What Do We Know About College Students' Stress?
The interactive data visualization and machine learning model
Why do students burnout, drop classes, even drop out of college?
Under similar conditions, why do some individuals excel while others fail?
To help college students have knowledge of their own stress experience and understand the complexities of the experiences of their peers, we chose the StudentLife Dataset, which contains data collected from 48 undergraduate and graduate students at Dartmouth University, to find common student patterns, form the stress model, and test our model that associated with high levels of stress.
We believe identifications and predictions of the factors that affect the stress level would help students to aware the impact of their personality and behavior patterns on their stress levels, so that they can proactively adjust their behavior and seek help in the timely manner. This effort can also allow university staff and health advocates to understand students' high-stress behaviors to offer support. Finally, this allows empathy: students can better identify and understand stress behaviors of their classmates.
My role in this five people team project:
Defined the research questions
Analyze the data
Conducted the user testing
Built the website.
About the Data
The StudentLife Dataset contains data collected from 48 undergraduate and graduate students at Dartmouth over the 10 week spring term. The dataset includes automatically sensed data, self-reported, and survey data to provide a holistic view of the day-to-day student experience, including sleep data, activity data, meals, academic performance data, location, and stress.
The dataset includes over 53 GB of continuous sensing data from smartphones, including:
Objective sensing data: sleep (bedtime, duration, wake up), face-to-face conservation duration, face-to-face conversation frequency and physical activity (stationary, walk, run)
Location-based data: location, co-location, indoor/outdoor mobility, and distance covered
Other phone data: light, Bluetooth, audio, Wi-Fi, screen lock/unlock, phone charge, and app usage
The dataset also comprises 32,000 daily self-reports covering affect, stress, exercise, mood, loneliness, social and study spaces; and pre-post surveys including PHQ9 depression scale, UCLA loneliness scale , positive and negative affect schedule (PANAS) , perceived stress scale (PSS), big five personality, flourishing scale , and the Pittsburgh sleep quality index.
Finally, the dataset includes academic assessment data, such as, class information, deadlines, academic performance (i.e., grades, term GPA, cumulative GPA), class attendance rates (from phone location data), Piazza usage data, and student dinning history including time, location, and cost.
Data Analysis: What We Know from the Data
Students’ PSS result before and after the semester
First, we wanted to learn about the distribution of students’ stress level before and after the term to get a general understanding of the how students are suffering from stress in Dartmouth College.
We grouped students into low, medium, and high stress according to their PSS score. According to Cohen’s description of the scale (1988), scores around 13 are considered average and scores of 20 or higher are considered high stress. Considering that college students might be more stressful than the average population, we adjusted our criteria according to Cohen’s norm among people aging from 18-29 years old (N=645, mean = 14.2, SD =6.2). Students scored below 20.4 (Mean + 1* SD) are considered low stress. Scores between 20.4 and 26.6 are considered medium stress (Mean + 2* SD). Scores above 26.6 are considered in high stress.
From Figures 1 and 2, we conclude that most students were highly stressful compared with the norm (general population). In the following analysis, we explored how students’ stress level changed over the term.
Notice that in this measurement, students were asked to evaluate their stress level on a five-point scale. Thus, the results can only represent the changes of stress level compared with their historical data, not with the norm.
Figure 1 shows the distribution of students in three stress level groups before the term. As the graph shows, most of the students were highly stressful even before the term began.
Figure 2 shows the distribution of students in three stress level groups after the term. As the graph shows, the general distribution of stress level did not change by the end of the term. We do observe that a few students moved from low-stress group to medium stress group in the post-test, however, this change was not significant. One reason is that the PSS was not used as an event-related stress test, rather it reflects the general stress level of an individual across the time. The post-test was also conducted after the finals, which may not be able to reflect how the coursework affected students’ stress level.
This heat map shows individual students' stress pattern over time. In this analysis, we want to monitor students’ daily stress level as well as compare their daily stress score with their PSS scores. We pick up a few representative students from the PSS score as examples.
Student 32, 22, 49, 57 are among the lowest stress students.
Student 16, 17, 33, 52 are among the most stress students.
We also picked student 19 here because it has a lot of data.
Figure 3: Students’ daily stress level
From our observation, the heat map shows that students’ stress level are both associated with their PPS score and their context (Day of Week and Week of Term). For example,
Student 17 is severely stressful every day, he/she also scored high in PSS.
