Exportar Publicação

Christopher McCarthy, Cassandra M. Brooks, Sternberg, Troy, Kyle Shaney, Buho Hoshino & Buho Hoshino (2026). Ai-Assisted Multi-Target Classification for Research-Policy Alignment in Conservation Science. Ecological Informatics. 94,  103669

C. McCarthy et al.,  "Ai-Assisted Multi-Target Classification for Research-Policy Alignment in Conservation Science", in Ecological Informatics, vol. 94, pp.  103669, 2026

@article{mccarthy2026_1779610794506,
	author = "Christopher McCarthy and Cassandra M. Brooks and Sternberg, Troy and Kyle Shaney and Buho Hoshino and Buho Hoshino",
	title = "Ai-Assisted Multi-Target Classification for Research-Policy Alignment in Conservation Science",
	journal = "Ecological Informatics",
	year = "2026",
	volume = "94",
	number = "",
	doi = "10.2139/ssrn.5390788",
	pages = " 103669"
}

TY  - JOUR
TI  - Ai-Assisted Multi-Target Classification for Research-Policy Alignment in Conservation Science
T2  - Ecological Informatics
VL  - 94
AU  - Christopher McCarthy
AU  - Cassandra M. Brooks
AU  - Sternberg, Troy
AU  - Kyle Shaney
AU  - Buho Hoshino
AU  - Buho Hoshino
PY  - 2026
SP  -  103669
SN  - 1574-9541
DO  - 10.2139/ssrn.5390788
AB  - Scientific research underpins effective conservation policy, yet current approaches for assessing whether sci- entific outputs meaningfully support defined management objectives rely primarily on manual expert review. This limitation constrains scalability, is time intensive and introduces potential bias in identifying knowledge gaps. We present a framework combining AI-assisted multi-target classification with systematic coverage analysis for automated evaluation of research alignment with conservation objectives. We compare traditional machine learning (TF-IDF + logistic regression), a generic BERT baseline, and an enhanced SciBERT approach incorpo- rating domain-specific adaptations including multi-target architecture, balanced loss functions, and target weighting optimized for conservation science. The framework classifies research topics and conservation objective alignment, two dimensions requiring comprehension of scientific content and policy implications. We demonstrate the approach using 295 expert-annotated peer-reviewed studies from the Ross Sea region Marine Protected Area in Antarctica. Our enhanced multi-target SciBERT model achieved 70.0% macro F1, out- performing TF-IDF (59.5%) and BERT (52.0%) baselines, with per-target improvements of 21% on research topics and 14.5% on conservation objectives. The framework achieved 78% agreement with expert annotations, with particularly strong performance on conservation objective alignment (87.7% F1, 94% agreement). The integrated system successfully identified and quantified descriptive patterns in research coverage across thematic and policy dimensions, enabling systematic assessment for research prioritization and automated coverage analysis. While demonstrated in the Antarctic context, the framework architecture is broadly transferable, though successful adaptation requires retraining with domain-specific expert annotations and fine-tuning to match local management frameworks.
ER  -