Detta är ett uppsatsförslag hämtat från Nationella Exjobb-poolen. Klicka här för att komma tillbaka till samtliga exjobbsförslag.
IDA-exjobb: A study of explanation facilities for a meal planning system and the relation to trust
For people of old age, malnutrition is a surprisingly common problem. Such malnutrition comes from a lack of variation in food intake, among other things, and is a common cause of hospitalisation among the elderly.
A research project at the laboratory for intelligent information systems at the department of computer science (at LiTH), is developing a meal planning system targeted at this malnutrition problem. This system provides the elderly user with a suggested meal plan for a specified time period. This meal plan is optimised based on several criteria including cost, ingredients available to the user, meal preparation time, the user's food taste, dietal restrictions, variation of ingredients, etc. This exjobb is about investigating facilities that attempt to explain to the users why a certain food recipe has been recommended. That is, based on the constraint satisfaction algorithm used to compute the recommendations, the key factors underlying the algorithm's choices must be made transparent to the user. Potential benefits for the users with such explanation facilities include better understanding of how the system works, which in turn could lead to a better calibrated trust in the system (e.g. to what extent, and in what contexts the provided recommendations can be trusted).
This exjobb is suitable for one or two students (e.g. from C, D, or IT programmes at LiTH) with an interest in human-computer interaction, user interface design, and user studies. Previous experience with GUI programming and the Java programming language is required. Knowledge about constraint satisfaction techniques would be an advantage but is not required.
1. Study related work on explanation facilities. Reading material will be provided by the examiner.
2. Study related work on the concept of trust, and how it can be measured. Reading material will be provided by the examiner.
3. Design and implement several alternative explanation facilities as extensions to the existing desktop user interface, based on the constraint satisfaction algorithm used by the meal planner. The designs must be grounded in the study of related work on explanation facilities.
4. Perform a user study to evaluate how the different explanation facilities work in general, and how they affect the users' trust in the system in general.
5. Document the work in the exjobb report (written in English or Swedish).
Please contact Dr. Johan Åberg ([email protected]) for further information.
Informationen om uppsatsförslag är hämtad från Nationella Exjobb-poolen.