc Schrvder (DFKI)
Michael Strube (EML Research) 
Pero Subasic (Yahoo Inc.)
Peter Turney (National Research Council Canada) 
Vzlem Uzuner (Massachusetts Institute of Technology) 
Casey Whitelaw (University of Sydney) 
Janyce Wiebe (University of Pittsburgh)