Data Skeptic

Discover how DIY network analysis unveils connections among past podcast guests based on their co-authorship. Dive into the intricacies of academic collaborations, exploring underrepresented voices and the application of machine learning. Unpack the challenges of multi-agent software and personal data privacy while learning about effective data visualization techniques. Gain insights into the dynamics of academic publishing and uncover metrics that reveal the hidden structures in scholarly networks, showcasing the richness of collaborative research.

Pål Grønås Drange, an Associate Professor at the University of Bergen, dives into parameterized complexity and its implications for solving tough computational problems. He unpacks the network diversion problem, illustrating the challenge of directing flow through specified paths rather than merely blocking routes. The discussion covers vulnerability measures in networks, with real-world examples like the Nord Stream incident, and highlights how certain structural characteristics can influence algorithm performance. Listeners gain insights into network efficiency and the intricate relationship between theory and practical application.

Baruch Barzel, a mathematics and physics professor at Bar-Ilan University and co-founder of OpMed AI, discusses the complexities of network dynamics. He highlights that understanding how interactions within networks influence information spread is crucial. Barzel explores the small world hypothesis and how personal connections drive social campaigns. He also delves into applying dynamic network theory to optimize hospital operations, showcasing innovative strategies that enhance efficiency and patient care.

Gabriel Ramirez, a Manager for GitHub's notifications team, explores the intersection of network science and teamwork. He discusses how GitHub's collaborative tools enhance organizational understanding and the delicate balance of knowledge sharing among experts. The conversation touches on the ethical aspects of network analysis and the impact of Git commits on collaboration. Ramirez also highlights tools like GH Graph Explorer for analyzing GitHub data, advocating for decentralized decision-making to boost team dynamics.

Dive into the fascinating world where graph theory meets computational complexity. Discover how algorithm efficiency diminishes as graph size increases and the engineering hurdles that come with it. Learn about NP-complete problems and their critical role in the data-driven landscape. The discussion also emphasizes the need for analytics education and collaboration with engineers to tackle real-world graph challenges effectively. This exploration reveals the intricate dance between complexity and practical solutions that shapes modern tech.

In this discussion, Armin Pournaki, a Joint PhD candidate at the Max Planck Institute, unfolds the concept of Actantial Networks. He reveals how these graph-based structures can dissect political narratives, showcasing how conflicting stories arise around events like COVID-19 and the war in Ukraine. Pournaki also highlights how natural language processing helps visualize social media discourse, aiding in understanding polarization and narrative persuasion. His insights transform the way we perceive political communication in a divisive landscape.

Utkarshani Jaimini, a grad student at the University of South Carolina's Artificial Intelligence Institute, focuses on causal neurosymbolic AI. She explores how AI can distinguish cause from correlation using knowledge graphs. Jaimini discusses the practical implications for healthcare, including personalized models for conditions like pediatric asthma. Additionally, she addresses challenges in causal inference and the integration of weights in link prediction, all while emphasizing the importance of explainability in AI systems.

Benjamin Schaefer, an assistant professor at the Karlsruhe Institute of Technology, dives into the complex dynamics of energy systems. He discusses the Brass Paradox, illustrating how adding connections can lead to inefficiencies. Schaefer explores how AI can optimize energy production and consumption amidst change, addressing challenges like blackouts. He highlights the intricate balancing act in expanding energy networks and draws parallels to traffic systems, revealing how shortcuts can unexpectedly complicate efficiency.

Bastian Rieke, a tenured professor of machine learning at the University of Fribourg and leader of the Eidos Lab, dives deep into the world of graph datasets. He discusses the RINGS framework for evaluating dataset robustness and the significance of community dynamics in network analysis. Rieke highlights how topology can enhance machine learning performance by revealing data structure insights. He also addresses the ongoing challenges in graph learning and the necessity for better real-world datasets to foster innovation in research.

In this episode we talk with Manita Pote, a PhD student at Indiana University Bloomington, specializing in online trust and safety, with a focus on detecting coordinated manipulation campaigns on social media.  Key insights include how coordinated reply attacks target influential figures like journalists and politicians, how machine learning models can detect these inauthentic campaigns using structural and behavioral features, and how deletion patterns reveal efforts to evade moderation or manipulate engagement metrics. Follow our guest X/Twitter Google Scholar Papers in focus Coordinated Reply Attacks in Influence Operations: Characterization and Detection ,2025 Manipulating Twitter through Deletions,2022