Sara Hooker
Impact in
- Health Informatics top 5%
- Artificial Intelligence in Healthcare and Education
- Safety Research top 10%
- Ethics and Social Impacts of AI
Papers in
-
- Natural Language Processing Techniques 5
- Topic Modeling 4
- Adversarial Robustness in Machine Learning 3
- Machine Learning and Data Classification 2
- Explainable Artificial Intelligence (XAI) 2
- Co-authors
- Daniel D’souza (2 shared papers)Chirag Agarwal (1 shared paper)Julia Kreutzer (6 shared papers)Patrick A. Lewis (2 shared papers)Beyza Ermiş (4 shared papers)Shayne Longpre (2 shared papers)Marzieh Fadaee (5 shared papers)Aaron Courville (1 shared paper)
- Journals
- Nature Machine Intelligence (2 papers)Nature (1 paper)Patterns (1 paper)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (1 paper)
- Partner nations
- United StatesUnited KingdomCanada
In The Last Decade
Sara Hooker
14 papers receiving 188 citations
Peers
Comparison fields: 5 of 81
- Health Informatics 27
- Safety Research 40
- Artificial Intelligence 110
- Computer Science Applications 11
- Family Practice 2
Countries citing papers authored by Sara Hooker
This map shows the geographic impact of Sara Hooker's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Sara Hooker with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Sara Hooker more than expected).
Fields of papers citing papers by Sara Hooker
This network shows the impact of papers produced by Sara Hooker. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Sara Hooker. The network helps show where Sara Hooker may publish in the future.
Co-authors
The 25 scholars most cited alongside Sara Hooker, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
| # | Work | ||
|---|---|---|---|
| 1 | 2021 | 95 | |
| 2 | 2022 | 26 | |
| 3 | 2024 | 18 | |
| 4 | 2024 | 17 | |
| 5 | 2023 | 10 | |
| 6 | 2024 | 10 | |
| 7 | Selective Brain Damage: Measuring the Disparate Impact of Model Pruning | 2019 | 7 |
| 8 | 2023 | 6 | |
| 9 | 2024 | 4 | |
| 10 | 2024 | 3 | |
| 11 | 2022 | 2 | |
| 12 | 2024 | 2 | |
| 13 | 2025 | 1 | |
| 14 | 2024 | 1 | |
| 15 | 2023 | 0 | |
| 16 | 2024 | 0 | |
| 17 | 2025 | 0 | |
| 18 | 2024 | 0 |
About Sara Hooker
Sara Hooker is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition, Health Informatics, Safety Research and Molecular Biology, having authored 18 papers that have together received 202 indexed citations. Recurring topics across this work include Natural Language Processing Techniques (5 papers), Topic Modeling (4 papers), Adversarial Robustness in Machine Learning (3 papers), Ethics and Social Impacts of AI (2 papers), Artificial Intelligence in Healthcare and Education (2 papers), Machine Learning and Data Classification (2 papers), Explainable Artificial Intelligence (XAI) (2 papers) and Mobile Crowdsensing and Crowdsourcing (1 paper). The work is most often cited by research in Health Informatics (27 citations), Safety Research (40 citations), Artificial Intelligence (110 citations), Computer Science Applications (11 citations) and Family Practice (2 citations). Sara Hooker has collaborated with scholars based in United States, United Kingdom and Canada. Frequent co-authors include Daniel D’souza, Chirag Agarwal, Julia Kreutzer, Patrick A. Lewis, Beyza Ermiş, Shayne Longpre, Marzieh Fadaee, Aaron Courville, Andrea Frome and Pin‐Yu Chen. Their work appears in journals such as Nature Machine Intelligence, Nature, Patterns and 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.