Ricerca

La mia attivita di ricerca si concentra sull’Intelligenza Artificiale Spiegabile (XAI), il Machine Learning e la Bibliometria, con un interesse specifico nello sviluppo di strutture interpretabili per Random Forest e Alberi Ensemble.

Articoli su Riviste

1. Aria, M., Gnasso, A., Iorio, C., & Fokkema, M. (2025). “Extending Explainable Ensemble Trees to Regression Contexts”. Applied Stochastic Models in Business and Industry, 42(1), e70064. DOI
2. Aria, M., Gnasso, A., Rivieccio, R., & Siciliano, R. (2025). “Predicting depression in Italy using random forest through the E2Tree methodology”. Annals of Operations Research. DOI
3. Aria, M., Gnasso, A., Iorio, C., & Pandolfo, G. (2024). “Explainable ensemble trees”. Computational Statistics, 39(1), 3-19. DOI
4. Aria, M., Cuccurullo, C., & Gnasso, A. (2021). “A comparison among interpretative proposals for Random Forests”. Machine Learning with Applications. DOI
5. Adamo, D., Gnasso, A., et al. (2021). “Assessment of Sleep Disturbance in Oral Lichen Planus and Validation of PSQI: a case-control multicenter study”. Journal of Oral Pathology & Medicine. DOI

Atti di Conferenza

• Gnasso, A., & Aria, M. (2025). “Can You Explain That? E2Tree, SHAP, and LIME for Interpretable Random Forests”. CLADAG-VOC 2025. Springer.
• Gnasso, A., Aria, M., & Siciliano, R. (2025). “From Prediction to Explanation: Interpreting Risk Factors in Health Survey Analytics”. CLADAG-VOC 2025. Springer.
• Gnasso, A., et al. (2025). “Research excellence and patient perception: investigating the impact of AHSCs’ scientific output”. IES 2025 - Innovation & Society.
• Gnasso, A., Aria, M., Iorio, C., & Fokkema, M. (2025). “Explainable Decision Tree Ensembles”. SIS 2024 - Methodological and Applied Statistics and Demography IV. Springer.
• Gnasso, A., & Aria, M. (2024). “The evolution of Explainable Artificial Intelligence (XAI): a preliminary systematic literature review”. ASA Conference 2024.
• Iorio, C., Gnasso, A., & Aria, M. (2024). “Inside the black-box models through explainable decision tree ensembles”. COMPSTAT 2024.
• Aria, M., Gnasso, A., Iorio, C., & Pandolfo, G. (2023). “Unlocking explainable in ensemble trees”. CMStatistics 2023.
• Aria, M., Gnasso, A., & D’Aniello, L. (2022). “Twenty Years of Random Forest: preliminary results of a systematic literature review”. IES 2022.
• Belfiore, A., Gnasso, A., Cuccurullo, C., & Aria, M. (2022). “AI and ML in accounting and finance: a bibliometric review”. JADT 2022.
• Aria, M., Cuccurullo, C., & Gnasso, A. (2021). “Supporting decision-makers in healthcare domain”. ASA 2021.

Working Papers

• Gnasso, A. “The evolution of Explainable Artificial Intelligence (XAI): a systematic literature review”.
• Gnasso, A., Aria, M., & Iorio, C. “GoI - Goodness of Interpretability”.