This thesis analyzes various text classification techniques in order to assess whether the knowledge of published news articles about selected companies can improve its' stock return volatility modelling and forecasting. We examine the content of the textual news releases and derive the news sentiment (po larity and strength) employing three different approaches: supervised machine learning Naive Bayes algorithm, lexicon-based as a representative of linguistic approach and hybrid Naive Bayes. In hybrid Naive Bayes we consider only the words contained in the specific lexicon rather than whole set of words from the article. For the lexicon-based approach we used independently two lexicons one with binary another with multiclass labels. The training set for the Naive Bayes was labeled by the author. When comparing the classifiers from the machine learning approach we can conclude that all of them performed similarly with a slight advantage of the hybrid Naive Bayes combined with multiclass lexicon. The resulting quantitative data in form of sentiment scores will be then incorpo rated into GARCH volatility modelling. The findings suggest that information contained in news feeds does bring an additional explanatory power to tradi tional GARCH model and is able to improve it's forecast. On the...
Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:372969 |
Date | January 2018 |
Creators | Pogodina, Ksenia |
Contributors | Šopov, Boril, Červinka, Michal |
Source Sets | Czech ETDs |
Language | English |
Detected Language | English |
Type | info:eu-repo/semantics/masterThesis |
Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.0026 seconds