Using Artificial Intuition in Distinct, Minimalist Classification of Scientific Abstracts for Management of Technology Portfolios

TL;DR

This paper introduces a novel method called artificial intuition, leveraging large language models to classify scientific abstracts in a way that mimics expert judgment, aiding strategic management of research portfolios.

Contribution

The paper presents a new approach using LLMs to generate metadata for scientific abstracts, improving classification accuracy and distinction without extensive manual labeling.

Findings

Artificial intuition effectively replicates expert classification.

Method improves distinction among overlapping labels.

Feasible for research portfolio and technology management.

Abstract

Classification of scientific abstracts is useful for strategic activities but challenging to automate because the sparse text provides few contextual clues. Metadata associated with the scientific publication can be used to improve performance but still often requires a semi-supervised setting. Moreover, such schemes may generate labels that lack distinction -- namely, they overlap and thus do not uniquely define the abstract. In contrast, experts label and sort these texts with ease. Here we describe an application of a process we call artificial intuition to replicate the expert's approach, using a Large Language Model (LLM) to generate metadata. We use publicly available abstracts from the United States National Science Foundation to create a set of labels, and then we test this on a set of abstracts from the Chinese National Natural Science Foundation to examine funding trends. We demonstrate the feasibility of this method for research portfolio management, technology scouting, and other strategic activities.