Filtreler

2022 - 20252
Filtreleri Sıfırla

Ayarlar

Konu: Education computing ×

Arama Sonuçları

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Yayın
    A proposal for a computational design and ecology based approach to architectural design studio
    (Springer, 2022-03) Karadağ, Derya; Tüker, Çetin
    Using computational design methods, this study aims to analyze the effects of an integrated design process model on the ecological awareness of architectural students, and on their ability to incorporate ecological issues in their design work. To this end, two studies have been carried out. The first one involves a survey about how ecology-related and computational design courses complement the architectural design studio at different universities in Turkey. The second one, which is the main study of this paper, presents the results of an ecology-based computational design workshop. According to the results of the first study, computer-based design courses in Turkey usually lack the dimension of “computational thinking”, focusing only on computer-aided design tools. Moreover, we have also found out that ecology courses in Turkish architectural education are mostly elective, and hence, have only very indirect connection to the architectural design studio. In the second study, we have demonstrated how incorporating computational thinking into the design process increase students’ awareness of the ecological dimension and their ability to make this dimension an integral part of their projects. The paper concludes by elaborating on the importance of computational methods in architectural education.
  • Küçük Resim
    Yayın
    Comparing pre-trained and fine-tuned transformer-based models for sentiment analysis in Turkish comments in student surveys
    (Institute of Electrical and Electronics Engineers Inc., 2025-08-15) Pourjalil, Kajal; Ekin, Emine; Recal, Füsun
    Student surveys are essential for evaluating teaching quality and course content, but analyzing open-ended responses is challenging due to their unstructured and multilingual nature. This study applies sentiment analysis to Turkish educational survey responses using three transformer-based models: SAVASY, DBMDZ BERT Base Turkish Cased, and XLM-RoBERTa Base. A labeled dataset of real-world student comments was used, with sentiment labels assigned using the Gemini AI tool to facilitate model fine-tuning. Evaluation metrics included accuracy, F1-score, precision, recall, and confidence scores. Results show that fine-tuning improves sentiment classification, effectively identifying positive, negative, and neutral sentiments. This highlights the value of transformer models in analyzing Turkish student feedback.