What makes classification trees comprehensible?
详细信息 查看全文
- 作者：Rok Piltavera ; b ; rok.piltaver@ijs.si" class="auth_mail" title="E-mail the corresponding author ; Mitja Lu&scaron ; treka ; b ; mitja.lustrek@ijs.si" class="auth_mail" title="E-mail the corresponding author ; Matjaž Gamsa ; b ; matjaz.gams@ijs.si" class="auth_mail" title="E-mail the corresponding author ; Sanda Martinčić-Ip&scaron ; ićc ; smarti@inf.uniri.hr" class="auth_mail" title="E-mail the corresponding author
- 关键词：Classification tree ; Comprehensibility ; Understandability ; Interpretability ; End-user survey
- 刊名：Expert Systems with Applications
- 出版年：2016
- 出版时间：15 November 2016
- 年：2016
- 卷：62
- 期：Complete
- 页码：333-346
- 全文大小：1693 K
文摘
- •
In-depth survey for empirical study of the classification-tree comprehensibility.
- •
Objective measurements suggest the most influential parameter: the depth of leaves.
- •
Number of leaves is a relevant comprehensibility measure only for complex trees.
- •
Tree visualization style and layout significantly influence the comprehensibility.
- •
Proposed 2 comprehensibility measures considering semantics and structure of the tree.