Ugur Kursuncu

Selected Publications

1. 

   Defining and detecting toxicity on social media: context and knowledge are key

   Sheth, Amit, Shalin, Valerie L, and Kursuncu, Ugur

   Neurocomputing 2022

   Abs HTML PDF

   Online platforms have become an increasingly prominent means of communication. Despite the obvious benefits to the expanded distribution of content, the last decade has resulted in disturbing toxic communication, such as cyberbullying and harassment. Nevertheless, detecting online toxicity is challenging due to its multi-dimensional, context sensitive nature. As exposure to online toxicity can have serious social consequences, reliable models and algorithms are required for detecting and analyzing such communication across the vast and growing space of social media. In this paper, we draw on psychological and social theory to define toxicity. Then, we provide an approach that identifies multiple dimensions of toxicity and incorporates explicit knowledge in a statistical learning algorithm to resolve ambiguity across such dimensions.

2. 

   When the Bad is Good and the Good is Bad: Understanding Cyber Social Health through Online Behavioral Change

   Kursuncu, Ugur, Purohit, Hemant, Agarwal, Nitin, and Sheth, Amit

   IEEE Internet Computing 2021

   Abs HTML PDF

   Online platforms have facilitated the exchange of harmful content at an unprecedented scale in the form of disinformation, hate speech, cyberbullying, and extremism. Its insidious impact has been observed in events related to health, disaster recovery, elections, finance, climate communication, and terrorism. Yet, it has been challenging to detect, monitor, counter, and overcome the malevolent behavior by ill-intentioned actors due to the complex nature of social media, and other large-scale socio-technical infrastructures. As harmful content is rich in subjectivity and emotion, it is challenging to understand individual messages in terms of its features and the human decision-making processes that foster its diffusion. Hence, the meaning of language varies depending on the source’s intent and the state of the target’s belief system, allowing the bad to be perceived as good due to positive social construction and vice versa. This becomes even more dangerous if malicious groups or state actors orchestrate their actions, involving bots and human actors, to disseminate misinformation and persuade individuals on its truthfulness by malicious groups, threatening an individual, our society, or democratic institutions at large. These efforts have led to negative consequences.

3. 

   Modeling Islamist extremist communications on social media using contextual dimensions: Religion, Ideology, and Hate

   Kursuncu, Ugur, Gaur, Manas, Castillo, Carlos, Alambo, Amanuel, Thirunarayan, Krishnaprasad, Shalin, Valerie, Achilov, Dilshod, Arpinar, I Budak, and Sheth, Amit

   Proceedings of the ACM on Human-Computer Interaction (CSCW) 2019

   Abs HTML PDF

   Terror attacks have been linked in part to online extremist content. Online conversations are cloaked in religious ambiguity, with deceptive intentions, often twisted from mainstream meaning to serve a malevolent ideology. Although tens of thousands of Islamist extremism supporters consume such content, they are a small fraction relative to peaceful Muslims. Divergent extremist and mainstream contexts challenge machine interpretation, with a particular threat to the precision of classification algorithms. Radicalization is a subtle long-running persuasive process that occurs over time. Our context-aware computational approach to the analysis of extremist content on Twitter breaks down this persuasion process into building blocks that acknowledge inherent ambiguity and sparsity that likely challenge both manual and automated classification. Based on prior empirical and qualitative research in social sciences, particularly political science, we model this process using a combination of three contextual dimensions – religion, ideology, and hate – each elucidating a degree of radicalization and highlighting independent features to render them computationally accessible. We utilize domain-specific knowledge resources for each of these contextual dimensions such as Qur’an for religion, the books of extremist ideologues and preachers for political ideology and a social media hate speech corpus for hate. The significant sensitivity of the Islamist extremist ideology and its local and global security implications require reliable algorithms for modelling such communications on Twitter. Our study makes three contributions to reliable analysis: (i) Development of a computational approach rooted in the contextual dimensions of religion, ideology, and hate, which reflects strategies employed by online Islamist extremist groups, (ii) An in-depth analysis of relevant tweet datasets with respect to these dimensions to exclude likely mislabeled users, and (iii) A framework for understanding online radicalization as a process to assist counter-programming. Given the potentially significant social impact, we evaluate the performance of our algorithms to minimize mislabeling, where our context-aware approach outperforms a competitive baseline by 10.2% in precision, thereby enhancing the potential of such tools for use in human review.

