Title | ||
---|---|---|
Student mental state inference from unintentional body gestures using dynamic Bayesian networks |
Abstract | ||
---|---|---|
Applications that interact with humans would benefit from knowing the intentions or mental states of their users. However,
mental state prediction is not only uncertain but also context dependent. In this paper, we present a dynamic Bayesian network
model of the temporal evolution of students’ mental states and causal associations between mental states and body gestures
in context. Our approach is to convert sensory descriptions of student gestures into semantic descriptions of their mental
states in a classroom lecture situation. At model learning time, we use expectation maximization (EM) to estimate model parameters
from partly labeled training data, and at run time, we use the junction tree algorithm to infer mental states from body gesture
evidence. A maximum a posteriori classifier evaluated with leave-one-out cross validation on labeled data from 11 students
obtains a generalization accuracy of 97.4% over cases where the student reported a definite mental state, and 83.2% when we
include cases where the student reported no mental state. Experimental results demonstrate the validity of our approach. Future
work will explore utilization of the model in real-time intelligent tutoring systems. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/s12193-009-0023-7 | J. Multimodal User Interfaces |
Keywords | DocType | Volume |
Affect analysis in context,Dynamic Bayesian networks,Mental state inference,Unintentional gestures | Journal | 3 |
Issue | ISSN | Citations |
1 | 1783-7677 | 4 |
PageRank | References | Authors |
0.44 | 22 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Abdul Rehman Abbasi | 1 | 46 | 3.33 |
Matthew N. Dailey | 2 | 331 | 26.44 |
Nitin V. Afzulpurkar | 3 | 50 | 5.44 |
Takeaki Uno | 4 | 1319 | 107.99 |