Creative minds contribute to innovation and exploration, two of the great engines of a prosperous society. Developing students’ creativity is always considered a priority in higher education because it can later contribute to economic and social development. In a recent paper, researchers from East China Normal University combined machine learning methods with questionnaires to reveal new dimensions of connections between the supervisor-student relationship. and student creative expression.
The paper was published in Journal of Social Computing.
“By understanding and addressing the factors that shape the supervisor-student relationship, we can cultivate an environment that nurtures and empowers graduate students, fosters their creativity and paves the way for their academic success,” said Jingyi Hu, the study’s first author.
Postgraduate education in China implements the supervisor system, and supervisors play an important role in cultivating the creativity of postgraduate students, according to the study.
In addition to daily classroom learning, the supervisor-student relationship is key to student growth and development.
“Postgraduate students who have closer communication and interaction with their supervisors show higher levels of creativity,” Hu said.
The reverse can also be true.
“It has also been argued that supervisor-student communication can inhibit the creativity of postgraduate students,” said Feng Liu, corresponding author. “But the effect of the supervisor-student relationship on the creativity of postgraduate students has not been clearly established.”
Previous studies have mainly focused on measuring characteristics, typologies, and predictors of supervisor-student relationships by administering questionnaires to identify and measure human emotions.
While the research team in this study also asked for answers through questions, the first stage of the experiment included video interviews and analysis through the method of facial expression recognition (FER). Based on deep learning methods, FER can directly identify emotional responses with greater objectivity and accuracy than self-report surveys and questionnaires, according to the study.
The researchers collected and analyzed video interview data from 74 East China Normal University postgraduate students and conducted FER analysis on a frame-by-frame basis to capture subtleties and micro details. expression. Through deep learning methods, the team plotted the emotional distribution of each subject, showing the probability ratios of the seven basic emotions: anger, fear, happiness, neutral, surprise, sadness , and anger.
The output data informed a mathematical model that the team used to map emotional changes and identify underlying patterns in student-mentor relationships.
“The combination of machine learning and mathematical modeling improves the accuracy and depth of our analysis, providing detailed insights into emotional experiences,” said Liu, who is also affiliated with Wuxi University.
Research findings confirm the groups’ hypothesis: widespread negative emotions experienced by a student may indicate a poor supervisor-student relationship.
“These findings contribute to a comprehensive understanding of the emotional landscape of such relationships, highlighting the need for interventions and improvements,” said Hu.
Insights in this arena can inform best practices, help design mentorship programs and policies, and enable educational institutions to create an atmosphere that maximizes the creative contributions of students. graduate student.
“In our ongoing research, we have made a significant effort to quantify computable emotions within the field of education and psychology,” Hu said. “Moving forward, our main goal is to examine the mechanisms of emotional change and its impact on students in real educational settings.”
In addition, researchers will investigate methods of quantifying creativity, collaborating with experts in the field of psychology to explore the concept of calculable emotion and its use in various interdisciplinary concerns.
“Ultimately, our goal is to quantify emotional processes in terms of computable sentiment and apply this knowledge to a wide range of practical scenarios,” Hu said.
Jingyi Hu et al, Emotional Mechanisms of Supervisor-Student Relationships: Evidence from Machine Learning and Investigation, Journal of Social Computing (2023). DOI: 10.23919/JSC.2023.0005
Provided by Tsinghua University Press
Citation: Machine learning tools reveal impact of supervisor-student relationship on student creativity (2023, July 18) retrieved on July 18, 2023 from https://phys.org/news/2023- 07-machine-learning-tools-reveal-impact-supervisor-student.html
This document is subject to copyright. Except for any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. Content is provided for informational purposes only.