| dc.identifier.uri | http://hdl.handle.net/11401/77399 | |
| dc.description.sponsorship | This work is sponsored by the Stony Brook University Graduate School in compliance with the requirements for completion of degree. | en_US |
| dc.format | Monograph | |
| dc.format.medium | Electronic Resource | en_US |
| dc.language.iso | en_US | |
| dc.publisher | The Graduate School, Stony Brook University: Stony Brook, NY. | |
| dc.type | Dissertation | |
| dcterms.abstract | To appropriately use the information from social media for finance-related problems is typically challenging to both finance and data mining. Traditional schemes in finance focus on identifying the trading activities and financial events that generate asset abnormal returns, while the usage of data typically only covers regular events such as earning announcements, financial statements, and new stock issuance. Related data-driven implementations mainly focus on developing trading strategies using social media data, while the results usually lack theoretical explanations. This work is designed to fill the gap between the usage of social media data and financial theories, with comprehensive evaluations using real-world data from social media and the stock market. A Degree of Social Attention (DSA) framework is developed based on a newly proposed influence propagation model, by leveraging on the vast social networks data, to bring profound impacts on research and practice in finance including market efficiency analysis. For each stock, the framework dynamically generates a DSA measurement that would accurately reflect the price shock. Specially, the topological structure of a social network is able to be modeled as well as the self-influence of each social media user. Furthermore, the market influence of the current DSA as well as the effects of historical ones on different stocks are estimated. The essential relationship is verified between social media activities and the stock market movement by testing the semi-strong-form efficient market hypotheses. And then it is confirmed that the effectiveness of our framework in the implementation of stock shock ranking. The results suggest that considering historical DSAs improve the model’s performance of fitting abnormal returns in terms of the statistical significance as well as the ranking accuracy. I also develop a new method to estimate social attention of stocks with sentiment analysis and the results show that the newly proposed measurement of social attention would significantly improve the forecasting power of our framework. | |
| dcterms.abstract | To appropriately use the information from social media for finance-related problems is typically challenging to both finance and data mining. Traditional schemes in finance focus on identifying the trading activities and financial events that generate asset abnormal returns, while the usage of data typically only covers regular events such as earning announcements, financial statements, and new stock issuance. Related data-driven implementations mainly focus on developing trading strategies using social media data, while the results usually lack theoretical explanations. This work is designed to fill the gap between the usage of social media data and financial theories, with comprehensive evaluations using real-world data from social media and the stock market. A Degree of Social Attention (DSA) framework is developed based on a newly proposed influence propagation model, by leveraging on the vast social networks data, to bring profound impacts on research and practice in finance including market efficiency analysis. For each stock, the framework dynamically generates a DSA measurement that would accurately reflect the price shock. Specially, the topological structure of a social network is able to be modeled as well as the self-influence of each social media user. Furthermore, the market influence of the current DSA as well as the effects of historical ones on different stocks are estimated. The essential relationship is verified between social media activities and the stock market movement by testing the semi-strong-form efficient market hypotheses. And then it is confirmed that the effectiveness of our framework in the implementation of stock shock ranking. The results suggest that considering historical DSAs improve the model’s performance of fitting abnormal returns in terms of the statistical significance as well as the ranking accuracy. I also develop a new method to estimate social attention of stocks with sentiment analysis and the results show that the newly proposed measurement of social attention would significantly improve the forecasting power of our framework. | |
| dcterms.available | 2017-09-20T16:52:37Z | |
| dcterms.contributor | Xing, Haipeng | en_US |
| dcterms.contributor | Deng, Yuefan | en_US |
| dcterms.contributor | Xiao, Keli. | en_US |
| dcterms.contributor | Rachev, Svetlozar | en_US |
| dcterms.creator | Zhang, Li | |
| dcterms.dateAccepted | 2017-09-20T16:52:37Z | |
| dcterms.dateSubmitted | 2017-09-20T16:52:37Z | |
| dcterms.description | Department of Applied Mathematics and Statistics | en_US |
| dcterms.extent | 117 pg. | en_US |
| dcterms.format | Application/PDF | en_US |
| dcterms.format | Monograph | |
| dcterms.identifier | http://hdl.handle.net/11401/77399 | |
| dcterms.issued | 2016-12-01 | |
| dcterms.language | en_US | |
| dcterms.provenance | Made available in DSpace on 2017-09-20T16:52:37Z (GMT). No. of bitstreams: 1
Zhang_grad.sunysb_0771E_12794.pdf: 1911563 bytes, checksum: 4415313c42cc8c9cb5699d8911cee286 (MD5)
Previous issue date: 1 | en |
| dcterms.publisher | The Graduate School, Stony Brook University: Stony Brook, NY. | |
| dcterms.subject | Finance -- Economic theory -- Mathematics | |
| dcterms.title | Influence Propagation Modeling and Applications in Finance | |
| dcterms.type | Dissertation | |
