Institution profile

University of Trento

Academic institutioneurope · it
Official website
Research library584linked papers
Opportunities0open roles
Selected work

Representative Papers

Stereotypical gender actions can be extracted from web text

Sep 01, 2011J. Assoc. Inf. Sci. Technol.

This study investigates whether web-based text—particularly Twitter corpora—can effectively represent gender-stereotyped behavioral associations and align with human commonsense judgments. Methodologically, we propose a quantification framework for action-gender bias grounded in user gender metadata and pronoun/name heuristics, integrated with the Open Mind Common Sense knowledge base to systematically extract and annotate gender-associated actions. To our knowledge, this is the first cross-source validation of gendered behavioral stereotypes between web text and structured commonsense knowledge. We construct a high-quality gender-action dataset comprising 441 manually annotated and 21,442 automatically annotated instances. Experimental results show that our model achieves a Spearman correlation of 0.47 and an AUC of 0.76 against human-annotated gold standards, demonstrating that web text can robustly model and complement commonsense-level gendered behavioral stereotypes with high recall. This work establishes a novel paradigm for large-scale, dynamic modeling of gender cognition.

26 citations2 influentialRead paper

Cross-domain object detection using unsupervised image translation

Dec 01, 2021Expert systems with applications

This work proposes a concise and interpretable unsupervised domain adaptation method to address the poor generalization of object detection models on unlabeled target domains. By integrating CycleGAN with AdaIN-based image translation, the approach leverages labeled source-domain images and unlabeled target-domain images to generate realistic synthetic target-domain data for training a more robust detector. The generated data effectively bridge the domain gap, substantially narrowing the performance gap compared to models trained with real annotated target-domain data. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance across multiple autonomous driving benchmarks, highlighting its effectiveness in enhancing cross-domain detection accuracy without requiring target-domain annotations.

23 citations2 influentialRead paper

Optimisation of cyber insurance coverage with selection of cost effective security controls

Feb 01, 2021Computers & security

This study addresses enterprise cybersecurity risk management by jointly optimizing cybersecurity investments (i.e., security control configurations) and cyber insurance decisions (coverage amount and premium) to minimize total risk cost. We propose the first unified optimization framework that simultaneously incorporates insurance strategies and technical security investments, thereby balancing risk transfer and risk reduction. Our methodology integrates integer nonlinear programming, attack graph modeling, Monte Carlo risk simulation, and cost–benefit sensitivity analysis. Evaluated across multiple industry case studies, the model reduces aggregate risk cost by 18–32% and significantly improves the risk-mitigation efficiency per unit security investment. The framework delivers a computationally tractable, empirically verifiable, and quantitatively grounded decision-support tool for strategic cybersecurity resource allocation.

23 citations1 influentialRead paper

Mapping AI avant-gardes in time: posthumanism, transhumanism, genhumanism

Oct 03, 2023Discover Artificial Intelligence

This paper addresses the challenge posed by AI development to the foundations of humanism, systematically tracing the historical evolution, conceptual distinctions, and paradigmatic shifts among posthumanism, transhumanism, and the newly proposed “genhumanism.” Employing a “time–ideology” three-dimensional framework, it integrates digital humanities, conceptual history analysis, interdisciplinary discourse mapping, and critical technology studies. The study identifies, for the first time, key divergences, intersections, and generational transitions across technological philosophy, ethics, and socio-imaginative dimensions. Its contributions include: (1) a dynamic intellectual history map of AI thought and a diachronic terminology timeline revealing a hitherto obscured biological turn; (2) the articulation of genhumanism as an integrative theoretical framework; and (3) the design of a collaborative practice initiative uniting philosophers and AI engineers—thereby grounding AI governance in historical depth and normative anchoring.

6 citationsRead paper

Towards Open Diversity-Aware Social Interactions

Feb 17, 2025arXiv.org

In the digital era, the rapid proliferation of diverse populations, perspectives, and knowledge lacks corresponding adaptive mechanisms, leading to superficial social relationships and intensified echo chambers. Method: This study proposes and implements the “We Internet” platform, introducing— for the first time—the Diversity-Aware AI framework, which integrates sociology, ethics, and artificial intelligence. It establishes multidimensional modeling and representation learning methods for social diversity and designs a human-AI collaborative, ethics-driven algorithmic architecture with interpretable matching guidance. Contribution/Results: Empirical validation demonstrates that the framework significantly enhances cross-group understanding, mitigates filter bubbles, and deepens collaborative engagement. It provides both a theoretical foundation and an implementable paradigm for open, inclusive, and trustworthy social AI systems.

3 citationsRead paper
Recent publications

Latest Papers