Paper: arXiv 2306.02148

Authors: David Ardia, Keven Bluteau

Abstract

We examine the influence of Twitter promotion on cryptocurrency pump-and-dump events. By analyzing abnormal returns, trading volume, and tweet activity, we uncover that Twitter effectively garners attention for pump-and-dump schemes, leading to notable effects on abnormal returns before the event. Our results indicate that investors relying on Twitter information exhibit delayed selling behavior during the post-dump phase, resulting in significant losses compared to other participants. These findings shed light on the pivotal role of Twitter promotion in cryptocurrency manipulation, offering valuable insights into participant behavior and market dynamics.

Complexity vs Empirical Score

  • Math Complexity: 3.0/10
  • Empirical Rigor: 7.5/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper relies on standard event-study methodology and regression analysis with statistical significance reporting, indicating moderate empirical implementation with backtest-ready data, but contains no complex mathematical derivations or advanced statistical theory.

Research Flowchart

  flowchart TD
  A["Research Goal"] --> B["Data Collection"]
  B --> C["Abnormal Returns<br>Volume Analysis<br>Tweet Activity"]
  C --> D["Computational Analysis"]
  D --> E{"Key Findings"}
  E --> F["Twitter drives<br>attention & pre-event returns"]
  E --> G["Investors using Twitter<br>sell late & lose money"]

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 investigates how Twitter promotion affects cryptocurrency pump‑and‑dump events by analyzing abnormal returns, trading volume and tweet activity.

Source sentence
We examine the influence of Twitter promotion on cryptocurrency pump-and-dump events.

Assumes 4

  • The analysis is limited to events on the Binance exchange using the Bitcoin trading pair. data
    Source sentence
    on events occurring on the Binance exchange using the Bitcoin (BTC) trading pair.
  • Bitcoin is unlikely to be the primary target of pump‑and‑dump schemes. market
    Source sentence
    speculative asset, is unlikely to be the primary target of pump-and-dump schemes.
  • Events involving highly popular coins (Dogecoin, Litecoin, Ethereum, Cardano) are excluded due to Twitter data‑collection limits. data
    Source sentence
    We exclude events related to Dogecoin, Litecoin, Ethereum, and Cardano, as their widespread popularity posed challenges in collecting data from Twitter.
  • Abnormal tweet counts and abnormal returns are measured over one‑minute intervals. statistical
    Source sentence
    We gather volume and closing price data for cryptocurrencies at a one‑minute frequency...

Data

  • Pump‑and‑dump events database alternative public
    2019‑02‑02 to 2022‑02‑02 · 1,160 pump‑and‑dump events on Binance
    Source sentence
    In total, our dataset comprises 1,160 pump-and-dump events.
  • Telegram messages · Telegram API text-news public
    messages from >100 pump‑and‑dump groups
    Source sentence
    The Telegram API, which is publicly accessible, facilitated downloading all messages from the groups or channels we had subscribed to or joined.
  • Price and volume data · www.cryptoarchive.com.au (Binance API) market-prices public
    minute‑level price and volume for Binance listed tokens
    Source sentence
    We gather volume and closing price data for cryptocurrencies at a one‑minute frequency from the website www.cryptoarchive.com.au.
  • Twitter data · Twitter API text-news public
    tweets mentioning pump‑and‑dump events
    Source sentence
    Twitter is a microblogging social network enabling users to share posts with a maximum…

Recognised sources: Binance Twitter / X

Costs

Not applicable The paper reports no trading or execution result.

Finds 5

  • A higher abnormal number of tweets in the last 30 minutes before an event is positively and significantly associated with higher abnormal returns. statistical
    Source sentence
    We observe a positive and statistically significant relationship between the abnormal number of tweets and abnormal returns.
  • The cumulative abnormal return before the event is significantly negatively related to the abnormal return during the dump phase, indicating larger pumps lead to larger dumps. statistical
    Source sentence
    Our findings reveal a significant negative relationship between the cumulative abnormal return at and preceding the event and its equivalent during the dump window.
  • There is no significant relationship between pre‑event tweet volume and the cumulative abnormal return during the dump window, suggesting Twitter‑informed investors do not sell during the dump. statistical
    Source sentence
    We do not observe a significant relationship between the abnormal number of tweets before the event and the cumulative abnormal return during the dump window.
  • Investors who receive information via Twitter sell later, causing a predominantly negative post‑dump abnormal return and larger losses compared to other participants. performance
    Source sentence
    We observe a predominantly negative and statistically significant relationship between the post-dump abnormal return and the cumulative abnormal number of tweets before the event.
  • Twitter promotion is pivotal in attracting participants to pump‑and‑dump events, shaping participant behavior before, during, and after the event. theoretical
    Source sentence
    Our regression analysis further confirms the influence of Twitter activity on abnormal returns before, during, and after the event, highlighting the significance of social media in shaping participant behavior.

Checked by others

Supported by

  • Cross-Domain Shopping and Stock Trend Analysis (2022)
    On the question: Do spikes in tweet volume predict short‑term positive returns in stocks or cryptocurrencies?
    Compare the findings

    This paper: A higher abnormal number of tweets in the last 30 minutes before an event is positively and significantly associated with higher abnormal returns.

    That paper: An increase in the number of tweets precedes an increase in the number of "Big Winning" stocks by 0‑1 days.

    Both find a positive link: A shows tweet rise precedes more "Big Winning" stocks by 0‑1 days; B shows abnormal tweets in the last 30 min associate with higher abnormal returns.

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.