Authors:
Shimeng Peng
and
Katashi Nagao
Affiliation:
Graduate School of Information Science and Nagoya University, Japan
Keyword(s):
Heart Rate Variability, Machine Learning, Discussion Performance Evaluation, Q&A Analysis.
Related
Ontology
Subjects/Areas/Topics:
Computer-Supported Education
;
Information Technologies Supporting Learning
;
Learning Analytics
;
Learning/Teaching Methodologies and Assessment
;
Metrics and Performance Measurement
Abstract:
Heart rate (HR) variability (HRV) has recently seen a surge in interest regarding the evaluation of cognitive performance as it always be used to measure the autonomic nervous system function. In this study, we argue that a presenters’ HR data can be used to effectively evaluate their cognitive performance, specifically presenters’ performance of discussion which consists of several Q&A segments (question and answer pairs) compared with using traditional natural language processing (NLP) such as semantic analysis. To confirm this, we used a non-invasive device, i.e., Apple Watch, to collect real-time updated HR data of presenters during discussions in our lab-seminar environment, their HR data were analyzed based on Q&A segments, and three machine-learning models were generated for evaluation: logistic regression, support vector machine, and random forest. We also discuss the meaningful HR and HRV features (metrics). Comparative experiments were conducted involving semantic data of Q
&A statements alone and a combination of HR and semantic data. The HR data of presenters resulted in effective evaluation of discussion performance compared with using only semantic data. The combination of these two types of data could improve the discussion performance evaluation ability to some extent.
(More)