Textual Sentiment and Sector specific reaction
by Wolfgang Karl Härdle
Ladislaus von Bortkieviecz Chair Professor of Statistics
Humbdolt-Universität zu Berlin, Germany
ABSTRACT
News move markets and contains incremental information about stock reactions. Future trading volumes, volatility and returns are affected by sentiments of texts and opinions expressed in articles. Earlier work of sentiment distillation of stock news suggests that risk profile reactions might differ across sectors. Conventional asset pricing theory recognizes the role of a sector and its risk uniqueness that differs from market or firm specific risk.
Our research assesses whether incorporating the sentiment distilled from sector specific news carries information about risk profiles. Textual analytics applied to about 600K articles leads us with lexical projection and machine learning to classification of sentiment polarities. The texts are scraped from official NASDAQ web pages and with Natural Language Processing (NLP) techniques, such as tokenization, lemmatization, a sector specific sentiment is extracted using a lexical approach and a financial phrase bank. Predicted sentence-level polarities are aggregated into a bullishness measure on a daily basis and fed into a panel regression analysis with sector indicators. Supervised learning with hinge or logistic loss and regularization yields good prediction results of polarity. Compared with standard lexical projections, the supervised learning approach yields superior predictions of sentiment, leading to highly sector specific sentiment reactions. The Consumer Staples, Health Care and Materials sectors show strong risk profile reactions to negative polarity.
ABOUT THE SPEAKER
Professor Wolfgang Karl HÄRDLE did his Dr. rer. nat. in Mathematics at Universität Heidelberg in 1982 and his Habilitation at Universität Bonn in 1988. He is Ladislaus von Bortkieviecz chair professor of statistics, Humboldt-Universität zu Berlin. He is director of the Sino German International Research Training Group IRTG1792 „High dimensional non stationary time series analysis“ (WISE, Xiamen University).
His research focuses on dimension reduction techniques, computational statistics and quantitative finance. He has published over 30 books and more than 300 papers in top statistical, econometrics and finance journals. He is highly ranked and cited on Google Scholar, REPEC and SSRN.
He has professional experience in financial engineering, smart data analytics, machine learning and cryptocurrency markets. He has created a financial risk meter FRM hu.berlin/frm and a cryptocurrency index CRIX hu.berlin/crix. His web page is: hu.berlin/wkh
Details
| Date |
Tuesday, 12 March 2019 |
| Time |
3:30pm - 5:00pm |
| Venue |
Singapore Management University
Lee Kong Chian School of Business
Level 2, Seminar Room 2.2
50 Stamford Road, Singapore 178899
(Click here for map) (Building #2)
|
| Register |
 |
Sim Kee Boon Institute for Financial Economics
To unsubscribe from SKBI mailing list, please email skbi_enquiries [at] smu.edu.sg ().
