Paper: arXiv 2309.00136
Authors: Ali Asgarov
Abstract
Forecasting financial market trends through time series analysis and natural language processing poses a complex and demanding undertaking, owing to the numerous variables that can influence stock prices. These variables encompass a spectrum of economic and political occurrences, as well as prevailing public attitudes. Recent research has indicated that the expression of public sentiments on social media platforms such as Twitter may have a noteworthy impact on the determination of stock prices. The objective of this study was to assess the viability of Twitter sentiments as a tool for predicting stock prices of major corporations such as Tesla, Apple. Our study has revealed a robust association between the emotions conveyed in tweets and fluctuations in stock prices. Our findings indicate that positivity, negativity, and subjectivity are the primary determinants of fluctuations in stock prices. The data was analyzed utilizing the Long-Short Term Memory neural network (LSTM) model, which is currently recognized as the leading methodology for predicting stock prices by incorporating Twitter sentiments and historical stock prices data. The models utilized in our study demonstrated a high degree of reliability and yielded precise outcomes for the designated corporations. In summary, this research emphasizes the significance of incorporating public opinions into the prediction of stock prices. The application of Time Series Analysis and Natural Language Processing methodologies can yield significant scientific findings regarding financial market patterns, thereby facilitating informed decision-making among investors. The results of our study indicate that the utilization of Twitter sentiments can serve as a potent instrument for forecasting stock prices, and ought to be factored in when formulating investment strategies.
Complexity vs Empirical Score
- Math Complexity: 5.0/10
- Empirical Rigor: 4.0/10
- Quadrant: Lab Rats — high math complexity, limited empirical testing
Why this score: The paper employs advanced ML techniques (LSTMs, BERT) which provide moderate mathematical complexity, but the summary lacks specific details on data preprocessing, backtest performance metrics, or implementation challenges, indicating lower empirical rigor.
Research Flowchart
flowchart TD
A["Research Goal: Predict Stock Prices via Social Media"] --> B["Data Collection"]
B --> C["Data Processing"]
subgraph C ["NLP & Time Series Processing"]
C1["Twitter Sentiment Analysis<br>(Positivity, Negativity, Subjectivity)"]
C2["Historical Stock Data"]
end
C --> D["Modeling: LSTM Neural Network"]
D --> E["Prediction & Validation"]
E --> F["Key Findings: Sentiment is a<br>strong predictor for<br>Tesla & Apple"]
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 an LSTM neural network model that incorporates Twitter sentiment scores and historical stock prices to predict stock price movements.
Source sentence
The data was analyzed utilizing the Long-Short Term Memory neural network (LSTM) model, which is currently recognized as the leading methodology for predicting stock prices by incorporating Twitter sentiments and historical stock prices data.
Assumes 5
- Twitter sentiment from the previous day can be used to forecast the next day's stock price. data
Source sentence
The study aims to assess the effectiveness of utilizing the stock prices and Twitter sentiment values from the previous day to forecast the stock prices of a company for the following day.
- Positivity, negativity, and the previous day's stock price are sufficient predictors of future stock prices. model
Source sentence
We employ the variables of 'positivity,' 'negativity,' and the previous day's stock price as predictors to anticipate the future values of stock prices.
- Time‑series data exhibit strong dependence on prior values, justifying the use of LSTM. statistical
Source sentence
Time-series data that is sequential in nature, such as stock prices, exhibit a high degree of dependence on previous values.
- The collected tweets (ranked by retweet count) are the most influential for stock price movements. data
Source sentence
In order to identify the tweets with the highest potential to affect public opinion and stock valuations, they were categorized according to the number of retweets they received.
Show 1 more
- The split of data into 80% training and 20% testing provides a reliable evaluation of model performance. model
Source sentence
The dataset was split into training and testing sets, with 80% of the data used for training and the remaining 20% for testing.
Data
- Twitter data (tweets_apple.csv, tweets_tesla.csv, etc.) alternative public
Source sentence
We collect Twitter data from the preceding day and merge it with stock market information for statistical analysis...
- Yahoo Finance stock price files (AAPL.csv, TSLA.csv, AMZN.csv, GOOG.csv) market-prices public
Source sentence
The Twitter API and Yahoo Finance API were utilized to compile various datasets, including stock market data files from Yahoo Finance, such as AAPL.csv, TSLA.csv, AMZN.csv, and GOOG.csv
Costs
Not applicable
Finds 2
- The LSTM model achieved a mean absolute error (MAE) of 9.93 in predicting stock prices using historical data and Twitter sentiment scores. predictive-accuracy
Source sentence
The MAE was found to be 9.93, indicating a moderate level of accuracy in the predicted stock prices.
- A robust association was observed between tweet emotions (positivity, negativity, subjectivity) and stock price fluctuations. statistical
Source sentence
Our study has revealed a robust association between the emotions conveyed in tweets and fluctuations in stock prices.
Checked by others
Supported by
- Social Media Emotions and Market Behavior
Compare the findings
This paper: A robust association was observed between tweet emotions (positivity, negativity, subjectivity) and stock price fluctuations.
That paper: Investor emotions extracted from social media forecast daily stock price fluctuations.
Contradicted by
- To the Moon: Analyzing Collective Trading Events on the Wings of Sentiment Analysis
Compare the findings
This paper: A robust association was observed between tweet emotions (positivity, negativity, subjectivity) and stock price fluctuations.
That paper: Twitter activity shows a significant relationship with stock volatility, while tweet sentiment has a weak link to stock performance.
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.