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 [1].
Mapping the landscape of Artificial Intelligence applications against COVID-19
Authors: Joseph Bullock, Alexandra Luccioni, Katherine Hoffman Pham, Cynthia Sin Nga Lam, Miguel Luengo-Oroz
JAIR 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this review, we present an overview of recent studies using Machine Learning and, more broadly, Artificial Intelligence, to tackle many aspects of the COVID19 crisis. |
| Researcher Affiliation | Collaboration | Joseph Bullock EMAIL United Nations Global Pulse, New York, NY, USA Institute for Data Science, Durham University, United Kingdom Alexandra Luccioni EMAIL Mila Québec Artificial Intelligence Institute Université de Montréal, Montréal, Canada Katherine Hoffmann Pham EMAIL United Nations Global Pulse, New York, NY, USA NYU Stern School of Business, New York, NY, USA Cynthia Sin Nga Lam EMAIL United Nations Global Pulse, New York, NY, USA Global Coordination Mechanism on NCDs, World Health Organization, Geneva, Switzerland Miguel Luengo-Oroz EMAIL United Nations Global Pulse, New York, NY, USA |
| Pseudocode | No | The paper describes various methods and approaches conceptually but does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper is a review of existing AI applications and does not describe a novel methodology for which source code would be provided. While it mentions open-source datasets and tools used by other research, it does not provide its own implementation code. |
| Open Datasets | Yes | 6. Datasets and Resources The success of the global effort to use AI techniques to address the COVID-19 pandemic hinges upon sufficient access to data. Machine Learning, and Deep Learning in particular, requires notoriously large amounts of data and computing power in order to develop and train new algorithms and neural network architectures. In this section, we describe some of the datasets and data collection efforts that exist at the present time. ... CORD-19 dataset (Wang et al., 2020) ... COVID-19 Tweet IDs dataset (Chen et al., 2020b) ... |
| Dataset Splits | No | The paper is a review and does not describe any specific experiments conducted by the authors that would require dataset splits for reproduction. |
| Hardware Specification | No | The paper is a review and does not describe specific experimental setups or hardware used for conducting its own research. |
| Software Dependencies | No | The paper is a review and does not detail specific ancillary software dependencies with version numbers used for its own methodology. |
| Experiment Setup | No | The paper is a review and does not describe any specific experimental setup details or hyperparameters for its own methodology. |