• Aucun résultat trouvé

Preface - EMPIRE 2013

N/A
N/A
Protected

Academic year: 2022

Partager "Preface - EMPIRE 2013"

Copied!
4
0
0

Texte intégral

(1)

EMPIRE 2013: Emotions and Personality in Personalized Services

Marko Tkalˇciˇc1, Berardina De Carolis2, Marco de Gemmis2, Ante Odi´c3, and Andrej Koˇsir3

1 Johannes Kepler University Department for Computational Perception, Linz, Austria

2 University of Bari Aldo Moro, Italy

3 University of Ljubljana Faculty of electrical engineering, Slovenia

Abstract. The EMPIRE workshop attempts to provide some answers to the growing interest of the user modeling research community on the role of human factors, especially personality and emotions, on various aspects of user modeling. This first edition of the workshop has six ac- cepted papers and an invited talk.

Keywords: personality, emotions, user modeling, recommender systems, social signal processing

1 Introduction

The 1st Workshop on Emotions and Personality in Personalized Services (EM- PIRE 20134) is taking place on 10. June 2013 in Rome at the Roma Tre Uni- versity in conjunction with the 21st conference on User Modeling, Adaptation, and Personalization (UMAP 20135).

While a lot of discussion has been made on filtering algorithms, and eval- uation measures, few studies have stood to consider the role of emotions and personality in user models and personalized services. The workshop attempts to provide insight into these issues.

Characterizing the user model and the whole user experience with person- alized service, by means of affective traits, is an important issue which merits attention from researchers and practitioners in both web technology and human factor fields.

Some questions motivate this workshop:

– Do affective traits (personality, emotions, and mood) influence and determine the acceptance of the personalized suggestions?

– How personality traits should be included in the user model?

– How the personalized services should be adapted to emotions and mood to increase user satisfaction?

4 http://empire2013.wordpress.com/

5 http://www.umap2013.org

(2)

2 Contributions

Personality is a recurrent theme among the accepted papers. It has been inves- tigated in connection with users’ preferences by Bologna et al. [1], Cantador et al. [2], Hu and Pu [3] and Odi´c et al. [5].

Bologna et al. [1] present the prototype of a recommender system for eCom- merce,that exploits the users’ personality in terms of theirvocational personality, as expressed with the RIASEC model. Their system performs a classical context- aware ranking and then re-ranks the list of top-N items according to the users’

personalities. The prototype is currently undergoing experimental validation.

In their work, Cantador et al. [2] present the outcomes of a study aimed at understanding the relationships between users’ personalities and their prefer- ences in different domains. Their study relies on the myPersonality dataset with over 3 million users. Of special interest is the result table with stereotypical user preferences.

A complementary view of the role of personality in users’ ratings is presented by Hu and Pu [3]. The basis of their study is a dataset of a gifts retailer. The authors are interested in various aspects of a single user’s rating behaviour and their relations with her/his personality type.

Odi´c et al. [5] present the results of a study that compares the ability of emotion induction (by movies as stimuli) in end users under different contextual situations and their personality types. The authors identify personality traits whose emotional responses are stable across different contextual values (alone vs. non-alone) and those who are not based on the COMODA dataset.

The work presented by Moore et al. [4] is focused on the validation of gener- ally accepted representation of smileys as emotion indicators. They carried out a large survey with nearly 1000 participants. Based on their dataset, they are able to discern universal emoticons from ambiguous emoticons.

In their work, Vodlan et al. [6] present the experimental design for the evalu- ation of the impact of the social signalhesitationon users’ decision making. More concretely, the authors use hesitation as an indicator of the user’s preference for more diverse or less diverse items in the evaluated conversational recommender system for movies. The presented work is currently undergoing experimental validation.

3 Acknowledgement

The EMPIRE workshop chairs would like to thank all the authors for their submissions.

Furthermore, we would like to thank the UMAP workshop chairs, Shlomo Berkovsky (from NICTA, Australia) and Pasquale Lops (from the University of Bari Aldo Moro, Italy), for their guidance during the workshop organization.

