Supervisor-Student Relationship and Its Impact on Student Creativity Revealed by Machine Learning Tools
Enhancing student creativity is a top priority in higher education, as it fosters economic and social development. To shed light on the relationship between supervisor-student dynamics and student creativity, researchers from East China Normal University utilized machine learning tools and questionnaires. Their study uncovered new insights into this crucial connection.
Jingyi Hu, the study’s first author, emphasized the importance of cultivating an environment that empowers graduate students. By understanding and addressing the factors that shape the supervisor-student relationships, we can nurture their creativity and pave the way for academic success, Hu said.
In Chinese postgraduate education, the supervisor system plays a vital role in cultivating the creativity of students. While daily classroom learning is critical, the relationship between supervisors and students is equally important for student growth and development.
According to Hu, Postgraduate students who have closer communication and interaction with their supervisors exhibit higher levels of creativity. However, the reverse can also be true. Hu explained, It has also been argued that supervisor-student communication can inhibit postgraduate students’ creativity, but the impact of this relationship has not been clearly established.
Previous studies in this field mainly relied on questionnaires to measure characteristics, typology, and predictors of supervisor-student relationships. In contrast, the research team at East China Normal University incorporated machine learning methods and facial expression recognition (FER) analysis into their study. The team conducted video interviews with 74 postgraduate students, analyzing the data frame by frame to capture subtle emotional nuances through deep-learning techniques.
The emotional distribution of each subject was then plotted using deep-learning methods, offering insights into the probability ratios of seven basic emotions: anger, fear, happiness, neutral, surprise, sadness, and disgust. These findings informed a mathematical model that allowed the team to map emotional changes and identify underlying patterns in student-mentor relationships.
Liu Feng, the corresponding author of the study, stated, The integration of machine learning and mathematical modeling enhances the precision and depth of our analysis, providing detailed insights into emotional experiences.
The researchers’ findings supported their hypothesis that negative emotions experienced by students can indicate a dysfunctional supervisor-student relationship. According to Hu, These findings contribute to a comprehensive understanding of the emotional landscape in such relationships, highlighting the need for interventions and improvements.
The insights gained from this study are invaluable for informing best practices and creating mentorship programs and policies that maximize graduate students’ creative contributions. Hu concluded, Our ongoing research aims to delve deeper into the mechanisms of emotional change and their impact on students in real educational settings.
In future research, the team plans to collaborate with experts in psychology to explore the concept of computable emotion and investigate methods to quantify creativity. Ultimately, they seek to leverage this knowledge in various practical scenarios.
This study demonstrates the power of machine learning tools in uncovering the intricate dynamics between supervisors and students, offering valuable insights for educational institutions seeking to nurture creativity and innovation among their graduate students.
