Paper: arXiv 2403.00785
Authors: Oluwafemi F Olaiyapo
Abstract
The objective of this research is to examine how sentiment analysis can be employed to generate trading signals for the Foreign Exchange (Forex) market. The author assessed sentiment in social media posts and news articles pertaining to the United States Dollar (USD) using a combination of methods: lexicon-based analysis and the Naive Bayes machine learning algorithm. The findings indicate that sentiment analysis proves valuable in forecasting market movements and devising trading signals. Notably, its effectiveness is consistent across different market conditions. The author concludes that by analyzing sentiment expressed in news and social media, traders can glean insights into prevailing market sentiments towards the USD and other pertinent countries, thereby aiding trading decision-making. This study underscores the importance of weaving sentiment analysis into trading strategies as a pivotal tool for predicting market dynamics.
Complexity vs Empirical Score
- Math Complexity: 2.5/10
- Empirical Rigor: 6.0/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper relies on basic ML algorithms like Naive Bayes and simple metrics like weighted averages, keeping math complexity low; however, it is grounded in real-world financial data (news/social media) and outlines specific data sources and processing steps, giving it practical, implementation-oriented rigor.
Research Flowchart
flowchart TD
Goal["Research Goal:<br>Forecast Forex (USD) movements<br>using news & social media sentiment"] -->|"Input Data"| Data
subgraph Data ["Data Inputs"]
News["News Articles"]
SocMed["Social Media Posts"]
end
Data -->|"Processing"| Methodology["Methodology:<br>1. Lexicon-Based Analysis<br>2. Naive Bayes ML Algorithm"]
Methodology -->|"Computational Process"| SentimentScore["Generate Sentiment Scores"]
SentimentScore -->|"Signal Generation"| TradingSignal["Create Trading Signals:<br>Buy/Sell/Hold"]
TradingSignal -->|"Validation"| Findings["Key Findings/Outcomes:<br>- Sentiment predicts market movements<br>- Effective across market conditions<br>- Valuable for trading strategies"]
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 methodology using lexicon‑based (VADER) and Naïve Bayes sentiment analysis combined with technical indicators to generate Forex trading signals.
Source sentence
This project proposed and implemented a methodology based on lexicon-based analysis and Naïve Bayes to assign a neutral, positive, or negative score to the sentiment of news articles and social media posts related to United States Dollars (USD), and then combine technical analysis indicators to generate a signal.
Assumes 5
- Naïve Bayes assumes all features (words) are independent. model
Source sentence
If one assumes that all features are independ‑ent, this relationship can be further simplified to:
- Gaussian distribution is assumed for estimating class probabilities in Naïve Bayes. statistical
Source sentence
For estimating ( ) P y and (| ) i P x y , a Gaussian assumption is leverage on the dependent varia‑ble through the Maximum A Posteriori (MAP):
- The H4 time‑frame is appropriate for linking sentiment to price action. market
Source sentence
For the purpose of this research, the H4 time‑frame was chosen for analysis.
- A trading signal is only generated when sentiment analysis aligns with technical indicators. execution
Source sentence
If the sentiment analysis and the technical indicators do not align, then no signal will be generated, and traders would have to wait and exercise caution.
Show 1 more
- Slippage is present but mitigated in the H4 timeframe. execution
Source sentence
This slippage was especially pronounced in timeframes like M1 and M5, where algorithmic trading systems respond instantly to informa‑tion. However, in the H4 timeframe these algo‑rithms react with a cushion against news events and sentiment scores, helping to mitigate the impact of slippage.
Data
- News and social media dataset text-news unknown
Source sentence
The dataset was collected from reputable news sources such as Reuters, Bloomberg, and Twitter posts.
- Historical Forex price data market-prices unknown
Source sentence
The experiment was based on historical data from April 1st, 2023, to July 26th, 2023.
Costs
Unclear - sources disagree
Source sentence (the authors' words)
This slippage was especially pronounced in timeframes like M1 and M5, where algorithmic trading systems respond instantly to informa‑tion. However, in the H4 timeframe these algo‑rithms react with a cushion against news events and sentiment scores, helping to mitigate the impact of slippage.
Finds 2
- Naïve Bayes generated trading signals yielded a profit of over 12% during the testing period. performance
Source sentence
the signals generated by the Naïve Bayes model showed that a profit of over 12% was gained over the testing period.
- Lexicon‑based signals yielded a profit of 5% over the testing period. performance
Source sentence
While the lexicon-based models using confirma‑tion from the RSI and MA indicators generated a profit of 5% over the testing period.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 23 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.