[Paper Review] pyBibX -- A Python Library for Bibliometric and Scientometric Analysis Powered with Artificial Intelligence Tools

Valdecy Pereira, Márcio Pereira Basílio+1 more|arXiv (Cornell University)|Apr 27, 2023

Bioinformatics and Genomic Networks17 citations

TL;DR

pyBibX is a Python library that performs bibliometric and scientometric analyses on data from Scopus, Web of Science, and PubMed, combining AI tools for EDA, network analysis, and NLP.

ABSTRACT

Bibliometric and Scientometric analyses offer invaluable perspectives on the complex research terrain and collaborative dynamics spanning diverse academic disciplines. This paper presents pyBibX, a python library devised to conduct comprehensive bibliometric and scientometric analyses on raw data files sourced from Scopus, Web of Science, and PubMed, seamlessly integrating state of the art AI capabilities into its core functionality. The library executes a comprehensive EDA, presenting outcomes via visually appealing graphical illustrations. Network capabilities have been deftly integrated, encompassing Citation, Collaboration, and Similarity Analysis. Furthermore, the library incorporates AI capabilities, including Embedding vectors, Topic Modeling, Text Summarization, and other general Natural Language Processing tasks, employing models such as Sentence-BERT, BerTopic, BERT, chatGPT, and PEGASUS. As a demonstration, we have analyzed 184 documents associated with multiple-criteria decision analysis published between 1984 and 2023. The EDA emphasized a growing fascination with decision-making and fuzzy logic methodologies. Next, Network Analysis further accentuated the significance of central authors and intra-continental collaboration, identifying Canada and China as crucial collaboration hubs. Finally, AI Analysis distinguished two primary topics and chatGPT preeminence in Text Summarization. It also proved to be an indispensable instrument for interpreting results, as our library enables researchers to pose inquiries to chatGPT regarding bibliometric outcomes. Even so, data homogeneity remains a daunting challenge due to database inconsistencies. PyBibX is the first application integrating cutting-edge AI capabilities for analyzing scientific publications, enabling researchers to examine and interpret these outcomes more effectively.

Motivation & Objective

• Enable comprehensive bibliometric and scientometric analysis from raw data sources across major databases.
• Integrate state-of-the-art AI capabilities (embeddings, topic modeling, text summarization) into bibliometric workflows.
• Provide Exploratory Data Analysis with graphical visualizations and network analyses (Citation, Collaboration, Similarity).
• Demonstrate the library on a real dataset to illustrate insights and practical usage.

Proposed method

• Ingest data from Scopus, Web of Science, and PubMed.
• Perform Exploratory Data Analysis with graphical outputs.
• Incorporate network analysis modules for Citation, Collaboration, and Similarity analyses.
• Apply AI/NLP tooling including embedding vectors, Sentence-BERT, BerTopic, BERT, chatGPT, and PEGASUS for text tasks.
• Enable interactive interpretation of results via chatGPT queries.

Experimental results

Research questions

• RQ1 How can AI tools enhance the interpretation of bibliometric and scientometric results?
• RQ2 What are the central authors and collaboration patterns in the analyzed dataset?
• RQ3 What topics emerge from AI-assisted text analysis of the publications?
• RQ4 What impact do data heterogeneity and database inconsistencies have on analyses across sources?

Key findings

• EDA indicates a growing fascination with decision-making and fuzzy logic methodologies.
• Network analysis identifies central authors and notable intra-continental collaboration, with Canada and China as collaboration hubs.
• AI analysis reveals two primary topics and chatGPT predominance in text summarization.
• The library enables researchers to pose questions to chatGPT about bibliometric outcomes.
• Data homogeneity remains challenging due to inconsistencies across databases.