Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2306.13075 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915541869920256 |
|---|---|
| author | Nguyen, Mark Beidler, Peter Tsai, Joseph Anderson, August Chen, Daniel Kinahan, Paul Kang, John |
| author_facet | Nguyen, Mark Beidler, Peter Tsai, Joseph Anderson, August Chen, Daniel Kinahan, Paul Kang, John |
| contents | Investigators, funders, and the public desire knowledge on topics and trends in publicly funded research but current efforts in manual categorization are limited in scale and understanding. We developed a semi-automated approach to extract and name research topics, and applied this to \$1.9B of NCI funding over 21 years in the radiological sciences to determine micro- and macro-scale research topics and funding trends. Our method relies on sequential clustering of existing biomedical-based word embeddings, naming using subject matter experts, and visualization to discover trends at a macroscopic scale above individual topics. We present results using 15 and 60 cluster topics, where we found that 2D projection of grant embeddings reveals two dominant axes: physics-biology and therapeutic-diagnostic. For our dataset, we found that funding for therapeutics- and physics-based research have outpaced diagnostics- and biology-based research, respectively. We hope these results may (1) give insight to funders on the appropriateness of their funding allocation, (2) assist investigators in contextualizing their work and explore neighboring research domains, and (3) allow the public to review where their tax dollars are being allocated. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_13075 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Semi-automated extraction of research topics and trends from NCI funding in radiological sciences from 2000-2020 Nguyen, Mark Beidler, Peter Tsai, Joseph Anderson, August Chen, Daniel Kinahan, Paul Kang, John Computation and Language Computer Vision and Pattern Recognition 68T50 (Primary), 68T10 (Secondary) I.2.7; I.5.3; J.3 Investigators, funders, and the public desire knowledge on topics and trends in publicly funded research but current efforts in manual categorization are limited in scale and understanding. We developed a semi-automated approach to extract and name research topics, and applied this to \$1.9B of NCI funding over 21 years in the radiological sciences to determine micro- and macro-scale research topics and funding trends. Our method relies on sequential clustering of existing biomedical-based word embeddings, naming using subject matter experts, and visualization to discover trends at a macroscopic scale above individual topics. We present results using 15 and 60 cluster topics, where we found that 2D projection of grant embeddings reveals two dominant axes: physics-biology and therapeutic-diagnostic. For our dataset, we found that funding for therapeutics- and physics-based research have outpaced diagnostics- and biology-based research, respectively. We hope these results may (1) give insight to funders on the appropriateness of their funding allocation, (2) assist investigators in contextualizing their work and explore neighboring research domains, and (3) allow the public to review where their tax dollars are being allocated. |
| title | Semi-automated extraction of research topics and trends from NCI funding in radiological sciences from 2000-2020 |
| topic | Computation and Language Computer Vision and Pattern Recognition 68T50 (Primary), 68T10 (Secondary) I.2.7; I.5.3; J.3 |
| url | https://arxiv.org/abs/2306.13075 |