Understanding College Algebra Students through Data Mining
Abstract
In a College Algebra class of 1,200 students, comparable to those at most state funded universities, the greatest obstacle to providing personalized, effective education is the anonymity of the students. Data mining provides a method for describing students by looking for patterns in the large amounts of information they generate. Traditionally, educational researchers have categorized students using a pre-existing framework developed after years of qualitative research and classroom studies. However, by using computer algorithms, or “black box” data mining methods, to analyze data, one can avoid the problem of determining if preconceived frameworks are relevant or valid. In this session, we will review a study conducted at a mid-sized public university of the academic behavior of College Algebra students. The presenter will review how the data was collected, analyzed and synthesized to extract the defining characteristics of student clusters. Then, the presenter will lead discussion on ideas for implementing differentiated instruction and targeted interventions for struggling students.
Location
Room 2903
Recommended Citation
Manspeaker, Rachel, "Understanding College Algebra Students through Data Mining " (2012). SoTL Commons Conference. 10.
https://digitalcommons.georgiasouthern.edu/sotlcommons/SoTL/2012/10
Understanding College Algebra Students through Data Mining
Room 2903
In a College Algebra class of 1,200 students, comparable to those at most state funded universities, the greatest obstacle to providing personalized, effective education is the anonymity of the students. Data mining provides a method for describing students by looking for patterns in the large amounts of information they generate. Traditionally, educational researchers have categorized students using a pre-existing framework developed after years of qualitative research and classroom studies. However, by using computer algorithms, or “black box” data mining methods, to analyze data, one can avoid the problem of determining if preconceived frameworks are relevant or valid. In this session, we will review a study conducted at a mid-sized public university of the academic behavior of College Algebra students. The presenter will review how the data was collected, analyzed and synthesized to extract the defining characteristics of student clusters. Then, the presenter will lead discussion on ideas for implementing differentiated instruction and targeted interventions for struggling students.
