Hiding in Plain Sight : Sentiment Analysis and the Efficient Market Hypothesis
Bibliographic record
Abstract
The stock market is a notoriously complex and unpredictable system, and because of this has always been an alluring subject for academic research seeking to make the unpredictable more predictable. This major research project is no different as it aims to quantify the predictive value of financial sentiment, determine which sentiments are most meaningful, when they are most meaningful, and if meaningful sentiment varies depending on type of stock. To pursue these goals, the project finds its theoretical footing in Eugene Fama’s Efficient Market Hypothesis and Daniel Kahneman’s Prospect Theory. However, the methodological component of this project enters into emerging territory as it employs sentiment analysis and machine learning, which have only recently been made possible by advances in technology and communications practices. Specifically, through the use of the Loughran-McDonald dictionary for financial sentiment, corporate press releases were analyzed and tested using a Random Forest machine learning model. The results from this project show that financial senitiment found in press releases does provide a slight predictive edge, however the sentiments responsible for that edge vary based on type of stock, type of fluctuation being predicted, and timeframe.
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 | 0.004 | 0.021 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".