Unveiling Hedge Funds: Topic Modeling and Sentiment Correlation with Fund Performance

Paper: arXiv 2512.06620

Authors: Chang Liu

Abstract

The hedge fund industry presents significant challenges for investors due to its opacity and limited disclosure requirements. This pioneering study introduces two major innovations in financial text analysis. First, we apply topic modeling to hedge fund documents-an unexplored domain for automated text analysis-using a unique dataset of over 35,000 documents from 1,125 hedge fund managers. We compared three state-of-the-art methods: Latent Dirichlet Allocation (LDA), Top2Vec, and BERTopic. Our findings reveal that LDA with 20 topics produces the most interpretable results for human users and demonstrates higher robustness in topic assignments when the number of topics varies, while Top2Vec shows superior classification performance. Second, we establish a novel quantitative framework linking document sentiment to fund performance, transforming qualitative information traditionally requiring expert interpretation into systematic investment signals. In sentiment analysis, contrary to expectations, the general-purpose DistilBERT outperforms the finance-specific FinBERT in generating sentiment scores, demonstrating superior adaptability to diverse linguistic patterns found in hedge fund documents that extend beyond specialized financial news text. Furthermore, sentiment scores derived using DistilBERT in combination with Top2Vec show stronger correlations with subsequent fund performance compared to other model combinations. These results demonstrate that automated topic modeling and sentiment analysis can effectively process hedge fund documents, providing investors with new data-driven decision support tools.

Complexity vs Empirical Score

• Math Complexity: 4.0/10
• Empirical Rigor: 7.5/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper applies well-established NLP models (LDA, Top2Vec, BERTopic, DistilBERT) with minimal novel mathematical derivation, but demonstrates high empirical rigor through a large unique dataset (35,000+ documents), comparative model validation, and quantitative correlation analysis with fund performance.

Research Flowchart

  flowchart TD
  A["Research Goal"] --> B["Data Collection"]
  B --> C{"Topic Modeling<br/>Comparison"}
  
  subgraph C ["Topic Modeling"]
      C1["LDA"]
      C2["Top2Vec"]
      C3["BERTopic"]
  end
  
  C --> D{"Sentiment Analysis<br/>Comparison"}
  
  subgraph D ["Sentiment Analysis"]
      D1["DistilBERT"]
      D2["FinBERT"]
  end
  
  D --> E["Performance Correlation"]
  E --> F["Key Findings"]
  
  F --> F1["LDA: Most interpretable<br/>& robust topics"]
  F --> F2["Top2Vec: Superior<br/>classification performance"]
  F --> F3["DistilBERT: Outperforms<br/>FinBERT for hedge fund docs"]
  F --> F4["DistilBERT + Top2Vec:<br/>Strongest performance correlation"]

Cited References (28)

1. FinBERT: Financial Sentiment Analysis with Pre-trained Language Models (2019) — link
2. A Topic Model for 10-K Management Disclosures (2023)
3. BERTopic: Neural topic modeling with a class-based TF-IDF procedure (2022) — link
4. Machine learning in finance: A topic modeling approach (2022) — link
5. Latent dirichlet allocation (2003)
6. Topic Modelling Meets Deep Neural Networks: A Survey (2021) — link
7. Topic modeling algorithms and applications: A survey (2023) — link
8. Top2Vec: Distributed Representations of Topics (2020) — link

0 of 28 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.