Financial Market Trend Forecasting using Text Sentiment Analysis: Social Media, News and Economic Texts with Transformer-based Neural Networks
Bibliographic record
Abstract
The emerging hegemony of digital information in the decision-making of financial information has changed the way investors are deciphering the signals in the market. In the world where gigantic quantities of text are produced daily with the help of social media, the news, and economic reports, it is important to understand the emotion that is held within such text and foresee the action of the market. The present research is dedicated to the financial market trend prediction on the basis of text sentiment analysis, the way in which the tone of emotion and opinion of the textual data can be linked to stock market changes. This study uses high-end transformer-based models like FinBERT and FinSentGPT to extract and measure the sentiment of various sources of text. The research questions will be addressed in the study: (1) How do the sentiments of varied text sources impact the trend in financial markets? (2) Is the addition of textual sentiment to quantitative indicators a better way of predicting the market? Due to multi-source data collection, preprocessing, and hybrid predictive modeling, it is shown that sentiment positively supports market prediction. It is concluded that the sentiment of text offers important information about investor psychology, which can be used to make more accurate and explainable financial forecasting models.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".