A5041253633- Topic Modeling
- Natural Language Processing Techniques
- Computational and Text Analysis Methods
- Hate Speech and Cyberbullying Detection
- Sentiment Analysis and Opinion Mining
- Social Media and Politics
- Advanced Text Analysis Techniques
- Complex Network Analysis Techniques
- Olfactory and Sensory Function Studies
- Misinformation and Its Impacts
- Public Relations and Crisis Communication
- Terrorism, Counterterrorism, and Political Violence
- Text Readability and Simplification
- Software Engineering Research
- Turkey's Politics and Society
- Advanced Chemical Sensor Technologies
- Data Quality and Management
- Political Conflict and Governance
- Time Series Analysis and Forecasting
- Data Visualization and Analytics
- Opinion Dynamics and Social Influence
- Authorship Attribution and Profiling
- Media, Religion, Digital Communication
- Data-Driven Disease Surveillance
- Linguistics and Cultural Studies
Koç University
2018-2024
Royal Netherlands Academy of Arts and Sciences
2023-2024
Radboud University Nijmegen
2013-2023
Innovation Cluster (Canada)
2022
Joint Research Centre
2012-2021
University of Essex
2021
Polish Academy of Sciences
2021
Sabancı Üniversitesi
2021
University of Sheffield
2021
Ambedkar University Delhi
2021
Despite the importance of understanding causality, corpora addressing causal relations are limited. There is a discrepancy between existing annotation guidelines event causality and conventional that focus more on linguistics. Many restrict themselves to include only explicit or clause-based arguments. Therefore, we propose an schema for addresses these concerns. We annotated 3,559 sentences from protest news with labels whether it contains not. Our corpus known as Causal News Corpus (CNC)....
Ali Hürriyetoğlu, Osman Mutlu, Erdem Yörük, Farhana Ferdousi Liza, Ritesh Kumar, Shyam Ratan. Proceedings of the 4th Workshop on Challenges and Applications Automated Extraction Socio-political Events from Text (CASE 2021). 2021.
Abstract We describe a gold standard corpus of protest events that comprise various local and international English language sources from countries. The contains document-, sentence-, token-level annotations. This facilitates creating machine learning models automatically classify news articles extract event-related information, constructing knowledge bases enable comparative social political science studies. For each source, the annotation starts with random samples continues drawn using...
Fiona Anting Tan, Hansi Hettiarachchi, Ali Hürriyetoğlu, Tommaso Caselli, Onur Uca, Farhana Ferdousi Liza, Nelleke Oostdijk. Proceedings of the 5th Workshop on Challenges and Applications Automated Extraction Socio-political Events from Text (CASE). 2022.
Ali Hürriyetoğlu, Hristo Tanev, Vanni Zavarella, Reyyan Yeniterzi, Osman Mutlu, Erdem Yörük. Proceedings of the 5th Workshop on Challenges and Applications Automated Extraction Socio-political Events from Text (CASE). 2022.
We describe our effort on automated extraction of socio-political events from news in the scope a workshop and shared task we organized at Language Resources Evaluation Conference (LREC 2020). believe event studies computational linguistics social political sciences should further support each other order to enable large scale information collection across sources, countries, languages. The consists regular research papers task, which is about sentence coreference identification (ESCI),...
Ali Hürriyetoğlu, Hristo Tanev, Vanni Zavarella, Jakub Piskorski, Reyyan Yeniterzi, Osman Mutlu, Deniz Yuret, Aline Villavicencio. Proceedings of the 4th Workshop on Challenges and Applications Automated Extraction Socio-political Events from Text (CASE 2021). 2021.
Ali Hürriyetoğlu, Osman Mutlu, Fırat Duruşan, Onur Uca, Alaeddin Gürel, Benjamin J. Radford, Yaoyao Dai, Hansi Hettiarachchi, Niklas Stoehr, Tadashi Nomoto, Milena Slavcheva, Francielle Vargas, Aaqib Javid, Fatih Beyhan, Erdem Yörük. Proceedings of the 5th Workshop on Challenges and Applications Automated Extraction Socio-political Events from Text (CASE). 2022.
Twitter is a social network, which contains information of the city events (concerts, festival, etc.), problems (traffic, collision, and road incident), news, feelings people, etc. For these reasons, there are many studies, use tweet data to detect useful support smart management. In this paper, ways finding citizen with their locations by using discussed. Tweets in Turkish language from Aegean Region Turkey were used for study. It aimed form system, detects citizens extracts problems' exact...
This paper tests the validity of a digital trace database (Politus) obtained from Twitter, with recently conducted representative social survey, focusing on use case religiosity in Turkey. Religiosity scores research are extracted using supervised machine learning under Politus project. The validation analysis depends two steps. First, we compare performances alternative tweet-to-user transformation strategies, and second, test for impact resampling via MRP technique. Estimates examined at...
Salvatore Giorgi, Vanni Zavarella, Hristo Tanev, Nicolas Stefanovitch, Sy Hwang, Hansi Hettiarachchi, Tharindu Ranasinghe, Vivek Kalyan, Paul Tan, Shaun Martin Andrews, Tiancheng Hu, Niklas Stoehr, Francesco Ignazio Re, Daniel Vegh, Dennis Atzenhofer, Brenda Curtis, Ali Hürriyetoğlu. Proceedings of the 4th Workshop on Challenges and Applications Automated Extraction Socio-political Events from Text (CASE 2021). 2021.
Using artificial intelligence, this article explores the intricate dynamics between ideologies, emotions, and political preferences of electorate in Turkey. Utilizing a dataset one billion posts from X (formerly Twitter), study maps out opinions, focusing on support for presidential candidates, ideological stances, collective emotions around pivotal 2023 Turkish elections. We discuss limitations conventional survey techniques introduce an ERC‐funded Politus project that processes digital...
What is the most optimal way of creating a gold standard corpus for training machine learning system that designed automatically collecting protest information in cross-country context? We show and testing models on basis randomly chosen news articles from archives yields better performance than selecting keyword filtering, which prevalent method currently used automated event coding. advance this new bottom-up approach to ensure generalizability reliability comparative collection...
Stefano Menini, Teresa Paccosi, Sara Tonelli, Marieke Van Erp, Inger Leemans, Pasquale Lisena, Raphael Troncy, William Tullett, Ali Hürriyetoğlu, Ger Dijkstra, Femke Gordijn, Elias Jürgens, Josephine Koopman, Aron Ouwerkerk, Sanne Steen, Inna Novalija, Janez Brank, Dunja Mladenic, Anja Zidar. Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change. 2022.
Tommaso Caselli, Osman Mutlu, Angelo Basile, Ali Hürriyetoğlu. Proceedings of the 4th Workshop on Challenges and Applications Automated Extraction Socio-political Events from Text (CASE 2021). 2021.
This paper presents an Artificial Intelligence approach to mining context and emotions related olfactory cultural heritage narratives, particularly fairy tales. We provide overview of the role smell in literature, as well highlight importance experience from psychology linguistic perspectives. introduce a methodology for extracting smells text, demonstrate context-based visualizations implemented novel tracker tool. The evaluation is performed using collection tales Grimm Andersen. find out...