This paper explores the use of data mining approaches to predict students' final performance based on their participation in online discussion forums. The study examines how instance and attribute selection, different classification algorithms, and the timing of data collection affect prediction accuracy and comprehensibility. A new Moodle module was developed to gather forum participation indicators from 114 university students in a first-year computer science course. Results show that both final and early predictions are feasible, clustering plus class association rules mining offers more interpretable models, and using a subset of attributes and subject-related messages improves classification accuracy.
-
Romero, Cristóbal, et al. "Predicting students' final performance from participation in on-line discussion forums." Computers & Education 68 (2013): 458-472.
-
Members
- Live Games
- JoelR
- Brian
- Como
- IC Essentials
- COSMIN
- Adriano Faria
- Nathan Explosion
- DawPi
- Square Wheels
- Auto Evoke
- YalcinA
- master963
- VAHID
- Chris Anderson
- Myr
- bernhara
- opentype
- ReyDev
- send2yoni
- A Zayed
- terabyte
- Dilip
- ZLTRGO
- adik
- eivindsimensen
- envy
- onlyME
- V0RT3X
- GazzaGarratt
- Analog
- Voyage
- Paul Kaiser
- N700
- Paul
- TracyIsland
- Andy Y
- Omar Barbeytia carretero
- JoeyM
- Ryancoolround
- rainx
- YourSharona
- Kentraiyle Robinson
- MichaelR
- Edward Ellas
- IPS THEME
- aXenDev
- PrettyPixels
- Denis Dyack
- Labis
- DursunKaptan
- MissB
- TheLlamaman
- aLEX49566
- Codepixel
- alsl sndnxnx
- burnyourfeelings
- isvans
- Marius
- Matt
- Thomas Taschler
- Surpac
- JoshB
- Ioannis D
- abobader
- Richard Arch
- bdmusic 24
- Majster87
- TomCat
- Pmw
- Torgeir Rui
- Kammer et
- Nicolas PC
- XwReK
- Claudia999
- Kirill Gromov
- Synergy
- bing11
- Marcin Martyniak
- ArashDev
- ali hagi
- StevenM
- NewVicious
- lukash
- Andhrafriends Admin
- Daffy
- hyprem
- GuitarGathering
- Tripp
- Askancy
- MLK
- Jelly Belly
- eveneme eveneme
- Nomad
- Morphe
- lordi
- shahed
- John Horton
- PayMap
- Serval