Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
7 results
Search Results
Article Citation - WoS: 3Citation - Scopus: 4A Novel Efficient Method for Tracking Evolution of Communities in Dynamic Networks(Institute of Electrical and Electronics Engineers Inc., 2022) Karataş, Arzum; Şahin, SerapTracking community evolution can provide insights into significant changes in community interaction patterns, promote the understanding of structural changes, and predict the evolutionary behavior of networks. Therefore, it is a fundamental component of decision-making mechanisms in many fields such as marketing, public health, criminology, etc. However, in this problem domain, it is an open challenge to capture all possible events with high accuracy, memory efficiency, and reasonable execution times under a single solution. To address this gap, we propose a novel method for tracking the evolution of communities (TREC). TREC efficiently detects similar communities through a combination of Locality Sensitive Hashing and Minhashing. We provide experimental evidence on four benchmark datasets and real dynamic datasets such as AS, DBLP, Yelp, and Digg and compare them with the baseline work. The results show that TREC achieves an accuracy of about 98%, has a minimal space requirement, and is very close to the best performing work in terms of time complexity. Moreover, it can track all event types in a single solution.Conference Object A Review on Predicting Evolution of Communities(Selçuk Üniversitesi, 2021) Karataş, Arzum; Şahin, SerapIn recent years, research on dynamic networks has increased as the availability of data has grown tremendously. Understanding the dynamic behavior of networks can be studied at the mezzo-scale (e.g., at the community level), as communities are the most informative structure in nonrandom networks and also evolve over time. Tracking the evolution of communities can provide evolution patterns to predict their future development. For example, a community may either grow into a larger community, remain stable, shrink into a smaller community, split into several smaller communities, or merge with another community. Predicting these evolutions is one of the most difficult problems in social networks. Better predictions of community evolution can provide useful information for decision support systems, especially for group-level tasks. So far, this problem has been studied by some researchers. However, there is a lack of a survey/review of existing work. This has prompted us to conduct this study. In this paper, we first categorize the existing works according to their methodological principles. Then, we focus on the works that use machine learning classifiers for prediction in this decade as they are in majority. We then highlight open problems for future research. In this way, this paper provides an up-to-date overview and a quick start for researchers and developers in the field of community evolution prediction.Conference Object Edu-Voting: an Educational Homomorphic E-Voting System(Karabük Üniversitesi, 2018) Tekin, Leyla; Özgür, Hüseyin Güven; Sayin, Burcu; Karataş, Arzum; Şenkula, Pelin; İrtem, Emre; Şahin, SerapAs an instrument of democracy, voting is a critical issue. Although paper-based voting systems are still used commonly, e-voting systems have started to substitute under favor of improvements in the technology. This situation gives rise to need for secure, reliable, and transparent e-voting systems to make people trust. To do this, there are some security requirements that should be concerned and satisfied such as privacy, fairness, verifiability etc. This study has an educational intuition that analyzes those requirements, theoretical background information related to cryptographic schemes behind them and creates a place-based e-voting design which was implemented for kiosk voting. As a contribution, Paillier homomorphic cryptosystem is used in our system. Moreover, our study includes a detailed criticism for the implemented system in terms of chosen cryptosystems and design modules with security and e-voting requirements.Article Sosyal Bot Algılama Teknikleri ve Araştırma Yönleri Üzerine Bir İnceleme(Gazi Üniversitesi, 2018) Karataş, Arzum; Şahin, SerapFacebook, Twitter, LinkedIn gibi çevrimiçi sosyal ağların (OSN) popülerliği ve web servislerinin yaygınlığı, bu alanlarda sosyal bot olarak nitelendirdiğimiz yazılımsal sosyal aktörlerin ortaya çıkmasına ve yaygınlaşmasına neden oldu. Ancak çoğunlukla bu aktörler kötü rollerde karşımıza çıkmaktadırlar. Örneğin, sosyal botlar insanmış gibi sohbetlere katılma, başka hesapları çalarak üzerinden dolandırıcılık yapma, yanlış bilgi yayma, borsayı manipüle etme, sahte halk tabakası oluşturarak propaganda yapma gibi ciddi problemlerde karşımıza çıkmaktadırlar. Bununla beraber, istenmeyen postaları ve zararlı yazılımları yaymanınetkin araçları haline gelmişlerdir. Dahası, botlar gerçek hesapları ele geçirerek “zombi bilgisayar ağı” (botnet attack) saldırıları düzenlemekte de kullanılabiliyorlar. Öte yandan, sosyal botların sosyal paylaşım ağları üzerindeki yaygınlığı ve önemi inkâr edilemez bir gerçektir. Bu çalışmada, kötü niyetli sosyal botların potansiyel tehlikeleri vurgulanmıştır. Sonrasında, metodolojik bir sınıflandırma içerisinde literatürdeki bot tespit yaklaşımları, bu yaklaşımların sınırları ve açık problemleri gözden geçirilmiştir. Makalenin son bölümünde, problemi çözmeye yönelik iki yeni yaklaşım önerilmiştir.Conference Object A Comparative Analysis of Two Most Recent Dynamic Community Tracking Methods(01. Izmir Institute of Technology, 2019) Karataş, Arzum; Şahin, SerapReal world networks are intrinsically dynamic, and they are mostly represented by dynamic graphs in virtual world. Analysis of these dynamic network data can give valuable information for decision support systems in many domains in criminology, politics, health, advertising and social networks etc. Community tracking is important to analyze and understand the dynamics of the group structures and predict the near futures of communities. With a successful analysis of these data, software engineering tools and decision support systems can produce more successful results for end users. In this study, we present a comparative study of two important and recent community tracking methods in terms of accuracy, algorithmic complexity and their characteristics. We use a benchmark dataset which have ground truth community information detected each time step as a test bed.Conference Object A Review on Social Bot Detection Techniques and Research Directions(Bilgi Güvenliği Derneği, 2017) Karataş, Arzum; Şahin, SerapThe rise of web services and popularity of online social networks (OSN) like Facebook, Twitter, LinkedIn etc. have led to the rise of unwelcome social bots as automated social actors. Those actors can play many malicious roles including infiltrators of human conversations, scammers, impersonators, misinformation disseminators, stock market manipulators, astroturfers, and any content polluter (spammers, malware spreaders) and so on. It is undeniable that social bots have major importance on social networks. Therefore, this paper reveals the potential hazards of malicious social bots, reviews the detection techniques within a methodological categorization and proposes avenues for future research.Conference Object Citation - Scopus: 2A Comparative Study of Modularity-Based Community Detection Methods for Online Social Networks(CEUR Workshop Proceedings, 2018) Karataş, Arzum; Şahin, SerapDigital data represent our daily activities and tendencies. One of its main source is Online Social Networks (OSN) such as Facebook, YouTube etc. OSN are generating continuously high volume of data and define a dynamic virtual environment. This environment is mostly represented by graphs. Analysis of OSN data (i.e.,extracting any kind of relations and tendencies) defines valuable information for economic, socio-cultural and politic decisions. Community detection is important to analyze and understand underlying structure and tendencies of OSNs. When this information can be analysed successfully, software engineering tools and decision support systems can produce more successful results for end users. In this study, we present a survey of selected outstanding modularity-based static community detection algorithms and do comparative analysis among them in terms of modularity, running time and accuracy. We use different real-world OSN test beds selected from SNAP dataset collection such as Facebook Ego network, Facebook Pages network (Facebook gemsec), LiveJournal, Orkut and YouTube networks.