ECAI 2010 WASSA 2010 DLSi
UA
1st Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (WASSA)
To be held in conjuntion with the ECAI 2010 Joint Conference
· Venue
NEWS
06.09.2010 You can access the slides of some of the presentations
12.08.2010 Proceedings
12.08.2010 Final program.
28.06.2010 Tentative program.
14.06.2010 List of accepted full papers with abstracts available here.
07.06.2010 Notification to authors: June 9, 2010
19.05.2010 Extended paper submission: May 21, 2010
15.01.2010 Submission system is now open.
SCOPE OF THE WORKSHOP
The recent growth in access to technology and the Internet, together with the development of the Web 2.0 (Social Web), has led to the birth of new and challenging social phenomena. On the one hand, the possibility to express opinion "by anyone, anywhere, on anything", in blogs, forums, review sites has made it possible for people all around the world to take better and more informed decisions at the time of buying products or contracting services. On the other hand, companies and public persons are more informed on the impact they have on people, because the large amount of opinions expressed on them offers a direct and unbiased, global feedback. Moreover, the birth of new ways of communication and self-expression has changed the manner in which news born, even in the context of consecrated sources - newspapers, magazines - which are no longer the privileged starting point of news. The other side of the coin is that uncontrolled expression of opinions or points of view has given way to negative social behaviour. Due to the large volumes of such data, automatic systems need to be built to deal with it, both to encounter ways to positively exploit it, as well as determining appropriate measures to deal with the issues it raises.
CALL FOR PAPERS

Subjectivity and sentiment analysis (opinion mining) are two tasks of growing importance in the field of Natural Language Processing (NLP). This is due to their high applicability to real-life domains - e.g. marketing, policy-making, decision-support, e-Government - but also to the fact that they improve other NLP tasks, such as Information Extraction, Information Retrieval or Question Answering.

The aim of this workshop is to bring together researchers in computational linguistics, dealing with subjectivity and sentiment analysis, but also from other disciplines related to this area: psychologists, sociologists, economists etc., with the objective of facilitating an interdisciplinary dialogue on the analysis, requirements, issues and applications of the study of subjectivity and sentiment in the context of traditional and emerging text types. We are especially interested in real-life applications, comparisons between approaches on different text types, in a monolingual or multilingual setting, joint topic and sentiment analysis, creation, annotation and evaluation of resources.

Download the pdf version of the CFP.

TOPICS OF INTEREST

We welcome original and unpublished evaluation or position papers on all subjectivity and sentiment-related issues. Some suggested topics include, but are not limited to:

  • Subjectivity and opinion retrieval, extraction, categorization, aggregation and summarization
  • Topic and sentiment studies and applications of topic-sentiment analysis
  • Mass opinion estimation based on NLP and statistical models.
  • Domain, topic and genre dependency of sentiment analysis
  • Ambiguity issues and word sense disambiguation of subjective language
  • Intrinsic and extrinsic evaluation methodologies
  • Proposals involving the computational treatment of large amounts of data
  • Pragmatic analysis of the opinion mining task
  • Annotation schemes for subjectivity and corpora creation
  • Improvement of NLP tasks using subjectivity and/or sentiment analysis
  • Real-world applications of opinion mining systems
  • Use of Semantic Web Technologies for subjectivity and sentiment analysis


wassa2010 [at] dlsi.ua.es   |   Last updated: 12:08 06/09/2010
Accesses since 2010-01-15: Comptador
XHTML 1.0 & CSS2 compliant.