🎉 🎉   RAPIDMINER 9.5 BETA IS OUT!!!   🎉 🎉

GRAB THE HOTTEST NEW BETA OF RAPIDMINER STUDIO, SERVER, AND RADOOP. LET US KNOW WHAT YOU THINK!

CLICK HERE TO DOWNLOAD

🦉 🎤   RapidMiner Wisdom 2020 - CALL FOR SPEAKERS   🦉 🎤

We are inviting all community members to submit proposals to speak at Wisdom 2020 in Boston.


Whether it's a cool RapidMiner trick or a use case implementation, we want to see what you have.
Form link is below and deadline for submissions is November 15. See you in Boston!

CLICK HERE TO GO TO ENTRY FORM

Analysis of student assigmnents for potential contract cheating

Matt_IrelandMatt_Ireland Member Posts: 1 Newbie
Hello, 

I'm currently an Academic Misconduct Officer for a regional University within Australia. At the present time, myself and other misconduct officers are finding it challenging to identify students that employ "contract cheating" websites where students pay such sites to write  assignments on their behalf and submit them under under the pretense of it being their own work. One such way we can identify this type of misconduct is by comparing previous assignments the submitted has submitted. Because contract cheating websites employ different people to write their assignments, a sudden change in style might indicate the student has used such a service. 

Therefore, I was wondering if there were extensions for rapidminer where word documents can be entered and a type of analysis done such as readability, metadata, punctuation, sentence length, vocabulary and other possible linguistic features? 

Many thanks in advance 
Matt

Answers

  • sgenzersgenzer 12Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,525  Community Manager
    Hi @Matt_Ireland - interesting question! So my first question is the classic one in this field: how much data do you have? A machine learning model "learns" on what we call a 'training set' which in your case would be a large number of sets of student work, with the fraudulent ones somehow indicated. Then you train the model to look for differences and apply to new ones.

    Feel free to follow up with me privately if you want to share more info that you don't want public.

    Scott

    ----------------------
    Don't forget to submit your great ideas for Wisdom 2020! Deadline is November 15.

    Wisdom 2020 – Call for Speakers Form 

Sign In or Register to comment.