Mapping subsets of scholarly information

Area of Science:

• Computer Science
• Bibliometrics
• Scientific Information Management

Background:

• Managing and analyzing large academic literature corpora is challenging.
• Identifying emerging research trends within existing literature is crucial for scientific advancement.

Purpose of the Study:

• To demonstrate the application of machine learning (ML) for analyzing and structuring academic literature.
• To show how ML can identify and delineate emerging research fields within a corpus.
• To facilitate the creation of coherent community structures for researchers.

Main Methods:

• Utilized machine learning algorithms for text analysis and corpus structuring.
• Developed methods to identify patterns indicative of emerging research areas.
• Applied techniques to maintain and evolve the academic literature corpus over time.

Main Results:

• Successfully analyzed and structured a large online corpus of academic literature.
• Demonstrated the capability of ML to identify an emerging research field within the corpus.
• Showcased the potential for improved community organization among researchers.

Conclusions:

• Machine learning offers powerful tools for managing and understanding large-scale academic literature.
• ML-driven identification of research fields can enhance scientific community cohesion.
• This methodology supports the dynamic evolution of scientific knowledge bases.