Network explanations and explanatory directionality

Assessing explanatory style: the content analysis of verbatim explanations and the Attributional Style Questionnaire.

We compare two methods of assessing explanatory style--the content analysis of verbatim explanations (CAVE) and the Attributional Style Questionnaire (ASQ). The CAVE technique is a method that allows the researcher to analyze any naturally occurring verbatim materials for explanatory style. This technique permits the measurement of various populations that are unwilling or unable to take the AS...

Enabling Large-Scale Bayesian Network Learning by Preserving Intercluster Directionality

We propose a recursive clustering and order restriction (R-CORE) method for learning large-scale Bayesian networks. The proposed method considers a reduced search space for directed acyclic graph (DAG) structures in scoring-based Bayesian network learning. The candidate DAG structures are restricted by clustering variables and determining the intercluster directionality. The proposed method con...

Evaluating the Explanatory Value of Bayesian Network Structure Learning Algorithms

This paper presents a technique for evaluating the degree of correctness of structural models produced by Bayesian network learning algorithms. In this method, (1) Bayesian networks are generated pseudo-randomly using a chosen model distribution; (2) data sets of various sizes are produced using the generated networks; (3) the data sets are passed to learning algorithms; and (4) the network str...

Conflicting Directionality

Explanations Count Explanations Count

In research areas such as decision support systems, one of the crucial features is the ability to automatically explain decisions. However, this ability does not typically play a large role in computer games. Here, I suggest that this situation will change: research on the automatic generation of explanations will have real import for many types of computer games. I discuss four possible ways t...