IPM 2014 - Computational Approaches to the Retrieval, Mining and Classification of Affective Texts

Computational Approaches to the Retrieval, Mining and Classification of Affective Texts
In the world today, people’s lives are marked by the growing influence of the Social Web (the web of interaction and communication). More than ever before, people are willing and happy to share their lives, knowledge, experience and thoughts with the entire world, through blogs, forums, wikis, review sites or microblogs. They are active participators, expressing opinions about and commenting on events that take place around the world and in all different spheres of society. The large volume of subjective information present on the Internet, in reviews, forums, blogs, microblogs and social network communications has produced an important shift in the manner in which people communicate, share knowledge and emotions and influence the social, political and economic behavior worldwide. In consequence, this new reality has led to important transformations in the manner, extent and rapidness in which news and their associated opinions circulate, leading to new and challenging social, economical and psychological phenomena.
In order to study these phenomena and address the issue of extracting the crucial knowledge that nowadays is contained in opinionated data, new fields of research were born in Natural Language Processing (NLP), aiming at detecting subjectivity in text and/or extracting and classifying opinions into different sets (usually positive, negative and neutral). The main issues that were tackled in NLP are subjectivity analysis (dealing with “private states” (Banfield, 1982), a term that encloses sentiment, opinions, emotions, evaluations, beliefs and speculations) sentiment analysis and opinion mining, although different terminologies have been used to denote the approaches taken (e.g. review mining, appraisal extraction) and sentiment analysis and opinion mining have been used interchangeably, as they are considered by some authors to point to the same task (Pang and Lee, 2008). A closely related task is also emotion detection, dealing with the classification of texts according to the emotion expressed. All these research areas are part of the wider field in Artificial Intelligence denominated affective computing (Picard, 1995).
As a follow on from the “4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis” (WASSA 2013) - http://optima.jrc.it/wassa2013/index.htm, papers are invited that address the topic of Computational Approaches to the Retrieval, Mining and Classification of Affective Texts. Possible topics for consideration are:
Lexical semantic resources, corpora and annotations for subjectivity, sentiment and social media analysis; (semi-)automatic corpora generation and annotation
Opinion retrieval, extraction, categorization, aggregation and summarization
Trend detection in social media using subjectivity and sentiment analysis techniques
Data linking through social networks based on affect-related NLP methods
Impact of affective data from social media
Mass opinion estimation based on NLP and statistical models
Online reputation management
Submissions guidelines
The deadline for submissions is 15th August 2013 and should be submitted via the journal’s online submission system available through the journal homepage:
http://www.journals.elsevier.com/information-proce...
or directly via:
http://ees.elsevier.com/ipm
choosing “Comp. Approaches” as the article type from the drop down menu.
Before submission, please consult the journal guidelines for authors at: http://www.elsevier.com/journals/information-proce...
Additional information can be obtained from either of the guest editors:
Dr. Alexandra Balahur
European Commission Joint Research Centre, Institute for the Protection and Security of the Citizen
alexandra.balahur-dobrescu-AT-jrc.ec.europa.eu
Dr. Theresa Wilson
John Hopkins University, Human Language Technology Center of Excellence
taw-AT-jhu.edu