A serious game to parameterize Bayesian networks: Validation in a case study in northeastern Madagascar

Celio, Enrico; Andriatsitohaina, R. Ntsiva N.; Zähringer, Julie G. (2019). A serious game to parameterize Bayesian networks: Validation in a case study in northeastern Madagascar. Environmental modelling & software, 122, p. 104525. Elsevier 10.1016/j.envsoft.2019.104525

Preview

Text (A serious game to parameterize Bayesian networks: Validation in a case study in northeastern Madagascar) Zähringer_2019_serious_game.pdf - Published Version Available under License Creative Commons: Attribution-Noncommercial-No Derivative Works (CC-BY-NC-ND). Download (1MB) | Preview

The management of multi-use landscapes is challenging, but essential when aiming at preserving the potential for ecosystem service provision. Land-use decisions lay at the center of this challenge. While land-use decision models may help to transparently grasp land-use decisions, the parameterization of such models is difficult as human decision-making is often not rational. We show here how we used a serious game to parameterize a Bayesian network-based land-use decision model. To elicit validation, game outputs are transformed to condi-tional probabilities and compared to conditional probabilities parameterized via a questionnaire and workshop exercises. The analysis of four types of validity shows encouraging results for criterion, respondent-related and practice-related validation. However, content validation (sensitivity analysis) was disappointing initially. We discuss how the success in validation quality may be related to the design of the game and conclude that the transfer from a game to Bayesian networks could improve the parameterization quality.

Interest & Impact

Downloads

1061 since deposited on 12 Dec 2019
42 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item