ELRA 2014 - 5th International Workshop on EMOTION, SOCIAL SIGNALS, SENTIMENT & LINKED OPEN DATA

The fifth instalment of the highly successful series of Corpora for Research on Emotion held at the last LRECs (2006, 2008, 2010, 2012) will help bridging the gap between research on human emotion, social signals and sentiment from speech, text, and further modalities, and low availability of language and multimodal resources and labelled data for learning and testing.
Following LREC 2014’s hot topics of Big Data and Linked Open Data in particular also approaches on semi-automated and collaborative labelling of large data archives such as by efficient combinations of active learning and crowd sourcing will be of interest ? in particular also for combined annotations of emotion, social signals, and sentiment. Multi- and cross-corpus studies (transfer learning, standardisation, corpus quality assessment, etc.) are further highly relevant, given their importance in order to test the generalisation power of models.
Linked Open Data is an increasingly wide-spread methodology for the publishing, sharing and interlinking of data sets. In the context of this workshop we are also interested in reports on and experiences with the use of Linked Open Data in the context of emotion, social signals, and sentiment in analysis projects and applications.
As before, also the multimodal community is invited and encouraged to contribute new corpora, perspectives and findings ? emotion, sentiment, and social behaviour are multimodal and complex and there is still an urgent need for sufficient naturalistic uni- and multimodal data in different languages and from different cultures.
Keynote speeches by distinguished researchers and technical demonstrations crossing the communities involved will contribute to the attractiveness of the workshop. A best paper award will be given.
Topics include, but are not limited to:
§ Novel corpora of affective speech in audio and multimodal data
§ Corpora of written language/multimodal data for sentiment analysis
§ Corpora of audio/multimodal data of behaviour and social signals
§ Interlinking resources with Linked Data
§ Techniques for integration and merging of different resources
§ Use of Linked Open Data knowledge resources (DBpedia, Yago, etc.)
§ New methods for community or distributed annotation
§ Semi-autonomous learning on Big Data
§ Resources and analysis of social emotions (shame, pride, etc.)
§ Figurative languages (irony, metaphor, parody, sarcasm, satire, etc.)
§ Social signals (consents, laughs, sighs, hesitations, etc.)
§ Discussion of models for annotation and representation
§ Multi- and cross-corpus aspects (transfer learning, standardization)
§ Real-life applications of language and multimodal resources
§ Long-term resources, situational and demographic context inclusion
§ Resources for under-represented languages and cultures
§ Publishing as Linguistic Linked Data (e.g. lemon, Marl, Onyx, NIF)
§ Legal and social aspects of semantic and language resources
§ Cultural bias and normalisation in expression and social signalling
Important Dates
1500-2000 words abstract submission deadline
10 February 2014
Notification of acceptance
5 March 2014
Camera ready paper
15 March 2014
Workshop
26/27 May 2014
Submission Policy
Submitted abstracts of papers for oral and poster must consist of about 1500 ? 2000 words. Final submissions must follow the submission guidelines at LREC 2014
Regular papers (8 pages)
Short papers (4 pages)
Demo papers (2-4 pages)
When submitting a paper from the START page, authors will be asked to provide essential information about resources (in a broad sense, i.e. also technologies, standards, evaluation kits, etc.) that have been used for the work described in the paper or are a new result of your research. Moreover, ELRA encourages all LREC authors to share the described LRs (data, tools, services, etc.), to enable their reuse, replicability of experiments, including evaluation ones, etc...
Organisers
Björn Schuller
TUM/Imperial College, UK
Paul Buitelaar
NUI Galway, Ireland
Laurence Devillers
U. Sorbonne/CNRS-LIMSI, France
Catherine Pelachaud
CNRS - LTCI, France
Thierry Declerck
DFKI, Germany
Anton Batliner
FAU/TUM, Germany
Paolo Rosso
U. Politèc. Valencia, Spain
Seán Gaines
Vicomtech-IK4, Spain
Program Committee
Rodrigo Agerri, EHU, Spain
Noam Amir, Tel-Aviv U., Isreal
Alexandra Balahur-Dobrescu, ISPRA, Italy
Cristina Bosco, U. Torino, Italy
Felix Burkhardt, Deutsche Telekom, Germany
Carlos Busso, UT Dallas, USA
Rafael Calvo, U. Sydney, Australia
Erik Cambria, NUS, Singapore
Antonio Camurri, U. Genova, Italy
Mohamed Chetouani, UPMC, France
Montse Cuadros, VicomTech, Spain
Francesco Danza, Expert System, Italy
Thierry Dutoit, U. Mons, Belgium
Francesca Frontini, CNR, Italy
Hatice Gunes, Queen Mary U., UK
Hayley Hung, TU Delft, the Netherlands
Carlos Iglesias, UPM, Spain
Isa Maks, VU, the Netherlands
Daniel Molina, Paradigma Tecnologico, Spain
Monica Monachini, CNR, Italy
Shrikanth Narayanan, USC, USA
Viviana Patti, U. Torino, Italy
German Rigau, EHU, Spain
Fabien Ringeval, U. Fribourg, Switzerland
Massimo Romanelli, Attensity EUROPE, Germany
Albert Ali Salah, Boğaziçi University, Turkey
Metin Sezgin, Koc U., Turkey
Carlo Strapparava, FBK, Italy
Jianhua Tao, CAS, P.R. China
Tony Veale, UCD, Ireland
Michel Valstar, U. Nottingham, UK
Alessandro Vinciarelli, U. Glasgow, UK
Piek Vossen, VU, the Netherlands