2 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 2 / 2
Yayın Learning to rank(Işık Üniversitesi, 2011-04-28) Kılıç, Yasin Ozan; Yıldız, Olcay Taner; Işık Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans ProgramıThe web has grown so rapidly in the last decade and it brought the need for proper ranking. Learning to rank (LTR) is the collection of machine learning technolo- gies that construct a ranking model using training data. The model can sort documents according to their degrees of relevance or preference. In this thesis, we introduce LTR technologies and divide them into three ap- proaches: the point-wise, pair-wise and list-wise. We review the theoritical aspects of each category and introduce the representative algorithms of them. We also introduce a new LTR method GRwC which uses classifîcation and graph algorithms. We reduce the ranking problem to a two class classifîcation problem and apply KNN algorithm on a modified LTR dataset. We compared it with the popular ranking algorithm RankingSVM. Experiments on the well-known ranking datasets show that our proposed method gives slightly worse results than RankingSVM.Yayın Disinformation, social media, and populism : emotional politics and polarization dynamics in Turkey’s 2023 presidential elections(Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü, 2024-07-01) Avcı Çeken, İnci Secem; Kayhan Pusane, Özlem; Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Uluslararası İlişkiler Yüksek Lisans Programı; Işık University, School of Graduate Studies, Master’s Program in International RelationsThis thesis explores the relationship between populist discourse and social media algorithms, examining their role in exacerbating political polarization. Its primary aim is to identify the correlation between the use of populist rhetoric and the algorithms driving social media engagement, highlighting how this relationship fosters societal divisions and benefits both platforms and political entities. Using critical discourse analysis (CDA), the thesis analyzes X (formerly Twitter) posts shared by 2023 Turkish presidential election candidates Recep Tayyip Erdoğan and Kemal Kılıçdaroğlu. In the first round of the campaign, shared posts were analyzed between 06.05.2024 and 14.05.2024. A total of 173 posts, 108 by Erdoğan and 65 by Kılıçdaroğlu, were analyzed. The full texts of these posts were obtained from X's official website. The findings reveal that posts featuring emotionally charged and popülist discourse have garnered higher views and engagement in the run-up to the 2023 presidential elections. This analysis will help to understand the political polarization in Turkey. Social media algorithms shape social interaction by strengthening populist discourses. This suggests that social media algorithms, prioritizing emotionally charged content, unintentionally promote populism. The study concludes that the design of social media platforms increases divisive content, leading to a rise in populist rhetoric among political candidates and voters.
