The 1st International Workshop on Emotion and Sentiment in Social and Expressive Media (ESSEM 20131) is taking place on December 3rd, 2013, in Turin as a workshop of the XIII conference of the Italian Association for Arti cial Intelligence (AI*IA 2013). Sentiment analysis and emotion detection have been trending topics since a while, but not enough emphasis has been placed so far on their relations with in social and expressive media. The latter, in particular, play a key role in applicative elds related to creativity, its expressions and outcomes, such as gurative arts, music or drama. In such elds, the advent of digital social media has brought about new paradigms of interactions that foster rst-person engagement and crowdsourcing content creation: the subjective and expressive dimensions move to the foreground, opening the way to the emergence of an affective component within a dynamic corpus of contents - contributed or enriched by users. This calls for delving into the evolution of approaches, techniques and tools for modeling and analyzing emotion and sentiment. The workshop aims at bridging between the communities of AI researchers working in the eld of a ective computing under di erent perspectives. Such perspectives include, on the one hand, research on models and techniques for sentiment analysis and opinion mining on linguistic corpora and unstructured data from social web; on the other hand, research on formal and cognitive models in intelligent agents and multi-agent systems. We believe that cross-fertilization between di erent but related communities is precious in order to face open challenges, in particular, the ones raised by the social and expressive media, e.g: { extracting concept-level sentiment conveyed by social media texts by relying on structured knowledge of a ective information, i.e. a ective categorization models expressed by ontologies, better still if psychologically motivated and encoded in the semantic web standards; { cross-validation between sentiment-based approaches and cognitive models; { investigating advanced social aspects of emotions, i.e. regulative or ethic issues related to emotions in virtual agents; { fostering the interoperability and integration of tools by encouraging compliance with emerging standards.
Given the leading thread described above, we have proposed a special focus for ESSEM 2013: emotions and sentiment in applicative elds related to creativity, its expressions and its outcomes, i.e. gurative arts, music, drama, etc. Artistic creation and performance, in fact, provide a very interesting testbed for cross-validating and possibly integrating approaches, models and tools for automatically analyzing and generating emotion and sentiment. On this line, we encouraged the submission of research papers investigating aspects of emotion and sentiment in elds related to creativity and expressive media. Moreover, in order to foster the bringing together of artists and researchers re ecting on the ESSEM themes, we launched a call for artworks, by welcoming submissions of artworks, where the generation of artistic contents or the implementation of new forms of interaction with the audience relies on a ecting computing or stems from a media design speci cally and recognizably tailored to the elicitation of emotions and emotional feedback.
We were very pleased to receive 38 submissions from 13 di erent countries, distributed among full, short, position and artwork papers. We provided authors with 3 reviews per full/short/position paper. The program committee did an exceptional job, managing to complete the review process in record time. Out of the 19 submissions that were reviewed in the full paper category, we selected 10 full papers (acceptance rate: around 50%). In addition, we selected 5 submissions as short papers and 2 submissions as position papers. For what concerns the `artwork track', the artistic committee selected 5 artworks (out of 15 submitted artworks) to be presented and exhibited in a special `artwork session' of the workshop. We included in the proceedings ve artwork papers, where artists describe the concept and the technology behind their works.
We would like to thank: the members of the Program Committee and the external reviewers for their support and reviews; the members of the Artistic Committee for managing the artwork selection. We thank our invited speaker Carlo Strapparava for accepting to deliver the keynote talk. We would like to express our gratitude for the sponsorship we received from Dipartimento di Informatica and for the o cial endorsement we received from the Working Group on Natural Language Processing of the AI*IA, CELI Torino, AIMI (Associazione Informatica Musicale Italiana), CIRMA and WIQ-EI (Web Information Quality Evaluation Initiative). Furthermore, we are grateful to all authors (researchers and artists) who submitted their works to ESSEM 2013, believing in a rst edition like this, and in the ideas it brings forth.
Erik Cambria Rossana Damiano Viviana Patti
Paolo Rosso
Erik Cambria Rossana Damiano Viviana Patti Paolo Rosso
Cristina Battaglino Andrea Bolioli Antonio Camurri Paula Carvalho Marc Cavazza Mrio J. Gaspar da Silva Dipankar Das Mehdi Dastani Andrea Esuli Giancarlo Fortino Virginia Francisco Marco Grassi Nicola Henze Anup Kalia Iolanda Leite Emiliano Lorini Viviana Mascardi Alessandro Moschitti Roberto Paredes Catherine Pelachaud Paolo Petta
Daniele Radicioni Francisco Rangel, Antonio Reyes Bjoern Schuller Giovanni Semeraro Michael Thelwall Andrea Valle Enrico Zovato
National University of Singapore, Singapore University of Turin, Italy University of Turin, Italy Technical University of Valencia, Spain European Commission Joint Research Centre, Italy University of Turin, Italy CELI, Italy University of Genova, Italy INESC-ID and ISLA Campus Lisboa, Portugal Teesside University, UK INESC-ID Lisboa, Portugal Jadavpur University, India Utrecht University, the Netherlands ISTI-CNR Pisa, Italy University of Calabria, Italy Universidad Complutense de Madrid, Spain Marche Polytechnic University, Italy Leibniz University, Hannover, Germany North Carolina State University, Releigh, USA Technical University of Lisbon, Portugal IRIT-CNRS, Toulouse, France University of Genova, Italy University of Trento, Italy Technical University of Valencia, Spain CNRS - LTCI, France Austrian Research Institute for Arti cial Intelligence, Austria University of Turin, Italy University of Turin, Italy Autoritas Consulting, Spain Lab. Tecnologias Linguisticas, ISIT, Mexico Technical University of Munich, Germany University of Bari, Italy University of Wolverhampton, UK University of Turin, Italy Nuance Communications, Italy
Wei Wei Bei Yu Dipartimento di Informatica, Universita di Torino CIRMA, Universita di Torino Working Group on Natural Language Processing of the AI*IA CELI s.r.l Torino AIMI (Associazione Informatica Musicale Italiana) WIQ-EI (Web Information Quality Evaluation Initiative)