Creating a Spam Filter
Comments
Contributed By
Description
This activity asks students to work in a team to develop a set of rules that can be used to program a SPAM filter for a client. The rules are based on characteristics of the subject lines of emails. Students are given samples of SPAM and non-SPAM subject lines to examine. After their rules are ready, they are given a test set of data to use and are asked to come up with a numerical measure to quantify how well their method (model) works. Each team writes a report describing how their model works and how well it performed on the test data. This activity could serve as an introduction to ideas of classification. Alternatively, the activity could be the basis for student introduction to types of statistical errors. Less
Learning Registry Activity
Bookmarks
Topics and Grades
Grade: Undergraduate to Graduate
Topics: Data Analysis, Statistics, and Probability, Mathematics, Professional Development
Resource Pedagogy
Resource Type/Classification:
- Teacher Materials
Tool for: Teachers