Student 22 and 32 seldom get stressful; they also scored low in PSS.
For Student 33, who scored high in PSS , the second half of term is more stressful than the first half of the term.
Counter-intuitively, a student such as Student 57, though get a rather low score in the stress questionnaire (pre and post test), he/she still gets frequently stressed in the middle of the term. This indicates that besides personality, the context may also influence students' perceived stress level.
Students of different personalities may have different sensitivity towards stress. The two personality graphs are comparing the BIG FIVE result of students who get low score in PSS (pre & post test) and who get high score in the PSS. According to the result, low stress students get lower score in neuroticism, higher score in conscientiousness and agreeableness.
From our observation, neuroticism is associated with perceived stress. It is reasonable since individuals who score high on neuroticism are more likely than average to be moody and to experience such feelings as anxiety, worry, fear, anger, frustration, envy, jealousy, guilt, depressed mood, and loneliness. We will use students’ score in this trait in our Bayes Network model.
Figure4: Low stress students
Figure5: High stress students
Lifestyle and Coursework
Figure 6: Students’ activity
This graph shows the change of students’ activity during the term. Students’ activities were collected by smartphone sensors. Their activities were classified into four categories: Stationary, Walking, Running, and Unknown. In this graph, we divided the whole term into 3 phases by months. The first month was the beginning of the term, the second month included the midterm weeks, and the third month included the final weeks. We can see that students’ walking and running time decreases in the second and third months compared with the first month, which indicates that they were less active as the term progressed.
This graph shows the total group of students' average stress level, # of deadlines and sleep hours across the whole term.
According to the graph, students express less stressed when they sleep longer.
Most of the deadlines happens on Mondays and Tuesdays. There is a weekly stress peak around Sundays and Mondays, which is indicative of an influence of days of weeks on deadlines, in turn influencing stress.
Figure 7: Students' sleep, deadline, and stress level
Machine Learning Model:
From previous observation, we found that students’ stress level is affected by the following factors:
Personality: Personality works as internal factors. We found that students who got a high score on Neuroticism from the Big Five Scale were more inclined to feel stress.
Lifestyle: Students’ lifestyle includes sleep hours and daily activity may also affect their perceived stress level. We observed from Figure 7 that students’ sleep hours were negatively associated with stress level. We also found that students spent less walking and running during the second half of the semester from their phone sensing data, suggesting that as the term gets busier, they exercise less.
Coursework: In addition to personality and lifestyle, coursework and school context are other significant factors. Based on our observation from figure 7, students’ stress level is positively associated with the number of deadlines.
We consider all those factors while building our machine learning model.
The model was tested on a set of withheld data from the original dataset, consisting of stress reports from five students through the term. Many of these daily stress reports included missing data for some of the attributes. Where at least half of the attributes were included, the model was run with maximum likelihood estimates for the remaining attributes.
The distribution of output stress values was compared to the distribution of stress values from the data. Assuming a Poisson distribution, the maximum likelihood estimate for the mean stress value was determined for each distribution to determine the bias of the model.
Assuming low stress = 1, medium stress = 2, and high stress = 3, the testing dataset had an expected mean of 2.04, while the model output had an expected mean of 2.16. The model is more likely to predict students at a slightly higher stress than is reality. This may be due to bias in the training dataset or introduced through the imputation process.
A large-sample z-test per Mathews (2010) was used to compare these distributions. There is not a statistically significant difference between the model output and the training dataset, but small datasets were used to compare these distributions. More data and testing will be required to determine how well the model's distribution matches that of the data.
What is your stress level?
Try it out!
Based on our model, we can help you identify your stress level and what are the main contributors making you feel stressed.
Please input your data per the instruction.
What I learned
Always look at the data in the context.
Before the data analysis, it is important to understand the rationale of the target data and how these data are collected. The product designer and the UX designer should actively involve in this stage to bring product and UX points of views to design the data collection. In the data analysis stage, the designers should take into account multiple important factors to interpret the data and ask right questions.
What is the good data visualization?
People are getting more and more visual. A good data visualization can tell a very impressive story. But how good is good? I think the bottom line is: a good data visualization is very selective about the data it include and very cautious the ways to illustrate the relationship among the data. The good data visualization fulfills the purposes in terms of the audience's needs. User testing should play a vital role in the data visualization.