Paige West: Mining data to improve student learning

The following story was written in April 2021 by Joey Bush IV in ENGL ​4824​: Science Writing ​as part of a collaboration between the English department and the Center for Communicating Science.

According to a recent Boston University study of over 30,000 college students, rates of depression and anxiety in students have been climbing to new highs during the coronavirus pandemic (McAlpine 2021). Dealing with the impacts of COVID-19 has proven to be a challenge for students and professors alike, and the quick switch to online learning is one of those challenges.

    Paige West, a civil engineering student at Virginia Tech, is conducting research in data analytics with the goal of making online classes just as good as in-person ones. She has been at Virginia Tech since the fall of 2015, finished her bachelor’s degree in 2019, and received her master’s degree in 2021. 

     “I had always been interested in education and improving it,” says West. “As you’ve probably experienced, there are some not too good classes and there are great classes. So, I wanted to find ways to make the bad classes better and a tool to help keep the great classes great.”

    West explains that there are tools on Canvas that allow professors to monitor their classes in various ways, such as knowing when a student accesses a file on Canvas and checking whether students click on different tabs in Canvas. 

    West described learning analytics as “interaction data.”

    “When you post on a discussion board or simply go to the course home page,” she says, “Canvas knows who you are, what time you did it, as well as a bunch of other data.” Just about whatever you do on Canvas, instructors can see. Data analytics takes the data that Canvas collects and gives that data to instructors to use. Having data analytics available for instructors to use allows an online classroom setting to be more flexible and personal. 

    Data analytics can allow instructors to help students in ways that are simply not possible otherwise. West says that one of her goals in data analytics is to use the data that is collected from Canvas to introduce a better way of conducting an online course.

    For example, she says, “You can figure out which time of day is most active for students in your course” and then use that knowledge to benefit students.

    “What I found in my research was that the afternoon/evening hours were the most active time for students,” West explains. “The professors can take that data and say ‘Hey, most of my students are active at 2 p.m., so maybe I should shift my office hours from 10 a.m. to 2 p.m.”

    Shifting assignment submission deadlines from 8 a.m. to 5 p.m. may prevent students from staying up all night to complete assignments and contribute to better mental health, the Boston University researchers suggest.

    How does West show instructors the value of data analytics?

    “One of the ways is to start small,” she says, by helping them to understand that “Canvas already has a dashboard that includes data analytics in it. You start with seeing that these analytics exist in your course right now and see what you can figure out.”

    However, because instructors are busy people, she says, “They probably won’t have the time to go through the data set, so, you get someone to do it for you, like a grad student.”

    Having a tool already available in Canvas allows professors to start using data analytics in the classroom setting. They can discover student use patterns and, based on those patterns, adapt the course to students’ needs, allowing for an overall better educational experience. 

    Converting data into reliable patterns is not without challenges, West says. 

    “The data sets are just so large that there could be errors in the data set and I wouldn’t know until I’m halfway done with my analysis,” she explains. “I could look back and see that everything could be wrong. Everything is just numbers, and it is very hard to figure out if these numbers are lining up with everything that is going on in Canvas.”

    Despite the challenges in her research, West continues to strive for a better online learning world. Data analytics is relatively new. But in years to come, data analytics has the potential to change how we view online learning forever, she says. West sees great potential in her work.

    “Professors can use the data to figure out which students are at risk for failing. [With data analytics] in an online course, the professor is not just looking at your grade. I’m a firm believer that your tests and exams are not always the full picture of the work you’re putting into the course.”

     West’s goal is “for instructors to realize that this data exists and that if they use it, it can help make their course better for students. It is all about trying to make the courses better for students and vice versa. If the students are better and happier in the course, then most likely so is the professor.”

    The work West is doing is applicable to all online courses, not just civil engineering courses.

    “Staying within civil engineering was a choice because of my familiarity with the content,” says West.  “If I can add to research in my field and improve the education in civil engineering, then maybe other disciplines will follow.”

    West is striving for a future in which online courses are not subpar to in-person classes. When she describes how data analytics can influence a class, it’s easy to imagine a future in which online courses are consistently better than in-person ones.

(Work cited: McAlpine, Kat J. (2021, February 17). Depression, anxiety, loneliness are peaking in college students. The Brink. Retrieved April 24, 2021, from http://www.bu.edu/articles/2021/depression-anxiety-loneliness-are-peaking-in-college-students/)