MOOCs Meet Measurement Theory: A Topic-Modelling Approach

Authors: Jiazhen He, Benjamin Rubinstein, James Bailey, Rui Zhang, Sandra Milligan, Jeffrey Chan

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the suitability of our approach with both quantitative experiments on three Coursera MOOCs, and with a qualitative survey of topic interpretability on two MOOCs by domain expert interviews.
Researcher Affiliation Academia Dept. Computing and Information Systems, The University of Melbourne, Australia National ICT Australia Melbourne Graduate School of Education, The University of Melbourne, Australia School of Computer Science and Information Technology, RMIT University, Australia {jiazhenh@student., baileyj, brubinstein, rui.zhang, s.milligan}@unimelb.edu.au, jeffrey.chan@rmit.edu.au
Pseudocode Yes Algorithm 1 NMF-Guttman
Open Source Code No The paper refers to a technical report (arXiv:1511.07961) which might contain additional material, but it does not explicitly state that the source code for the described methodology is released or provide a direct link to a code repository.
Open Datasets No The paper states using data from "three Coursera MOOCs from Education, Economics and Computer Science offered by The University of Melbourne," but does not provide specific access information (e.g., URL, DOI, or a formal citation with author and year) for these datasets to indicate public availability.
Dataset Splits No The paper specifies a "training set (70% students) and a test set (30% students)" but does not explicitly mention or detail a separate validation set split, which is part of the required 'training/test/validation' criteria.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU/GPU models, memory) used to run the experiments, only general statements about using data from Coursera MOOCs.
Software Dependencies No The paper does not provide specific version numbers for any software dependencies (e.g., programming languages, libraries, or frameworks) used in the experiments.
Experiment Setup Yes Hyperparameter Settings Table 4 shows the parameter values used for parameter sensitivity experiments, where the default values in boldface are used in other experiments. The parameters are set using the values in boldface in Table 4.