Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Topic Modeling on Health Journals With Regularized Variational Inference
Authors: Robert Giaquinto, Arindam Banerjee
AAAI 2018 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our results show significant improvements over competing topic models particularly after regularization, and highlight the DAP model s unique ability to capture common journeys shared by different authors. ... Section 5 introduces the evaluation dataset and procedure. Section 6 shares the results of the experiments. |
| Researcher Affiliation | Academia | Robert Giaquinto, Arindam Banerjee Dept of Computer Science & Engineering University of Minnesota, Twin Cities {EMAIL, EMAIL} |
| Pseudocode | No | No structured pseudocode or algorithm blocks are provided. The generative process of the model is described in prose. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | No | The Caring Bridge (CB) dataset is mentioned: 'The full dataset includes 13.1 million journals written by approximately half a million authors between 2006 and 2016. From the CB dataset we draw an evaluation dataset consisting of journals written by authors who posted, on average, at least twice a month over a one year period.' However, no link, DOI, repository, or citation for public access to this specific dataset is provided. |
| Dataset Splits | No | The paper states: 'Journals are split into training and test sets with 90% of each author s journals (N = 103, 018) for training and 10% (N = 11, 728) for testing.' It also mentions '10-fold cross validation'. However, a separate validation split (e.g., for hyperparameter tuning) is not explicitly mentioned. |
| Hardware Specification | No | The paper mentions 'University of Minnesota Supercomputing Institute (MSI) for technical support' in the acknowledgments, but no specific hardware details such as GPU/CPU models, processor types, or memory used for experiments are provided. |
| Software Dependencies | No | No specific software dependencies with version numbers (e.g., library names with versions) are mentioned. |
| Experiment Setup | Yes | Following the approach of others, we simply fix the number of topics at 25 for all models. The number of personas learned by the DAP model is fixed at 15. |