Our gratitude goes also to our invited speaker, Neal Lathia (from the Uni- versity of Cambridge), for sharing his insights on the recent developments in the field.

(3)

Last but not least, we want to thank the members of the programme com- mittee who reviewed the submissions and helped to keep a high quality of the accepted papers.

3.1 Programme Committee

– Alessandro Vinciarelli, University of Glasgow – Aleksander Valjamae, Graz University – Elisabeth Andre, Augsburg University – Floriana Grasso, University of Liverpool

– Francesco Ricci, Free University of Bozen-Bolzano – Gustavo Gonzalez, MediaPro (Imagina Group) – Ioannis Arapakis, Yahoo! Barcelona

– Judith Masthoff, University of Aberdeen – Li Chen, Hong Kong Baptist University

– Man-Kwan Shan, National Chengchi University, Department of Computer Science

– Marius Kaminskas, Free University of Bozen-Bolzano – Martijn Willemsen, Eindhoven University of Technology – Markus Zanker, University of Klagenfurt

– Michal Kosinski, Microsoft

– Mohammad Soleymani, University of Geneva/Imperial college – Neal Lathia, Cambridge University

– Rong Hu, Swiss Federal Institute of Technology in Lausanne (EPFL)

References

1. Ciro Bologna, Anna Chiara De Rosa, Alfonso De Vivo, Matteo Gaeta, Giuseppe Sansonetti and Valeria Viserta. Personality-Based Recommendation in E- CommerceIn Proceedings of the 1st Workshop on Emotions and Personality in Personalized Services (EMPIRE 2013)

2. Iv´an Cantador, Ignacio Fernandez-Tobias and Alejandro Bellogin. Relating Personality Types with User Preferences in Multiple Entertainment Domains In Proceedings of the 1st Workshop on Emotions and Personality in Person- alized Services (EMPIRE 2013)

3. Rong Hu and Pearl Pu. Exploring Relations between Personality and User Rating BehaviorsIn Proceedings of the 1st Workshop on Emotions and Per- sonality in Personalized Services (EMPIRE 2013)

4. Adam Moore, Christina M. Steiner and Owen Conlan.Design and develop- ment of an empirical smiley-based affective instrumentIn Proceedings of the 1st Workshop on Emotions and Personality in Personalized Services (EM- PIRE 2013)

5. Ante Odi´c, Marko Tkalˇciˇc, Jurij Franc Tasiˇc and Andrej Koˇsir. Personal- ity and Social Context: Impact on Emotion Induction from MoviesIn Pro- ceedings of the 1st Workshop on Emotions and Personality in Personalized Services (EMPIRE 2013)

(4)

6. Tomaˇz Vodlan, Marko Tkalˇciˇc and Andrej Koˇsir. The Role of Social Sig- nals in Telecommunication: Experimental DesignIn Proceedings of the 1st Workshop on Emotions and Personality in Personalized Services (EMPIRE 2013)

Références

Documents relatifs

Michal Kompan and Maria Bielikova, Social Structure and Personality En- hanced Group Recommendation, Proceedings of the 2nd Workshop Emotions and Personality in Personalized

In this study, we explored the relation between the emotions of 5,865 Facebook users with their age, gender and personality by using their status updates (almost 1 million posts)..

Whereas personality is usually used to alleviate the cold-start problem in recommender systems (i.e., new users and sparse data sets) [11], or to determine the amount of diversity

On the other hand, people who like cartoons have on average a dissimilar personality to those who prefer educational books, and users who prefer sports shows have low similarity

Based on model-based diagnosis techniques [12, 17, 26], the environment supports users in the following situa- tions: (1) if no solution could be found for a set of user

To measure the degree of satisfaction related to user experience and gather feedback in a movie recommendation scenario, we used both a questionnaire approach based on two simple

Specifically, in recommender systems, the exploitation of user personality information has enabled address cold-start situations [25], facilitate the user preference

The fir edi ion of he XI-ML E plainable and In erpre able Machine Learning ork hop a held on Sep ember 21, 2020 a he ​43rd German Conference on Ar ificial In elligence,