More than just sentiment: Using social, cognitive, and behavioral information of social media to predict stock markets with artificial intelligence and big data
Digital transformation offers unprecedented opportunities to access data on hard-to-measure social aspects. In this digital era, social media platforms have become critical data sources for the social sciences. This study moves beyond traditional finance assumptions of “perfect information,” “ration...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Borsa Istanbul Review |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214845024001571 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591803238318080 |
|---|---|
| author | Yunus Emre Akdogan Adem Anbar |
| author_facet | Yunus Emre Akdogan Adem Anbar |
| author_sort | Yunus Emre Akdogan |
| collection | DOAJ |
| description | Digital transformation offers unprecedented opportunities to access data on hard-to-measure social aspects. In this digital era, social media platforms have become critical data sources for the social sciences. This study moves beyond traditional finance assumptions of “perfect information,” “rational humans,” and “isolated individuals” by analyzing retail investor behavior using Twitter data. It adopts a human model characterized by incomplete information, bounded rationality, and the influence of social and emotional factors. Tweets shared between January 1, 2012, and February 28, 2020, were collected. A GRU-based context classifier achieved 98% accuracy in identifying tweets related to Borsa Istanbul (BIST). Sentiment classification using a BERT model achieved 91% accuracy for positive and negative classes. Relationships between Twitter-obtained features and BIST indices were analyzed using machine learning methods such as linear regression, Lasso regression, random forest, and XGBoost. The analysis revealed that 91% of the change in the opening value, 63% of the change in trading volume, and 67% in volatility of the BIST 100 index could be attributed to cognitive, behavioral, and social features gleaned from tweets. |
| format | Article |
| id | doaj-art-deeff83961fc4c49932883f760c90211 |
| institution | Kabale University |
| issn | 2214-8450 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Borsa Istanbul Review |
| spelling | doaj-art-deeff83961fc4c49932883f760c902112025-01-22T05:42:32ZengElsevierBorsa Istanbul Review2214-84502024-12-01246182More than just sentiment: Using social, cognitive, and behavioral information of social media to predict stock markets with artificial intelligence and big dataYunus Emre Akdogan0Adem Anbar1Yozgat Bozok University, Faculty of Economics and Administrative Sciences, Department of Business Administration, Türkiye; Corresponding author.Bursa Uludag University, Faculty of Economics and Administrative Sciences, Department of Business Administration, TürkiyeDigital transformation offers unprecedented opportunities to access data on hard-to-measure social aspects. In this digital era, social media platforms have become critical data sources for the social sciences. This study moves beyond traditional finance assumptions of “perfect information,” “rational humans,” and “isolated individuals” by analyzing retail investor behavior using Twitter data. It adopts a human model characterized by incomplete information, bounded rationality, and the influence of social and emotional factors. Tweets shared between January 1, 2012, and February 28, 2020, were collected. A GRU-based context classifier achieved 98% accuracy in identifying tweets related to Borsa Istanbul (BIST). Sentiment classification using a BERT model achieved 91% accuracy for positive and negative classes. Relationships between Twitter-obtained features and BIST indices were analyzed using machine learning methods such as linear regression, Lasso regression, random forest, and XGBoost. The analysis revealed that 91% of the change in the opening value, 63% of the change in trading volume, and 67% in volatility of the BIST 100 index could be attributed to cognitive, behavioral, and social features gleaned from tweets.http://www.sciencedirect.com/science/article/pii/S2214845024001571G41G17G14G11 |
| spellingShingle | Yunus Emre Akdogan Adem Anbar More than just sentiment: Using social, cognitive, and behavioral information of social media to predict stock markets with artificial intelligence and big data Borsa Istanbul Review G41 G17 G14 G11 |
| title | More than just sentiment: Using social, cognitive, and behavioral information of social media to predict stock markets with artificial intelligence and big data |
| title_full | More than just sentiment: Using social, cognitive, and behavioral information of social media to predict stock markets with artificial intelligence and big data |
| title_fullStr | More than just sentiment: Using social, cognitive, and behavioral information of social media to predict stock markets with artificial intelligence and big data |
| title_full_unstemmed | More than just sentiment: Using social, cognitive, and behavioral information of social media to predict stock markets with artificial intelligence and big data |
| title_short | More than just sentiment: Using social, cognitive, and behavioral information of social media to predict stock markets with artificial intelligence and big data |
| title_sort | more than just sentiment using social cognitive and behavioral information of social media to predict stock markets with artificial intelligence and big data |
| topic | G41 G17 G14 G11 |
| url | http://www.sciencedirect.com/science/article/pii/S2214845024001571 |
| work_keys_str_mv | AT yunusemreakdogan morethanjustsentimentusingsocialcognitiveandbehavioralinformationofsocialmediatopredictstockmarketswithartificialintelligenceandbigdata AT ademanbar morethanjustsentimentusingsocialcognitiveandbehavioralinformationofsocialmediatopredictstockmarketswithartificialintelligenceandbigdata |