Paper: arXiv 2312.11531

Authors: Ana Fernández Vilas, Rebeca Díaz Redondo, Antón Lorenzo García

Abstract

There is a consensus about the good sensing characteristics of Twitter to mine and uncover knowledge in financial markets, being considered a relevant feeder for taking decisions about buying or holding stock shares and even for detecting stock manipulation. Although Twitter hashtags allow to aggregate topic-related content, a specific mechanism for financial information also exists: Cashtag. However, the irruption of cryptocurrencies has resulted in a significant degradation on the cashtag-based aggregation of posts. Unfortunately, Twitter’ users may use homonym tickers to refer to cryptocurrencies and to companies in stock markets, which means that filtering by cashtag may result on both posts referring to stock companies and cryptocurrencies. This research proposes automated classifiers to distinguish conflicting cashtags and, so, their container tweets by analyzing the distinctive features of tweets referring to stock companies and cryptocurrencies. As experiment, this paper analyses the interference between cryptocurrencies and company tickers in the London Stock Exchange (LSE), specifically, companies in the main and alternative market indices FTSE-100 and AIM-100. Heuristic-based as well as supervised classifiers are proposed and their advantages and drawbacks, including their ability to self-adapt to Twitter usage changes, are discussed. The experiment confirms a significant distortion in collected data when colliding or homonym cashtags exist, i.e., the same $ acronym to refer to company tickers and cryptocurrencies. According to our results, the distinctive features of posts including cryptocurrencies or company tickers support accurate classification of colliding tweets (homonym cashtags) and Independent Models, as the most detached classifiers from training data, have the potential to be trans-applicability (in different stock markets) while retaining performance.

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper uses standard machine learning models (SVM, LSTM) and statistical tests, presenting moderate mathematical complexity, but is highly empirical with real-world Twitter data, a specific dataset (LSE-100), and detailed performance analysis of multiple classifiers.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Distinguish conflicting cashtags<br>between stocks and crypto"] --> B["Data Input<br>London Stock Exchange FTSE-100 & AIM-100<br>Twitter Cashtags $"]
  
  B --> C{"Methodology"}
  C --> D["Heuristic-based Classifier<br>Rule-based logic"]
  C --> E["Supervised Classifier<br>Feature analysis & ML"]
  
  D --> F["Computational Process<br>Feature Extraction & Model Training"]
  E --> F
  
  F --> G["Key Findings / Outcomes<br>Significant data distortion confirmed<br>Accurate classification achieved<br>Independent Models show trans-applicability"]

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 automated classifiers to distinguish conflicting cashtags in tweets referring to stock companies and cryptocurrencies.

Source sentence
This research proposes automated classifiers to distinguish conflicting cashtags and, so, their container tweets by analyzing the distinctive features of tweets referring to stock companies and cryptocurrencies.

Assumes 1

  • Tweets are correctly labeled as cryptocurrency or company by expert manual annotation. data
    Source sentence
    tweets were manually annotated (cryptocurrency or company) by expert considering their content, the user’s characteristics and any additional information added to the tweet by a hyperlink were carefully analyzed.

Data

  • Non-homonym Cryptocurrencies tweets text-news unknown
    Source sentence
    Non-homonym Cryptocurrencies tweets: a set of tweets that contains at least one of the cashtags of non-homonym cryptocurrencies, that is, no coincident with the tickers in FTSE-100 and AIM-100.
  • Non-homonym LSE-100 tweets text-news unknown
    Source sentence
    Non-homonym LSE-100 tweets: a set of tweets that have at least one cashtag from an LSE-100 co…
  • Homonym cashtags dataset text-news unknown
    Source sentence
    The set of Homonym tickers is shown in Table I and it is the main scenario analyzed in this paper: the incidence of new tweets related to cryptocurrencies on the tweets referring to a company in a stock exchange (LSE-100 in our case).

Recognised sources: Twitter / X

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • Extended SVM classifier achieves accuracy 0.997, F‑Score 0.938 and AUC 0.997, with precision >95% and recall >90%. performance
    Source sentence
    A slight improvement in all measurements can be appreciated in Table X, especially accuracy and F-score and even more remarkable in terms of AUC with a value practically equal to 1
  • LSTM‑adapted SVM classifier reaches accuracy 0.999, F‑Score 0.975 and AUC 0.9990, but only slight improvement over previous classifiers. performance
    Source sentence
    ... Since the extra computational load in LSTM‑SVM classifier does not provide a significant improvement in performance (slight improvement from previous classifiers) is not worthy.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 22 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.