HDHasan Davulcu

Hasan Davulcu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hasan Davulcu has a total of 90 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Beyond the Black Box: Programmable AI and Explainable Text Analysis for Trustworthy Social Intelligence

    by Anshul Trivedi, Yusuf Mücahit Çetinkaya, Michael A. Cowan, Martha Newson, Natko Vlahović, Hasan Davulcu

    Life demands safe, reliable, and explainable artificial intelligence (AI) grounded in scientific reasoning and guided by human oversight. We present a neuro-symbolic programmable AI algorithm that transforms neural outputs into interpretable logic-patterned narratives via symbolic pattern lifting and lowering. It is designed for social scientists and enables reproducible Human + AI text analysis across sources such as social media, interviews, and news. It is demonstrated on 1.3 million tweets about global energy trends, and the system ensures AI that not only says what it does but does what it says, replacing black-box opacity with transparent, accountable reasoning.

  • Masking the Bias: From Echo Chambers to Large Scale Aspect-Based Sentiment Analysis

    by Yeonjung Lee, Yusuf Mücahit Çetinkaya, Emre Külah, Hakkı Toroslu, Hasan Davulcu


  • Open Access

    NeSHFS: Neighborhood Search with Heuristic-based Feature Selection for Click-Through Rate Prediction

    by Dogukan Aksu, Ismail Hakki Toroslu, Hasan Davulcu

    Click-through-rate (CTR) prediction plays an important role in online advertising and ad recommender systems. In the past decade, maximizing CTR has been the main focus of model development and solution creation. Therefore, researchers and practitioners have proposed various models and solutions to enhance the effectiveness of CTR prediction. Most of the existing literature focuses on capturing either implicit or explicit feature interactions. Although implicit interactions are successfully captured in some studies, explicit interactions present a challenge for achieving high CTR by extracting both low-order and high-order feature interactions. Unnecessary and irrelevant features may cause high computational time and low prediction performance. Furthermore, certain features may perform well with specific predictive models while underperforming with others. Also, feature distribution may fluctuate due to traffic variations. Most importantly, in live production environments, resources are limited, and the time for inference is just as crucial as training time. Because of all these reasons, feature selection is one of the most important factors in enhancing CTR prediction model performance. Simple filter-based feature selection algorithms do not perform well and they are not sufficient. An effective and efficient feature selection algorithm is needed to consistently filter the most useful features during live CTR prediction process. In this paper, we propose a heuristic algorithm named Neighborhood Search with Heuristic-based Feature Selection (NeSHFS) to enhance CTR prediction performance while reducing dimensionality and training time costs. We conduct comprehensive experiments on three public datasets to validate the efficiency and effectiveness of our proposed solution.

  • Toward a Programmable Humanizing Artificial Intelligence Through Scalable Stance-Directed Architecture

    by Yusuf Mücahit Çetinkaya, Yeonjung Lee, Emre Külah, İsmail Hakkı Toroslu, Michael A. Cowan, Hasan Davulcu

    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 content generation propensities of Large Language Models (LLMs) by fine-tuning them with a programmable stance-directed focus on core human values and common good. We propose a streamlined keyword coding and processing pipeline to generate weakly labeled data to train AI models that can avoid toxicity and champion civil discourse. We also developed a toxicity classifier and an Aspect-based Sentiment Analysis (ABSA) model to assess and control the effectiveness of a humanizing AI model. We evaluate the proposed pipeline using a contentious real-world Twitter dataset on U.S. race relations. Our approach successfully curbs the toxic content generation propensity of an unrestricted LLM by a significant 85%.


  • Open Access

    Quantifying Variations in Controversial Discussions within Kuwaiti Social Networks

    by Yeonjung Lee, Hana Alostad, Hasan Davulcu

    During the COVID-19 pandemic, pro-vaccine and anti-vaccine groups emerged, influencing others to vaccinate or abstain and leading to polarized debates. Due to incomplete user data and the complexity of social network interactions, understanding the dynamics of these discussions is challenging. This study aims to discover and quantify the factors driving the controversy related to vaccine stances across Kuwaiti social networks. To tackle these challenges, a graph convolutional network (GCN) and feature propagation (FP) were utilized to accurately detect users’ stances despite incomplete features, achieving an accuracy of 96%. Additionally, the random walk controversy (RWC) score was employed to quantify polarization points within the social networks. Experiments were conducted using a dataset of vaccine-related retweets and discussions from X (formerly Twitter) during the Kuwait COVID-19 vaccine rollout period. The analysis revealed high polarization periods correlating with specific vaccination rates and governmental announcements. This research provides a novel approach to accurately detecting user stances in low-resource languages like the Kuwaiti dialect without the need for costly annotations, offering valuable insights to help policymakers understand public opinion and address misinformation effectively.


