From headlines to stock trends: Natural language processing and explainable artificial intelligence approach to predicting Turkey's financial pulse

dc.authorid0000-0001-8450-7551
dc.authorid0000-0002-5131-577X
dc.authorid0000-0002-0685-7641
dc.contributor.authorIbrahim, Mahat Maalim
dc.contributor.authorKhan, Asad ul Islam
dc.contributor.authorKaplan, Muhittin
dc.contributor.otherYönetim Bilimleri Fakültesi, İktisat Bölümü
dc.date.accessioned2025-07-30T06:25:30Z
dc.date.issued2025
dc.departmentİHÜ, Yönetim Bilimleri Fakültesi, İktisat Bölümü
dc.departmentİHÜ, Lisansüstü Eğitim Enstitüsü, İktisat Ana Bilim Dalı
dc.description.abstractThe dynamic field of financial markets is constantly in search of new ways to understand complex market dynamics. The increasing availability of vast amounts of text data offers new avenues for investigation (Botchway et al., 2020). This study aims to shed light on the dynamics between stock market movements and news narratives in Turkey. To address this issue, the study will include the analysis of business, financial, and economic news from four major news journals (The Economist, The New York Times, The Guardian, and Yeni Şafak) along with local tweets. Yeni Şafak and local tweets serve as proxies for local news sentiment. The analysis rests on daily Turkish stock market data from January 1, 2015, to February 27, 2024, obtained from Yahoo Finance. The issue was addressed using state-of-the-art Natural Language Processing (NLP), machine learning, and explainable AI techniques. The findings reveal that international news significantly predicts the Turkish Stock market, with the majority of machine learning models yielding approximately 80 percent predictive accuracy. The Explainable AI methods demonstrate that traditional international news media have a significant impact on the Turkish stock market in comparison to local news sources such as Yeni Şafak and Twitter which serve as less effective predictors. Notably, the ensemble algorithms, comprising Random Forest, Gradient Boosting, and XGBoost, demonstrate robust performance across all datasets.
dc.identifier.citationIbrahim, M. M., Khan, A. I. & Kaplan, M. (2025). From headlines to stock trends: Natural language processing and explainable artificial intelligence approach to predicting Turkey's financial pulse. Borsa Istanbul Review, 1-14. https://www.doi.org/10.1016/j.bir.2025.06.013
dc.identifier.doi10.1016/j.bir.2025.06.013
dc.identifier.endpage14
dc.identifier.issn2214-8450
dc.identifier.scopus2-s2.0-105009927038
dc.identifier.scopusqualityQ1
dc.identifier.startpage1
dc.identifier.urihttps://www.doi.org/10.1016/j.bir.2025.06.013
dc.identifier.urihttp://hdl.handle.net/20.500.12154/3428
dc.indekslendigikaynakScopus
dc.institutionauthorIbrahim, Mahat Maalim
dc.institutionauthorKhan, Asad ul Islam
dc.institutionauthorKaplan, Muhittin
dc.institutionauthorid0000-0001-8450-7551
dc.institutionauthorid0000-0002-5131-577X
dc.institutionauthorid0000-0002-0685-7641
dc.language.isoen
dc.publisherBorsa Istanbul Anonim Şirketi
dc.relation.ispartofBorsa Istanbul Review
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - İdari Personel
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Öğrenci
dc.relation.publicationcategoryÖğrenci
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.relation.sdgGoal-08: Decent Work and Economic Growth
dc.relation.sdgGoal-09: Industry, Innovation and Infrastructure
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectExplainable AI
dc.subjectMachine Learning
dc.subjectNatural Language Processing
dc.subjectSentiment Analysis
dc.subjectStock Market
dc.subjectTransformers
dc.titleFrom headlines to stock trends: Natural language processing and explainable artificial intelligence approach to predicting Turkey's financial pulse
dc.typeArticle
dspace.entity.typePublication
relation.isAuthorOfPublication5d56d061-267c-4b33-8b78-b50e651ee5aa
relation.isAuthorOfPublication04e6333a-2ec2-4c28-a02b-c49e3f178e90
relation.isAuthorOfPublication.latestForDiscovery5d56d061-267c-4b33-8b78-b50e651ee5aa
relation.isOrgUnitOfPublication9d1809d1-3541-41aa-94ed-639736b7e16f
relation.isOrgUnitOfPublication.latestForDiscovery9d1809d1-3541-41aa-94ed-639736b7e16f

Dosyalar

Orijinal paket

Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
ibrahim-khan-kaplan.pdf
Boyut:
6.19 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text

Lisans paketi

Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: