Ege Demirci

I am a first year PhD student in Computer Science at the University of California, Santa Barbara, conducting research in the DYNAMO Lab under the supervision of Dr. Ambuj Singh. My work mainly focuses on machine learning on graph-structured data, with the goal of developing advanced techniques for predicting network structure and flows, critical to planning and optimizing infrastructure systems.

I graduated as valedictorian in June 2024 from Sabanci University with a B.Sc. in Computer Science and Engineering. For three years, I worked as a research assistant at VRL Lab, where we investigated human behaviors and societal patterns by integrating both online and offline data, under the supervision of Dr. Onur Varol.

During my time at Sabanci University, my research primarily focused on exploring how actors execute misinformation and propaganda campaigns to promote ideas in the politically charged environment of the 2023 Turkish elections on social media, using machine learning and network science techniques. In my final year, my work centered on habit formation, employing causal inference and machine learning techniques to investigate factors influencing the establishment of consistent exercise habits.

research interests

My research interests can be summarized with few keywords:

Machine Learning on Graphs: Developing and applying machine learning techniques to graph-structured data to gain insights into networked systems.
Network Science: Investigating the structure and dynamics of social networks, and how they influence individual and collective behavior. Studying the formation, evolution, and impact of social networks on various aspects of society.
Machine Learning for Social Good: Applying machine learning methods to address social issues and improve public well-being.
Causal Inference: Evaluating the effectiveness of interventions and understanding causality in complex systems, particularly in the context of digital media and social networks.

news

Jan 09, 2025	My first-author preprint, From Occasional to Steady: Habit Formation Insights From a Comprehensive Fitness Study, is now available on ArXiv and currently under review!
Jun 13, 2024	I’m happy to share that I graduated from Sabanci University!
Mar 25, 2024	My first paper as a co-author, titled First public dataset to study 2023 Turkish general election, has been accepted by Scientific Reports!

publications

Preprint

From Occasional to Steady: Habit Formation Insights From a Comprehensive Fitness Study

Ege Demirci, Efe Tüzün, Ahmet Furkan Un, Taner Giray Sonmez, and Onur Varol

Under review, Jan 2025

Abs PDF

Exercising regularly is widely recognized as a cornerstone of health, yet the challenge of sustaining consistent exercise habits persists. Understanding the factors that influence the formation of these habits is crucial for developing effective interventions. This study utilizes data from Mars Athletic Club, Türkiye’s largest sports chain, to investigate the dynamics of gym attendance and habit formation. The general problem addressed by this study is identifying the critical periods and factors that contribute to the successful establishment of consistent exercise routines among gym-goers. Here we show that there are specific periods during which gym attendance is most crucial for habit formation. By developing a survival metric based on gym attendance patterns, we pinpoint these critical periods and segment members into distinct clusters based on their visit patterns. Our analysis reveals significant differences in how various subgroups respond to interventions, such as group classes, personal trainer sessions, and visiting different clubs. Using causal inference analysis, we demonstrate that personalized guidance and social dynamics are key drivers of sustained long-term engagement. By systematically examining these variables and considering the specific characteristics of different clusters, our research demonstrates the importance of a tailored, multi-dimensional approach to promoting exercise habits, which integrates social dynamics, personalized guidance, and strategic interventions to sustain long-term engagement.
Scientific Reports

First public dataset to study 2023 Turkish general election

Ali Najafi, Nihat Mugurtay, Yasser Zouzou, Ege Demirci, Serhat Demirkiran, Huseyin Alper Karadeniz, and Onur Varol

Scientific Reports, Mar 2024

Abs PDF

In the context of Turkiye’s most recent parliamentary and presidential elections (“seçim” in Turkish), social media has played an important role in shaping public debate. It is of utmost importance to capture social media trends during the 2023 Turkish elections, since it uncovers a great deal of information of election propaganda, political debates, smear campaigns, and election manipulation by domestic and international actors. We provide a comprehensive dataset for social media researchers to study Turkish elections, develop tools to prevent online manipulation, and gather novel information to inform the public. We are committed to continually improving the data collection and updating it regularly leading up to the election. Using the #Secim2023 dataset, researchers can examine the social and communication networks between political actors, track current trends, and investigate emerging threats to election integrity. Our dataset and analysis code available through Harvard Dataverse and Github, respectively.