TY - UNPB
T1 - A Semi-Automated Solution Approach Selection Tool for Any Use Case via Scopus and OpenAI
T2 - a Case Study for AI/ML in Oncology
AU - Kılıç, Deniz Kenan
AU - Vasegaard, Alex Elkjær
AU - Desoeuvres, Aurélien
AU - Nielsen, Peter
N1 - The paper is under review in Expert Systems with Applications, Elsevier
PY - 2023/7/10
Y1 - 2023/7/10
N2 - In today's vast literature landscape, a manual review is very time-consuming. To address this challenge, this paper proposes a semi-automated tool for solution method review and selection. It caters to researchers, practitioners, and decision-makers while serving as a benchmark for future work. The tool comprises three modules: (1) paper selection and scoring, using a keyword selection scheme to query Scopus API and compute relevancy; (2) solution method extraction in papers utilizing OpenAI API; (3) sensitivity analysis and post-analyzes. It reveals trends, relevant papers, and methods. AI in the oncology case study and several use cases are presented with promising results, comparing the tool to manual ground truth.
AB - In today's vast literature landscape, a manual review is very time-consuming. To address this challenge, this paper proposes a semi-automated tool for solution method review and selection. It caters to researchers, practitioners, and decision-makers while serving as a benchmark for future work. The tool comprises three modules: (1) paper selection and scoring, using a keyword selection scheme to query Scopus API and compute relevancy; (2) solution method extraction in papers utilizing OpenAI API; (3) sensitivity analysis and post-analyzes. It reveals trends, relevant papers, and methods. AI in the oncology case study and several use cases are presented with promising results, comparing the tool to manual ground truth.
KW - cs.AI
KW - cs.IR
KW - cs.LG
U2 - 10.48550/arXiv.2307.04573
DO - 10.48550/arXiv.2307.04573
M3 - Preprint
BT - A Semi-Automated Solution Approach Selection Tool for Any Use Case via Scopus and OpenAI
PB - arXiv
ER -