4. 

   Knowledge infused Learning (K-IL): Towards Deep Incorporation of Knowledge in Deep Learning

   Kursuncu, Ugur, Gaur, Manas, and Sheth, Amit

   In Proceedings of the AAAI 2020 Spring Symposium on Combining Machine Learning and Knowledge Engineering in Practice (AAAI-MAKE) 2020

   Abs HTML PDF

   Learning the underlying patterns in data goes beyond instance-based generalization to external knowledge represented in structured graphs or networks. Deep learning that primarily constitutes neural computing stream in AI has shown significant advances in probabilistically learning latent patterns using a multi-layered network of computational nodes (i.e., neurons/hidden units). Structured knowledge that underlies symbolic computing approaches and often supports reasoning, has also seen significant growth in recent years, in the form of broad-based (e.g., DBPedia, Yago) and domain, industry or application specific knowledge graphs. A common substrate with careful integration of the two will raise opportunities to develop neuro-symbolic learning approaches for AI, where conceptual and probabilistic representations are combined. As the incorporation of external knowledge will aid in supervising the learning of features for the model, deep infusion of representational knowledge from knowledge graphs within hidden layers will further enhance the learning process. Although much work remains, we believe that knowledge graphs will play an increasing role in developing hybrid neuro-symbolic intelligent systems (bottom-up deep learning with top-down symbolic computing) as well as in building explainable AI systems for which knowledge graphs will provide scaffolding for punctuating neural computing. In this position paper, we describe our motivation for such a neuro-symbolic approach and framework that combines knowledge graph and neural networks.

5. 

   ALONE: A Dataset for Toxic Behavior among Adolescents on Twitter

   Wijesiriwardene, T., Inan, H., Kursuncu, U., Gaur, M., Shalin, V.L., Thirunarayan, K., Sheth, A., and Arpinar, I.B.

   In Proceedings of International Conference on Social Informatics (SocInfo) 2020

   Abs HTML PDF

   The convenience of social media has also enabled its misuse, potentially resulting in toxic behavior. Nearly 66% of internet users have observed online harassment, and 41% claim personal experience, with 18% facing severe forms of online harassment. This toxic communication has a significant impact on the well-being of young individuals, affecting mental health and, in some cases, resulting in suicide. These communications exhibit complex linguistic and contextual characteristics, making recognition of such narratives challenging. In this paper, we provide a multimodal dataset of toxic social media interactions between confirmed high school students, called ALONE (AdoLescents ON twittEr), along with descriptive explanation. Each instance of interaction includes tweets, images, emoji and related metadata. Our observations show that individual tweets do not provide sufficient evidence for toxic behavior, and meaningful use of context in interactions can enable highlighting or exonerating tweets with purported toxicity

6. 

   Predictive analysis on Twitter: Techniques and applications

   Kursuncu, Ugur, Gaur, Manas, Lokala, Usha, Thirunarayan, Krishnaprasad, Sheth, Amit, and Arpinar, I Budak

   In Emerging Research Challenges and Opportunities in Computational Social Network Analysis and Mining 2019

   Abs HTML PDF

   Predictive analysis of social media data has attracted considerable attention from the research community as well as the business world because of the essential and actionable information it can provide. Over the years, extensive experimentation and analysis for insights have been carried out using Twitter data in various domains such as healthcare, public health, politics, social sciences, and demographics. In this chapter, we discuss techniques, approaches and state-of-the-art applications of predictive analysis of Twitter data. Specifically, we present fine-grained analysis involving aspects such as sentiment, emotion, and the use of domain knowledge in the coarse-grained analysis of Twitter data for making decisions and taking actions, and relate a few success stories.