Mapping the Global Research Landscape in Private Capital Markets: A Computational Bibliometric and NLP-Based Analysis

Advisor: Julius Maisch, M.Sc.

Type: Bachelor’s Thesis
Start: asap

 

Overview

Private capital markets including private equity, venture capital and growth investments have grown substantially in economic importance over the past decades. At the same time, the academic research landscape in this domain remains fragmented across journals, institutions and methodological traditions.

Recent bibliometric work has begun to map the intellectual structure of venture capital and private equity research. In particular, Cumming, Kumar and Lim (2022) provide a comprehensive overview of the thematic foundations and future research directions of the field. However, less attention has been paid to the institutional structure of private capital research and the identification of high-impact research clusters at leading universities.

This thesis aims to computationally map the intellectual and institutional structure of private capital research using bibliometric methods, network science and modern natural language processing techniques. By constructing a comprehensive field-wide research corpus and benchmarking it against an elite-institution subsample, the thesis will analyze thematic specialization, collaboration structures and institutional concentration within private capital research.

Research Objectives

The thesis will consist of four main components:

1. Corpus Construction
   1. Definition of leading finance and entrepreneurship journals
   2. Systematic identification of private capital related publications
   3. Construction of a structured research corpus including authors, affiliations, publication year and citations
   4. Definition of an elite-institution subsample based on transparent ranking criteria
   5. Parsing of research articles using tools such as GROBID to extract structured metadata and text
       
2. Bibliometric and Network Analysis
   1. Identification of core researchers based on publication and citation metrics
   2. Construction of co-authorship and institutional collaboration networks
   3. Application of centrality measures and community detection algorithms
   4. Comparative network analysis of elite institutions and the broader field
       
3. NLP Enabled Thematic Analysis
   1. Text preprocessing and embedding-based vectorization
   2. Dimensionality reduction and clustering
   3. Identification of dominant research themes
   4. Comparative thematic profiling of elite institutions versus the full field
       
4. Institutional Concentration
   1. Identification of high-centrality institutional hubs
   2. Measurement of geographic and institutional concentration
   3. Analysis of thematic specialization and influence within elite research clusters

Requirements

• Strong technical skills (GitHub & Python knowledge required)
• Prior experience with data analysis or NLP strongly preferred
• Ability to independently implement a technically demanding empirical project

Literature

• Cumming, D., Kumar, S., & Lim, W. (2022). Mapping the Venture Capital and Private Equity Research: A Bibliometric Review and Future Research Agenda. Small Business Economics.

Contact & Application

If you are interested in writing your thesis on this topic, please include this project in your application and briefly outline your motivation, research interests, and programming experience. Please note that the thesis topic can be tailored to your interests—for example, by focusing more on econometric modeling, machine learning, or empirical applications.