ES³ 2012 - Corpora for Research on EMOTION SENTIMENT & SOCIAL SIGNALS

Organisers

Laurence Devillers

U. Paris-Sorbonne 4, France

Björn Schuller

TUM, Germany

Anton Batliner

FAU, Germany

Paolo Rosso

U. Politec. Valencia, Spain

Ellen Douglas-Cowie Queen's Univ. Belfast, UK

Roddy Cowie

Queen's Univ. Belfast, UK

Catherine Pelachaud

CNRS - LTCI, France

ASC-Inclusion

ILHAIRE

Scope

The fourth instalment of the workshop series on Corpora for Research on Emotion held at LREC aims at further cross-fertilisation between the highly related communities of emotion and affect processing based on acoustics of the speech signal, and linguistic analysis of spoken and written text, i.e., the field of sentiment analysis including figurative languages such as irony, sarcasm, satire, metaphor, parody, etc. At the same time, the workshop opens up for the emerging field of behavioural and social signal processing including signals such as laughs, smiles, sighs, hesitations, consents, etc. Besides data from human-system interaction, dyadic and human-to-human data, its labelling and suited models as well as benchmark analysis and evaluation results on suited and relevant corpora are invited. By this, we aim at bridging between these larger and highly connected fields: Emotion and sentiment are part of social communication, and social signals are highly relevant in helping to better understand affective behaviour and its context. For example, understanding of a subject's personality is needed to make better sense of observed emotional patterns. At the same time, non-linguistic behaviour such as laughter and linguistic analysis can give further insight into the state or personality trait of the subject.

All these fields further share a unique trait: Genuine emotion, sentiment and social signals are hard to collect, ambiguous to annotate, and tricky to distribute due to privacy reasons. In addition, the few available corpora suffer from a number of issues owing to the peculiarity of these young and emerging fields: As in no related task, different forms of modelling exist, and ground truth is never solid due to the often highly different perception of the mostly very few annotators. Due to data sparseness, cross-validation without strict partitioning including development sets and without strict separation of speakers and subjects throughout partitioning are frequently seen.

Program Committee

Vered Aharonson, AFEKA, Israel
Alexandra Balahur, EC JRCentre, Italy
Felix Burkhardt, D. Telekom, Germany
Carlos Busso, UT Dallas, USA
Rafael Calvo, U. Sydney, Australia
Erik Cambria, NUS, Singapore
Mohamed Chetouani, UPMC, France
Thierry Dutoit, Univ. Mons, Belgium
Julien Epps, UNSW, Australia
Anna Esposito, IIASS, Italy
Hatice Gunes, Queen Mary Univ., UK
Catherine Havasi, MIT Media Lab., USA
Bing Liu, U. Illinois Chicago, USA
Florian Metze, CMU, USA
Shrikanth Narayanan, USC, USA
Maja Pantic, Imperial College, UK
Antonio Reyes, UP Valencia, Spain
Fabien Ringeval, U. Fribourg, CH
Peter Robinson, U. Cambridge, UK
Florian Schiel, LMU, Germany
Jianhua Tao, CAS, China
Jose A. Troyano, U. de Sevilla, Spain
Tony Veale, UCD, Ireland
Alessandro Vinciarelli, U. Glasgow, UK
Haixun Wang, Microsoft, China

Important Dates

1500-2000 words abstract submission deadline

1 March 2012 (extended)

Notification of acceptance

12 March 2012

Camera ready paper

20 March 2012

Workshop

26 May 2012

Topics include, but are not limited to:

+ Novel corpora of affective speech in audio & multimodal data

+ Novel corpora for sentiment and opinion mining analysis

+ Novel corpora of audio & multimodal social signals

+ Novel corpora with combined annotation of the above

+ Analysis in speech, language and multimodal cues

+ Rich emotion and personality: dimensional, categories, etc.

+ Figurative languages: irony, sarcasm, satire, metaphor, parody

+ Social signals: laughs, smiles, sighs, hesitations, consents, etc.

+ Discussion of models for emotion, sentiment & social signals

+ Measures for quantitative corpus quality assessment

+ Standardisation of corpora and labels for cross-corpus testing

+ Real-life applications of language & multimodal resources

+ Long-term recordings of interactional & dyadic communication

+ Rich and novel annotations such as situational context

+ Communications on testing protocols

+ Evaluations on novel or multiple corpora

+ New methods for community or distributed annotation

+ Unsupervised learning techniques to exploit additional data

+ Synthesis of data for learning in sparse data tasks

+ Resources for underrepresented languages & cultures

+ Evaluations on novel or multiple corpora

Submission Policy

Submitted abstracts of papers for oral and

poster must consist of about 1500-2000

words.

Final submissions should be 4 pages long,

must be in English, and follow the submission guidelines at LREC 2012. Please follow this link for submission.

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. For further information on this new initiative, please refer to

http://www.lrec-conf.org/lrec2012/?LRE-Map-2012

http://emotion-research.net/sigs/speech-sig/es12

Contact: lrec-emotion@limsi.fr