Learning Latent Engagement Patterns of Students in Online Courses
Authors: Arti Ramesh, Dan Goldwasser, Bert Huang, Hal Daume III, Lise Getoor
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We apply our model to real data collected from several Coursera courses and empirically show its ability to capture behavioral patterns of students and predict course completion. |
| Researcher Affiliation | Academia | 1University of Maryland, College Park 2University of California, Santa Cruz |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Full model available at https://github.com/artir/ramesh-aaai14. |
| Open Datasets | No | We evaluate our models on three Coursera MOOCs at University of Maryland: Surviving Disruptive Technologies, Women and the Civil Rights Movement, and Gene and the Human Condition. Our data consists of anonymized student records, grades, and online behavior recorded during the seven week duration of each course. |
| Dataset Splits | Yes | We use ten-fold cross-validation, leaving out 10% of the data for testing and revealing the rest for training the model weights. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running its experiments. |
| Software Dependencies | No | The paper mentions using 'probabilistic soft logic (PSL)' and 'Opinion Finder (Wilson et al. 2005)' but does not provide specific version numbers for these or any other software dependencies. |
| Experiment Setup | No | The paper describes the temporal division of the course data ('start, mid, end') and the training approach ('expectation maximization') but does not provide specific hyperparameter values or other system-level training settings for the models. |