  • Targeted marketing on social media: utilizing text analysis to create personalized landing pages

    by Yusuf Mücahit Çetinkaya, Emre Külah, İsmail Hakkı Toroslu, Hasan Davulcu


  • Open Access

    Q8VaxStance: Dataset Labeling System for Stance Detection towards Vaccines in Kuwaiti Dialect

    by Hana Alostad, Shoug Dawiek, Hasan Davulcu

    The Kuwaiti dialect is a particular dialect of Arabic spoken in Kuwait; it differs significantly from standard Arabic and the dialects of neighboring countries in the same region. Few research papers with a focus on the Kuwaiti dialect have been published in the field of NLP. In this study, we created Kuwaiti dialect language resources using Q8VaxStance, a vaccine stance labeling system for a large dataset of tweets. This dataset fills this gap and provides a valuable resource for researchers studying vaccine hesitancy in Kuwait. Furthermore, it contributes to the Arabic natural language processing field by providing a dataset for developing and evaluating machine learning models for stance detection in the Kuwaiti dialect. The proposed vaccine stance labeling system combines the benefits of weak supervised learning and zero-shot learning; for this purpose, we implemented 52 experiments on 42,815 unlabeled tweets extracted between December 2020 and July 2022. The results of the experiments show that using keyword detection in conjunction with zero-shot model labeling functions is significantly better than using only keyword detection labeling functions or just zero-shot model labeling functions. Furthermore, for the total number of generated labels, the difference between using the Arabic language in both the labels and prompt or a mix of Arabic labels and an English prompt is statistically significant, indicating that it generates more labels than when using English in both the labels and prompt. The best accuracy achieved in our experiments in terms of the Macro-F1 values was found when using keyword and hashtag detection labeling functions in conjunction with zero-shot model labeling functions, specifically in experiments KHZSLF-EE4 and KHZSLF-EA1, with values of 0.83 and 0.83, respectively. Experiment KHZSLF-EE4 was able to label 42,270 tweets, while experiment KHZSLF-EA1 was able to label 42,764 tweets. Finally, the average value of annotation agreement between the generated labels and human labels ranges between 0.61 and 0.64, which is considered a good level of agreement.


  • Open Access

    Q8VaxStance: Dataset Labeling System for Stance Detection Towards Vaccines in Kuwaiti Dialect

    by Hana Alostad, Shoug Dawiek, Hasan Davulcu

    The Kuwaiti dialect is a particular dialect of Arabic spoken in Kuwait; it differs significantly from standard Arabic and the dialects of neighboring countries in the same region. Few research papers with a focus on the Kuwaiti dialect have been published in the field of NLP. In this study, we created Kuwaiti dialect language resources using Q8VaxStance, a vaccine stance labeling system for a large dataset of tweets. This dataset will fill this gap and provide a valuable resource for researchers studying vaccine hesitancy in Kuwait. Furthermore, it will contribute to the Arabic natural language processing field by providing a dataset for developing and evaluating machine learning models for stance detection in the Kuwaiti dialect. The proposed vaccine stance labeling system combines the benefits of weak supervised learning and zero-shot learning; for this purpose, we implemented 52 experiments on 42815 unlabeled tweets extracted between December 2020 and July 2022. The results of the experiments show that using keyword detection in conjunction with zero-shot model labeling functions is significantly better than using only keyword detection labeling functions or just zero-shot model labeling functions. Furthermore, using the Arabic language in both the labels and prompt or a mix of Arabic labels and an English prompt is statistically significant compared to using English in both the labels and prompt for the total number of generated labels evaluation metric. Finally, the best accuracy for Macro-F1 values were found in the experiments KHZSLF-EE4 and KHZSLF-EA1, with values of 0.83 and 0.83, respectively. And, for the total automatically labeled data evaluation metric, experiment KHZSLF-EE4 labeled 42,270 tweets, while experiment KHZSLF-EA1 was able to generate 42,764 labels.


  • Open Access

    Detecting and Measuring the Polarization Effects of Adversarial Botnets on Twitter

    by Yeonjung Lee, Mert Ozer, Steven R. Corman, Hasan Davulcu

    In this paper we use a Twitter dataset collected between December 8, 2021 and February 18, 2022 towards the 2022 Russian invasion of Ukraine to design a data processing pipeline featuring a high accuracy Graph Convolutional Network (GCN) based political camp classifier, a botnet detection algorithm and a robust measure of botnet effects. Our experiments reveal that while the pro-Russian botnet contributes significantly to network polarization, the pro-Ukrainian botnet contributes with moderating effects. In order to understand the factors leading to different effects, we analyze the interactions between the botnets and the barrier-crossing vs. barrier-bound users on their own camps. We observe that, where as the pro-Russian botnet amplifies barrier-bound partisan users on their own camp majority of the time, the pro-Ukrainian botnet amplifies barrier-crossing users on their own camp alongside themselves majority of the time.