Using CMS reports for data mining
Colleges Mine Data to Predict Dropouts - Chronicle.com
John P. Campbell's data mining project at Purdue is featured in the Chronicle this week. I first heard about this project at Educause Midwest in 2007; the project is much further now. Campbell and his colleagues are able to notify students when the data indicates the student is struggling, and students are responding.
From the article: "Purdue researchers found that students in the moderate-risk (yellow light) group who received the e-mail messages did better in the course than did their counterparts in a control group. Most of the students identified as being at highest risk (red light) still did not rectify their situations or take advantage of campus resources, however."
The middle range of students is a big group - if this type of system can help them, then it certainly has promise.
I wonder how successful this program would be if students were more widely aware of it. Would they find it intrusive? Would they try to game the system by logging in more or clicking around the discussion area in order to make it seem like they are more engaged? What do you think?
