Where does your energy come from? What your data says about your personality

Have you ever wondered whether your daily habits—how you spend your time, interact with others, or recharge your energy—might reveal something meaningful about your personality? 

Check out Predicting Personality Types Using Behavioral Data, an application developed by May Phuu Thwel, Parami’s undergraduate student majoring in Statistics and Data Science (SDS), which explores how machine learning can be used to understand introversion and extroversion through everyday behavior. In this project, May applies data science to a relatable and personal question: how can understanding our personality help us take better care of ourselves?

While still exploring her academic interests in data science, May Phuu Thwel developed a strong curiosity about human behavior. This interest shaped her first complete machine learning application. Prior to this project, she worked on personality prediction for her mid-term coursework and later explored customer segmentation in retail for her final project for the Introduction to Machine Learning course by Dr. Nwe Nwe Htay Win.

The project aims to predict whether a person is more likely to be an introvert or an extrovert—a topic many young people can easily relate to. Although personality is complex and cannot be fully captured by two categories, May focused on these traits given the structure of the Kaggle dataset she used.

“I didn’t want people to think introversion or extroversion is about how good you are at leading or speaking,” May explained. “For me, it’s more about where you get your energy from.”

May is more introverted, finding balance by spending time alone through activities such as mindful walking, meditation, swimming, reading, writing, and organizing. In contrast, extroverts often feel recharged by social interactions, whereas ambiverts fall between extroverts and introverts.

The idea for the project grew from a simple reflection. “If we understood our personality better, maybe we could take better care of ourselves,” she said. “That thought stayed with me throughout the project.”

Designed for individuals interested in their personality, the application allows users to explore their traits through a brief questionnaire. She also sees broader applications in workplaces, schools, and psychology-related fields where understanding personality can support better communication and collaboration.

“I wanted to build something useful, not just an assignment,” she shared. “Even if it’s simple, I hope it helps people reflect on themselves.”

This project holds special significance for May, as it is her first full machine learning application built from start to finish. Using scikit-learn, she learned to clean data, train models, and evaluate results. The process posed challenges, but those moments proved valuable learning experiences.

The dataset includes behavioral and social information such as time spent alone, frequency of social events, social circle size, feelings after socializing, and social media activity. After handling missing values, scaling features, and encoding categorical variables, May trained a logistic regression model that achieved 92% accuracy. Key predictors included feeling drained after socializing, stage fright, and time spent alone.

The application is built with the Streamlit web framework, using a dataset sourced from Kaggle, and the full code is available on GitHub. Through this project, May aims to demonstrate that machine learning can be accessible, practical, and deeply connected to everyday life. Check your personality here.

Students enrolled in the Introduction to Machine Learning course taught by Dr. Nwe Nwe Htay Win are given the opportunity to develop machine-learning–based applications focused on projects that are personally meaningful to them. This hands-on learning approach reflects the essence of Parami University’s liberal arts education, where interdisciplinary thinking, real-world problem-solving, and personal engagement are central to the learning experience.