Grant: Discovery Grants Program - Individual
Simon Fraser University
$25,000.00
Improving quality of user model inputs by opening the model to the users
FY 2011-12
Summary
User or learner modeling has become a cornerstone of many approaches to adaptive (or personalized) systems in general and in the learning domain in particular. User models can be classified along several axes, for example: what is being modeled, how the information is represented, and how the model is maintained. In this research we are interested in the particular aspects of the model maintenance. Ideally, the system would have a plenty of information available to initiate the user model either via initial interview with the user or through numerous observations of user's interaction with the system. However, many systems do not provide these opportunities and our ability to understand the interactions via observations is limited and we depend the explicit feedback. In our own research in the museum guides it is unacceptable to request users to spend significant amount of time answering questions to build their user model before using the system. An extensive explicit feedback during the system use is not appropriate because it interferes with the main goal of the application, e.g. museum exploration. Rather, continuous observations and minimalistic explicit feedback are used to dynamically build and rectify the model. Similarly, in the context of just-in-time workplace learning the learning system might have an established user model from the previous formal learning sessions but a strong motivation on the user side is needed to provide an explicit feedback after the learning event to maintain the model (as feedback activity competes with the task itself). These two settings share the characteristics that frame the type of systems we are interested in: limited opportunities for explicit feedback for user model maintenance. The long term goal of this research is to develop the methods to increase the amount and quality of the explicit user feedback while minimizing perceived disruptions to the ongoing system use. This short term 3-year research aims to establish the validity for this goal. Our hypothesis is that employment of the open user (learner) models will improve the amount and quality of explicit user feedback while not decreasing the usability of the system as measured by the perceived disruptions to its use.
Program
Discovery Grants Program - Individual
Recipient
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
238798-2010
Name nom
Hatala, Marek
Department département
Interactive Arts and Technology, School of (SIAT)
Organization id
5
Institution établissement
Simon Fraser University
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2010
Award amount
25000
Program id
RGPIN
Program nane en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
1103
Area of application group en
Health, education and social services
Area of application group fr
Santé publique, éducation et services sociaux
Area of application en
Learning and education
Area of application fr
Apprentissage et éducation
Research subject code
2803
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Knowledge representation
Research subject fr
Répresentation des connaissances
Partie
2
Nb partie
3
Application title
Improving quality of user model inputs by opening the model to the users
Keyword
NSERC
Application summary
User or learner modeling has become a cornerstone of many approaches to adaptive (or personalized) systems in general and in the learning domain in particular. User models can be classified along several axes, for example: what is being modeled, how the information is represented, and how the model is maintained. In this research we are interested in the particular aspects of the model maintenance. Ideally, the system would have a plenty of information available to initiate the user model either via initial interview with the user or through numerous observations of user's interaction with the system. However, many systems do not provide these opportunities and our ability to understand the interactions via observations is limited and we depend the explicit feedback. In our own research in the museum guides it is unacceptable to request users to spend significant amount of time answering questions to build their user model before using the system. An extensive explicit feedback during the system use is not appropriate because it interferes with the main goal of the application, e.g. museum exploration. Rather, continuous observations and minimalistic explicit feedback are used to dynamically build and rectify the model. Similarly, in the context of just-in-time workplace learning the learning system might have an established user model from the previous formal learning sessions but a strong motivation on the user side is needed to provide an explicit feedback after the learning event to maintain the model (as feedback activity competes with the task itself). These two settings share the characteristics that frame the type of systems we are interested in: limited opportunities for explicit feedback for user model maintenance. The long term goal of this research is to develop the methods to increase the amount and quality of the explicit user feedback while minimizing perceived disruptions to the ongoing system use. This short term 3-year research aims to establish the validity for this goal. Our hypothesis is that employment of the open user (learner) models will improve the amount and quality of explicit user feedback while not decreasing the usability of the system as measured by the perceived disruptions to its use.