The Generation of Hybrid Feature-Based Research Topics Using Text Mining and K-Means Algorithms for Government Science and Technology Projects

Abstract

Many research projects contain large amounts of contextual data. This helps researchers quickly understand the research topic of a research project from large amounts of contextual data. In this paper, we propose the topic identification system, which using text mining and K-means algorithm to generate hybrid feature-based research topics for government science and technology projects (GRB) projects. Using the titles, abstracts and keywords of research projects for cross-analysis, and utilize natural language processing technology to obtain keywords that determine hybrid features from a large amount of contextual data. Then we use the K-means algorithm to group and analyze research topics for GRB projects. Finally, the framework makes it possible to find optimal functions and clusters using ChatGPT. Then, the results of ChatGPT are used to generate research topics.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 3 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.