İsmail Hakkı Toroslu

E-mail

toroslu@metu.edu.tr

Department

Department of Computer Engineering

ORCID

0000-0002-4524-8232

Scopus Author ID

6603451626

Web of Science Researcher ID

Q-5390-2019

Neighborhood search with heuristic-based feature selection for click-through rate prediction Aksu, Dogukan; Toroslu, İsmail Hakkı; Davulcu, Hasan (2025-04-15) Click-through-rate (CTR) prediction is crucial in online advertising and recommender systems. Maximizing CTR has been a major focus, leading to the development of numerous models designed to capture implicit and explicit f...
Efficient Parallel Algorithm for Approximating Betweenness Centrality Values of Top k Nodes in Large Graphs Toroslu, İsmail Hakkı; Suleymanli, Gadir (2025-02-28) Computing betweenness centrality (BC) in large graphs is crucial for various applications, including telecommunications, social, and biological networks. However, the huge size of the data presents significant challenges. ...
DocSpider: a dataset of cross-domain natural language querying for MongoDB Özer, Arif Görkem; Çekinel, Recep Fırat; Toroslu, İsmail Hakkı; Karagöz, Pınar (2025-02-12) Natural language querying allows users to formulate questions in a natural language without requiring specific knowledge of the database query language. Large language models have been very successful in addressing the tex...
Leveraging In-Context Learning to Transfer Cross-Domain Knowledge in Click-Through Rate Prediction Baglam I i grenme Kullanilarak Tiklama Orani Tahminlerine apraz Alan Bilgilerinin Aktarilmasi Aydogdu, Mehmet Erdeniz; Sengor Altingovde, Ismail; Karagöz, Pınar; Toroslu, İsmail Hakkı (2025-01-01) With the development of large language models, natural language tasks have seen significant improvements, including personalized recommendation. Traditional approaches in recommendation are often based on collaborative fil...
Improving Cross-Domain Recommendation Methods with Factorization Machine Integration C apraz Alan O neri Yo ntemlerinin Fakto rizasyon Makinesi Entegrasyonu ile Iyiles tirilmesi Colak, Ahmet Eren; Sengor Altingovde, Ismail; Karagöz, Pınar; Toroslu, İsmail Hakkı (2025-01-01) Cross-domain recommender systems aim to im- prove recommendations in the target domain by exploiting the source domain where abundant data is present. In this study, we investigate the combination of a shallow model, the f...
Enhancing Virtual Environments: Hybrid Approach to Neural Style Transfer BAHTİYAR, HÜSEYİN; Katipoğlu, Bahadır İrfan; Yüksel, Eda; Toroslu, İsmail Hakkı; Karagöz, Pınar (2024-07-01)
Targeted marketing on social media: utilizing text analysis to create personalized landing pages Çetinkaya, Yusuf Mucahit; Külah, Emre; Toroslu, İsmail Hakkı; Davulcu, Hasan (2024-04-01) The widespread use of social media has rendered it a critical arena for online marketing strategies. To optimize conversion rates, the landing pages must effectively respond to a visitor segment’s pain points that they nee...
Towards a Programmable Humanizing AI through Scalable Stance-Directed Architecture Çetinkaya, Yusuf Mucahit; Lee, Yeonjung; Külah, Emre; Toroslu, İsmail Hakkı; Cowan, Michael A.; Davulcu, Hasan (2024-01-01) The rise of harmful online content underscores the urgent need for AI systems to effectively detect, filter those, and foster safer and healthier communication. This article introduces a novel approach to mitigate toxic co...
A Comparative Study of Contemporary Learning Paradigms in Bug Report Priority Detection Yilmaz, Eyup Halit; Toroslu, İsmail Hakkı; Koksal, Omer (2024-01-01) The increasing complexity of software development demands efficient automated bug report priority classification, and recent advancements in deep learning hold promise. This paper presents a comparative study of contempora...
Traffic signal optimization using multiobjective linear programming for oversaturated traffic conditions Coşkun, Mustafa Murat; Şener, Cevat; Toroslu, İsmail Hakkı (2024-01-01) In this study, we present a framework designed to optimize signals at intersections experiencing oversaturated traffic conditions, utilizing mixed-integer linear programming (MILP) techniques. The proposed MILP solutions w...

Citation Formats