Desenvolvimento de modelo para predição de cotações de ação baseada em análise de sentimentos de tweets

ArXiv ID: 2309.06538 “View on arXiv”

Authors: Unknown

Abstract

Training machine learning models for predicting stock market share prices is an active area of research since the automatization of trading such papers was available in real time. While most of the work in this field of research is done by training Neural networks based on past prices of stock shares, in this work, we use iFeel 2.0 platform to extract 19 sentiment features from posts obtained from microblog platform Twitter that mention the company Petrobras. Then, we used those features to train XBoot models to predict future stock prices for the referred company. Later, we simulated the trading of Petrobras’ shares based on the model’s outputs and determined the gain of R$88,82 (net) in a 250-day period when compared to a 100 random models’ average performance.

Keywords: sentiment analysis, XGBoost, social media data, predictive modeling, stocks

Complexity vs Empirical Score

• Math Complexity: 3.0/10
• Empirical Rigor: 6.0/10
• Quadrant: Street Traders
• Why: The paper uses standard ML tools (XGBoost) with minimal novel mathematical derivations, but it is highly empirical, involving data collection from APIs, feature engineering (sentiment analysis), and a detailed backtest simulation comparing model performance against random baselines.

  flowchart TD
    A["Research Goal<br>Predict Petrobras stock prices using Twitter sentiment analysis"] --> B["Data Acquisition<br>Collect tweets mentioning Petrobras"]
    B --> C["Feature Extraction<br>Use iFeel 2.0 to extract 19 sentiment features"]
    C --> D["Model Training<br>Train XGBoost regression models"]
    D --> E["Prediction & Simulation<br>Predict future prices & simulate trading"]
    E --> F["Outcome<br>Net gain of R$88.82 over 250 days"]
    F --> G["Benchmark<br>Outperformed 100 random models"]