Chair: Montanelli Picascia
Manzi, G., Guo, Q., Russo, L., Grané, A. An AI-based approach for transforming textual information into structured survey data
Abstract
In this work we present an original approach for transforming textual data in survey data with the use of chatbot technologies. We consider ChatGPT APIs to associate any short text (regarded as a ”possible answer”) to the most probable question which could generate it among a list of few questions, possibly representing a survey questionnaire. We also ask ChatGPT to give, according to the meaning of each short text, a possible answer option. This short text might be, for example, (i) an X tweet or (ii) an open-ended question in a real survey questionnaire. In case (i) we construct a survey data set from X messages, and in case (ii) we use this procedure to check for answer reliability in a real survey.
Bitetto, A., Cerchiello, P., Agosto, A., Kostiuk, Y. How to measure Environmental Sustainability? A Data-Driven Approach
Abstract
This paper introduces the Data-Driven Environmental Performance Index (DDEPI), a novel, objective tool for assessing environmental sustainability. Developed using robust statistical techniques such as Robust Principal Component Analysis (RobPCA), the DDEPI overcomes biases inherent in traditional indices by relying on historical data and data-driven methodologies. It evaluates the environmental performance of 167 countries over the period 2015–2022. The results highlight the importance of governance, institutional quality, and energy transition in driving sustainability, offering actionable insights for policymakers.
Spelta, A., Facchinetti, S., Osmetti, S., Tarantola, C., Mare, C., Merli, L., Mazzalli, A. Wasserstein Propagation in Social Networks for Country-Level Cyber Risk Profiling
Abstract
This paper applies Wasserstein Propagation in Social Networks to model the diffusion of cyber risk across interconnected economic systems. By leveraging a dataset of global cyber attacks and macroeconomic indicators, we estimate risk profiles for countries lacking sufficient data. Our results highlight critical interdependencies and vulnerabilities among nations, demonstrating the utility of network-based cyber risk modeling and its implications for global cybersecurity resilience.