Enhancing Financial Market Analysis and Prediction with Emotion Corpora and News Co-Occurrence Network
Bibliographic record
Abstract
This study employs an improved natural language processing algorithm to analyze over 500,000 financial news articles from sixteen major sources across 12 sectors, with the top 10 companies in each sector. The analysis identifies shifting economic activity based on emotional news sentiment and develops a news co-occurrence network to show relationships between companies even across sectors. This study created an improved corpus and algorithm to identify emotions in financial news. The improved method identified 18 additional emotions beyond what was previously analyzed. The researchers labeled financial terms from Investopedia to validate the categorization performance of the new method. Using the improved algorithm, we analyzed how emotions in financial news relate to market movement of pairs of companies. We found a moderate correlation (above 60%) between emotion sentiment and market movement. To validate this finding, we further checked the correlation coefficients between sentiment alone, and found that consumer discretionary, consumer staples, financials, industrials, and technology sectors showed similar trends. Our findings suggest that emotional sentiment analysis provide valuable insights for financial market analysis and prediction. The technical analysis framework developed in this study can be integrated into a larger investment strategy, enabling organizations to identify potential opportunities and develop informed strategies. The insights derived from the co-occurrence model may be leveraged by companies to strengthen their risk management functions, making it an asset within a comprehensive investment strategy.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".