Show simple item record

dc.contributor.authorRossouw, Sen_NZ
dc.contributor.authorGreyling, Ten_NZ
dc.contributor.authorSteyn, Den_NZ
dc.date.accessioned2020-07-13T23:23:46Z
dc.date.available2020-07-13T23:23:46Z
dc.date.copyright2020-04-02en_NZ
dc.identifier.citationGLO Discussion Paper, No. 502, Global Labor Organization (GLO), Essen
dc.identifier.urihttp://hdl.handle.net/10292/13524
dc.description.abstractThis paper investigates the predictability of stock market movements using text data extracted from the social media platform, Twitter. We analyse text data to determine the sentiment and the emotion embedded in the Tweets and use them as explanatory variables to predict stock market movements. The study contributes to the literature by analysing high-frequency data and comparing the results obtained from analysing emerging and developed markets, respectively. To this end, the study uses three different Machine Learning Classification Algorithms, the Naïve Bayes, K-Nearest Neighbours and the Support Vector Machine algorithm. Furthermore, we use several evaluation metrics such as the Precision, Recall, Specificity and the F-1 score to test and compare the performance of these algorithms. Lastly, we use the K-Fold Cross-Validation technique to validate the results of our machine learning models and the Variable Importance Analysis to show which variables play an important role in the prediction of our models. The predictability of the market movements is estimated by first including sentiment only and then sentiment with emotions. Our results indicate that investor sentiment and emotions derived from stock market-related Tweets are significant predictors of stock market movements, not only in developed markets but also in emerging markets.
dc.publisherGlobal Labor Organizationen_NZ
dc.relation.urihttps://www.econstor.eu/handle/10419/215436en_NZ
dc.rightsEconStor supports Green Open Access. All papers on EconStor are made freely available without restrictions or embargo periods. Publication on EconStor is based on usage agreements with authors or the editors/publishers of a series or journal. Authors' copyrights are safeguarded. Publication on EconStor does not inhibit further publication of the documents in journals or on other document servers. Disseminating publications with EconStor is free for publishers and authors (FAQ).
dc.subjectSentiment Analysis; Classification; Stock Prediction; Machine Learning
dc.titleSentiment, Emotions and Stock Market Predictability in Developed and Emerging Marketsen_NZ
dc.typeDiscussion Paper
dc.rights.accessrightsOpenAccessen_NZ
aut.relation.softwareversion502en_NZ
pubs.elements-id383462


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record