Mapping Literature Landscapes with Data-Driven Discovery: A Case Study on MOEA/D

TL;DR

This paper presents LitLA, a comprehensive data-driven workflow for mapping large-scale scientific literature landscapes, demonstrated through a detailed case study on MOEA/D research, revealing insights into research trends, collaborations, and future directions.

Contribution

The paper introduces LitLA, an end-to-end system that constructs and analyzes large bibliographic knowledge graphs for scientific landscapes, integrating diverse metadata and enabling exploratory analysis.

Findings

Constructed a KG with over 5,400 papers and 78,000 keywords.

Mapped collaboration and citation networks to analyze community growth.

Explored latent patterns to predict future research directions.

Abstract

We are living in an era of "big literature", where scientific literature is expanding exponentially. While this growth presents new opportunities, it complicates mapping global scientific research landscapes, as manual review methods become infeasible. Recent advancements in machine learning, complex networks, and natural language processing have enabled numerous data-driven discovery methods. Building upon these tools, we introduce an end-to-end workflow for analyzing large-scale literature landscapes, LitLA. This workflow first integrates diverse publication metadata into a bibliographic knowledge graph (KG) representing the research landscape. It then offers tools for exploratory analysis of various landscape aspects. We demonstrate the effectiveness of LitLA via a case study on follow-up works of multi-objective evolutionary algorithm based on decomposition (MOEA/D). In doing so, we constructed the MOEA/D research landscape as a KG comprising over 5,400 papers, 10,000 authors, 1,600 institutions, and 78,000 keywords. With this landscape, we start with descriptive statistics and investigate prominent topics pertaining to MOEA/D and interrogate their spatial-temporal and bilateral relationships. We then map the collaboration and citation networks to reveal the community's growth over time. We further experiment whether learning on latent patterns of this landscape can hint on future research directions.