Home // ACHI 2020, The Thirteenth International Conference on Advances in Computer-Human Interactions // View article
Authors:
Tran Phuong Thao
Midori Takahashi
Nobuo Shigeta
Mhd Irvan
Toshiyuki Nakata
Rie Shigetomi Yamaguchi
Keywords: Machine Learning; Multiple (Linear) Regression; Student's T-test (t-test); Human Factors.
Abstract:
Japan is well known for one of the highest suicide rates in the world, and suicide is the third cause of death after cancer and accidents. The most common reason of suicide comes from overwork- and stress-related issues. Researchers have found that education is listed in the top 6 job categories that are highly affected by overwork and stress. In this paper, we investigate the human factors that influence the exhaustion and stress levels of nursery teachers which is one of the top social issues in the education system of Japan. We are the first to possess a novel dataset that was collected using survey-based and real-time approaches with professional devices. We built a regression model in machine learning with t-test in statistics and divided the effect levels of the factors into three levels: normal, nearly-significant, and significant. We found some following results. First, we found the evidence that working on Thursday and Friday affects both exhaustion and stress. Interestingly, although working on Friday is more exhaustive than on Thursday, working on Thursday is more stressful than on Friday. Surprisingly, we found that while working on Saturday does not affect either exhaustion or stress, working on Sunday is a factor affecting the stress (but not exhaustion) of the participants. Furthermore, gender, weight, and height do not appear as the affecting factors. Also, people who are less than 30 years old get more easily stressed than the other ages.
Pages: 136 to 141
Copyright: Copyright (c) IARIA, 2020
Publication date: March 22, 2020
Published in: conference
ISSN: 2308-4138
ISBN: 978-1-61208-761-0
Location: Valencia, Spain
Dates: from November 21, 2020 to November 25, 2020