Challenge: to automate the assessments of online discussions in an educational setting Goal: formative assessment (gauging progress, aiding learning), and summative assessments (scoring)
Some Resources:
http://www.irrodl.org/index.php/irrodl/article/view/1857/3067
https://pdfs.semanticscholar.org/b89f/3d846b4f2d8ac91096efd93762d3cd773a0c.pdf
http://files.eric.ed.gov/fulltext/EJ768879.pdf
http://www.sciencedirect.com/science/article/pii/S0360131504000788
https://www.ets.org/research/topics/as_nlp/
http://nlp.stanford.edu/courses/cs224n/2013/reports/song.pdf
Possible Data Sources:
https://www.kaggle.com/c/asap-aes (from the automated essay scoring competition)
~2,000 untagged posts from several recent courses on the topic of Cyber Security. I have a commitment from work that faculty and mentors will label some portion of this data to use as a test set.
https://docs.google.com/document/d/1kGt_-UIQbe0GBvlaxf0ebn4t_beJsgbaveENis6b4XE/edit?ts=583246ec
clone the repo
from the root of the repo, run make notebook
in the browser, go to: localhost:9126