High Frequency Newswire Textual Sentiment: Evidence from international stock markets during the European Financial Crisis
Bibliographic record
Abstract
Textual analysis is performed in a total of 13145 high frequency (intraday) news: 6536 news from the Dow Jones Newswires and 6609 news from the Thomson Reuters Newswires. Selected news are Euro-periphery (Portugal, Ireland, Italy, Greece, Spain) crisis-related news which contain a number of keywords in their content and their title. News pessimism as a product of textual analysis sentiment significantly and negatively affects stock returns (an increase in news pessimism is associated with lower stock prices). Media pessimism does not only affect the crisis-hit Euro-periphery countries but also European (Germany, France, Austria, Belgium, Finland, UK, Switzerland, Norway) and overseas (Brazil, Canada, US Dow Jones, US S&P, Japan, China) stock markets. Stock markets can be very fast when "absorbing" the shocks of media pessimism. Even small time frames such as 30-minutes can be enough for stock prices to be negatively affected by a higher media pessimism. The results are significant in the sense that they provide quantitative evidence that individual countries in crisis can indeed affect not only their own stock markets, not only markets close to them, but also overseas markets from both sides of the globe. The media (and especially newswires which release news with extreme speeds and coverage) provide a channel through which "bad" news are instantaneously circulated and provide worldwide "shocks" to stock prices in extremely small time windows (even 30 minutes). If one takes into account the number of news examined (13145), small shocks can ultimately add up to pretty significant losses for all parties involved (individual investors, funds, corporations, nations). Stock market shocks from Athens, Lisbon, Madrid, Dublin and Rome are "felt" quite fast not only in Berlin, Paris, Vienna, London and Zurich, but also in New York, Toronto, Tokyo and Hong Kong.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.004 | 0.004 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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".