Workshop on

Attitude, Personality and Emotions in User-Adapted Interaction

in conjunction with User Modeling 99

Banff Centre, Banff, Alberta, Canada

June 20-24, 1999

Call for Papers

Program

Program Committee

Elisabeth André 
DFKI, GmbH, Ge

Gene Ball 
Microsoft , USA 

Sandra Carberry 
University of Delaware, USA 

Cristiano Castelfranchi 
IP-CNR, Italy 

Kerstin Dautenhahn 
University of Reading, UK 

Fiorella de Rosis 
University of Bari, Italy 

Clark Elliott
DePaul University , USA 

Gloria Mark 
GMD-FITD, Germany 
Yorick Wilks 
University of Sheffield, UK

Important Dates:

 march 15, 99: 
deadline for submissions

april 15, 99: 
notification of acceptance

may 31, 99: 
deadline for final copy

WS Coordinator:

Fiorella de Rosis
Intelligent Interfaces 
University of Bari, Italy 

Paper Format:

 Papers should not exceed 2000 words; 
they should be sent electronically, 
in Word or (preferably) in HTML,  
to the address mentioned below, 
so that they can be published 
on the Workshop site 
before the Conference.

Questions concerning the Workshop

 should be addressed to 
derosis@di.uniba.it

Why this workshop

Adaptivity in human-computer interaction has been focused on the knowledge, plans, interests, and preferences of the user and has not yet considered extrarational factors such as the user's attitude, personality, or emotional state. Recent research findings prove, however, that humans tend to assign personalities to interfaces, even when they are based on traditional techniques like graphics or natural language and do not include any kind of anthropomorphism, and that the usability of these interfaces is affected from the compatibility between their personality and the user's personality. In addition, it appears that interfaces may better serve the user if they recognize the user's changing attitudes (such as doubt or uncertainty) and respond appropriately. 
If people already perceive computers based on the 'graphical tool' metaphor as 'having a personality', this perception will most probably increase in that interfaces will evolve towards the new 'assistant' metaphor. Agent interfaces that are installed on the more recent commercial products or are demonstrated as research prototypes show some 'implicit' (and probably unplanned) personality which is potentially perceived as being very 'friendly' by some users, but might be met with disapproval by others. In the present interfaces, and even more in the future world of agent interfaces, it is therefore reasonable to assume that adaptivity should extend from the rational aspects of the mental state that were considered so far to personality and emotions, so as to show not only a friendly but also a warm and empathic interaction.
In proposing this Workshop, we start from Carbonell's claim that "Understanding personality traits is important for generating expectations about probable behaviours" and from the statement that "Emotion is not regarded anymore as an undesirable consequence of our embodiment that must be neglected, but as a necessary component of intelligent behavior that of fers a rich potential for the design of artificial systems, and for enhancing our interactions with them" . We wish to promote acquisition, in the UM community, of theories about personality and emotions that have been developed in different domains (such as cognitive science, 'believable agents', conversation, entertainment and so on), and investigation of how they might influence adaptation in HCI. We assume that utilization of these theories in our community will contribute to improving human-computer interaction and will produce, at the same time, an advancement of the 'believable agents' field through discovery of new problems and development of new methods. 

In particular, the Workshop will: 
(i) discuss the meaning of attitude, personality, and emotion and how they can be formalized in a working model for HCI; discuss the difference between (stable) personalities and (short-lived) emotions, and the way that emotions may evolve during interaction;
(ii) examine existing interfaces and interface agents to assess which 'personalities' are (implicitly or explicitly) embedded in them and whether they are envisioned to adapt to the user characteristics, 
(iii) discuss how methods and techniques which have been employed successfully in recognizing and modeling the user should also be employed in modeling the user's 'affective state'; 
(iv) investigate whether techniques employed to adapt the interface appearance and behaviour (for instance, message generation) should be enhanced to consider personality and emotional factors;
(v) discuss how these new interfaces can be evaluated: this is very important in this new type of interaction, since emotions and personality are, to a large extent, subjective and individual; carefully designed evaluation should therefore be planned in engineering-oriented projects, so as to insure acceptability of results; 
(vi) examine specific application domains (such as tutoring, health care or family planning), in which the communication process is particularly influenced by the emotional state of the two participants and by their relationship.
Finally, considering these new user attitudes involves reflecting on aspects of human-human interaction which promise to influence HCI in a not too distant future. Some examples include lies or deception, which might be particularly relevant in application domains like electronic trade or health care; the possibility (for users) to confide private or secret information and to blame or even to 'insult' the interface; the recognition of such user behaviour in order to establish how to adapt interaction accordingly.

Suggested Topics

1. What user attitudes might be usefully modelled?
2. What is the meaning of personality ?
3. What is the difference between personality and emotion, in cognitive science theories?
4. How are attitude, personality, and emotion related to other extrarational factors that are relevant in human-computer interaction, such as culture? How can the environment influence attitudes and emotions, for instance in art, entertainment and leisure?
5. Which user attitude, personality, and emotional factors may affect human-computer interaction, and how? (theoretical foundations and results of empirical studies) 
6. How can attitudinal, emotional, and personality factors be recognized?
7. How can they be modeled? 
8. How can the interface display an attitude, express a personality, or demonstrate emotions and when is it appropriate to do so? Ex: 
in the graphics employed
in the language employed in messages and in 'story telling'
in the level of help users require from the interface and the interface provides to them 
in the preferences or biases of the interface agent.
9. Which personality can be attributed to existing agent interfaces?
10.How should the interface be dynamically adapted to the user's attitudes, personality, and emotional state? 

How the Workshop will be organised 

Though the subject of personality and emotions in software agents is not new, this is the first time their introduction in User-Adapted interaction is discussed in an International Workshop. The goal of this meeting is therefore to show results of ongoing research and to collect, at the same time, ideas, problems and difficulties by those who entered more recently in the field. The Workshop will be organised according to submitted contributions: in principle, it will include a few medium-length talks and will allocate a large space to position statements, key-note talks and discussions. Short and long contributions will be made available in a Web site before the UM99 Conference, so that people can read them in advance. 
The possibility of collecting longer versions of the contributions in a book or a Special Issue of the Journal UMUAI will be examined immediately after the Workshop.