Page 34 - summer18

of [a student’s] social circle, and we can analyze
Sudha Ram / Chris Richards photo
Ram’s work comes at a
time when universities
nationwide, including
the UA, are committing
more resources to
harnessing data
analytics in ways
that support student
success.
32 ARIZONA ALUMNI MAGAZINE
changes in these networks to see if their social
circle is shrinking or growing, and if the strength
of their connections is increasing or decreasing
over time,” she says.
Ram additionally used the CatCard data to
look at the regularity of students’ routines and
whether they had fairly established patterns
of activity during the school week. She and her
collaborators developed a machine learning
algorithm to determine ways to quantify these
patterns.
USING ID CARDS TO TRACK Considered together with demographic
SOCIAL INTERACTIONS information and other predictive measures of
freshman retention, an analysis of students’
social interactions and routines was able
tudents at the UA are issued CatCard student to accurately predict 85 to 90 percent of the
SIDs when they enroll. They use the cards at freshmen who would not return for a second year
locations including residence halls, the Student at the UA, with those having less-established
Recreation Center, various campus labs, the routines and fewer social interactions most at
library and the Think Tank academic support risk for leaving.
center, to name a few. “Of all the students who drop out at the end
Many students also load cash onto the card for of the first year, with our social integration
use in vending machines and to pay for food and measures, we’re able to do a prediction at the end
of the first 12 weeks of the semester with 85 to 90
services at the Student Union Memorial Center.
The total number of campus locations that accept percent recall,” Ram says. “That means that out
CatCards is near 700. of the 2,000 students who drop out, we’re able to
“It’s kind of like a sensor that can be used for identify 1,800 of them.”
tracking them,” Ram says of the card. “It’s really Ram found that social integration and routine
not designed to track their social interactions, were stronger predictors than end-of-term
but you can, because you have a timestamp and grades, one of the traditionally used predictors of
location information.” freshman retention in higher education.
For example, if Student A on multiple The problem with relying solely on grades
occasions uses her CatCard at the same location for making predictions is that national literature
and at roughly the same time that Student B uses suggests freshmen who ultimately leave the
her card, the pattern suggests a social interaction university make the decision to do so in the first
between the two. 12 weeks of the 16-week semester, and often as
Working in partnership with UA Information early as the first four weeks — long before final
Technology, Ram gathered and analyzed data on grades are posted, Ram says.
freshman CatCard usage over a three-year period. “A public university like ours is very large, and
She then used that data to create large networks students can get lost,” Ram says. “There are social
mapping which students interacted with one science theories that indicate that when these
another and how often. She also looked at how students come in, they need to establish a regular
students’ interactions changed over time by routine, learn how to manage their time, and they
constructing networks representing two weeks of need to get socially integrated. Those are some of
data at a time over a 12-week period. the reasons they tend to drop out — they’re not
“There are several quantitative measures you socially integrated and they haven’t established a
can extract from these networks, like the size regularity of routine on campus.”