Paper: arXiv 2306.05803

Authors: Lubdhak Mondal, Udeshya Raj, Abinandhan S, Began Gowsik S, Sarwesh P, Abhijeet Chandra

Abstract

This study investigates the relationship between narratives conveyed through microblogging platforms, namely Twitter, and the value of crypto assets. Our study provides a unique technique to build narratives about cryptocurrency by combining topic modelling of short texts with sentiment analysis. First, we used an unsupervised machine learning algorithm to discover the latent topics within the massive and noisy textual data from Twitter, and then we revealed 4-5 cryptocurrency-related narratives, including financial investment, technological advancement related to crypto, financial and political regulations, crypto assets, and media coverage. In a number of situations, we noticed a strong link between our narratives and crypto prices. Our work connects the most recent innovation in economics, Narrative Economics, to a new area of study that combines topic modelling and sentiment analysis to relate consumer behaviour to narratives.

Complexity vs Empirical Score

  • Math Complexity: 2.5/10
  • Empirical Rigor: 6.5/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The math complexity is low to moderate, relying primarily on standard NLP techniques like GSDMM and TF-IDF without advanced statistical derivations. The empirical rigor is relatively high due to the use of a large real-world dataset (10M+ tweets), explicit data collection and preprocessing steps, and application to cryptocurrency price data, making it more implementation-heavy.

Research Flowchart

  flowchart TD
  A["Research Goal: Causality between<br>Sentiment & Cryptocurrency Prices"] --> B["Data Input:<br>Twitter Microblogging Data"]
  B --> C["Computational Process 1:<br>Topic Modelling<br>Unsupervised ML"]
  B --> D["Computational Process 2:<br>Sentiment Analysis"]
  C & D --> E{"Integration & Analysis"}
  E --> F["Key Findings & Outcomes"]
  F --> G["Identified 4-5 Narratives<br>e.g., Investment, Tech, Regulation"]
  F --> H["Strong Link Discovered<br>between Narratives & Prices"]
  F --> I["Contribution:<br>Linking Narrative Economics<br>to Consumer Behavior"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes a unique technique that builds cryptocurrency narratives by combining short‑text topic modelling with sentiment analysis.

Source sentence
Our study provides a unique technique to build narratives about cryptocurrency by combining topic modelling of short texts with sentiment analysis.

Assumes 4

  • The research assumes symmetric Dirichlet priors for the GSDMM model. model
    Source sentence
    it is essential to note that the research assumes symmetric Dirichlet priors.
  • Each document (tweet) is assumed to contain only one topic. model
    Source sentence
    assumes just one topic per document.
  • Only English‑language tweets are used in the analysis. data
    Source sentence
    We obtained >10M English‑only tweets from Twitter API v2 Academic Research product subcategory for this investigation.
  • TF‑IDF is used to create stopwords, assuming it better captures word significance than Bag of Words. model
    Source sentence
    We picked TF‑IDF over Bag of Words (BoW) for creating stopwords since Bag of Words (BoW) needs constructing a bag of comparable terms that may match the words in Tweets.

Data

  • Twitter API v2 Academic Research tweets · Twitter text-news public
    Source sentence
    We obtained >10M English‑only tweets from Twitter API v2 Academic Research product subcategory for this investigation.

Recognised sources: Twitter / X Binance

Costs

Not applicable The paper reports no trading or execution result.

Finds 3

  • The authors observed a strong link between the extracted narratives and cryptocurrency prices. statistical
    Source sentence
    In a number of situations, we noticed a strong link between our narratives and crypto prices.
  • Four to five cryptocurrency‑related narratives were identified, covering investment, technology, regulation, assets, and media coverage. other
    Source sentence
    we revealed 4‑5 cryptocurrency‑related narratives, including financial investment, technological advancement related to crypto, financial and political regulations, crypto assets, and media coverage.
  • A structural break in the daily Bitcoin price series was detected between January 2014 and May 2021. statistical
    Source sentence
    we discovered a structural break in the daily bitcoin price series beginning from January 2014 to May 2021.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 16 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.