Sergio Galletta


Last Name

Galletta

First Name

Sergio

ORCID

0000-0002-2254-9147

Organisational unit

09627 - Ash, Elliott / Ash, Elliott

Filters

2015 - 201992020 - 202528
Reset filters

Search Results

Publications1 - 10 of 37
  • On the determinants of happiness: a classification and regression tree (CART) approach
    Item type: Journal Article
    Galletta, Sergio (2016)
    Applied Economics Letters
  • War Violence Exposure and Tax Compliance
    Item type: Other Conference Item
    Galletta, Sergio; Giommoni, Tommaso (2023)
  • Students Mental Health Support with the Safespace Generative AI Chatbot: A Feasibility Study
    Item type: Working Paper
    Pinna, Matteo; Galletta, Sergio; Elmer, Timon; et al. (2025)
    Center for Law & Economics Working Paper Series
    This study evaluates the feasibility and usage patterns of the Safespace AI chatbot, an AI-driven smartphone application that offers an LLM-powered interactive chatbot to support mental health. We explored usage patterns and their associations with pre-intervention depressive symptoms in a sample of 20 university students who used the chatbot over two to four weeks. First, we find that those with elevated depression scores were significantly more likely to emotionally open up during their interactions with the chatbot. Second, usage patterns demonstrated that the highest levels of interaction occurred early in the morning and late at night, when peer and professional support may be inaccessible. Third, students who engaged more frequently with the chatbot exhibited worse pre-intervention depressive symptoms. The difference large but statistically not significant, but hints a relevant difference to explore with further data collection. These findings provide initial insights on the utility and engagement dynamics of Safespace and highlight directions for future research to optimize AI-driven mental health interventions. at index 0 with This study evaluates the feasibility and usage patterns of the Safespace AI chatbot, an AI-driven smartphone application that offers an LLM powered interactive chatbot to support mental health. We explored usage patterns and their associations with pre-intervention depressive symptoms in a sample of 20 university students who used the chatbot over two to four weeks. First, we find that those with elevated depression scores were significantly more likely to emotionally open up during their interactions with the chatbot. Second, usage patterns demonstrated that the highest levels of interaction occurred early in the morning and late at night, when peer and professional support may be inaccessible. Third, students who engaged more frequently with the chatbot exhibited worse pre-intervention depressive symptoms. The difference large but statistically not significant, but hints a relevant difference to explore with further data collection. These findings provide initial insights on the utility and engagement dynamics of Safespace and highlight directions for future research to optimize AI-driven mental health interventions.
  • How AI chatbots can improve voter information
    Item type: Other Publication
    Ash, Elliott; Galletta, Sergio; Opocher, Giacomo (2025)
    VoxEU
  • War Violence Exposure and Tax Compliance
    Item type: Presentation
    Galletta, Sergio; Giommoni, Tommaso (2023)
  • War Violence Exposure and Tax Compliance
    Item type: Working Paper
    Galletta, Sergio; Giommoni, Tommaso (2023)
    SSRN
    This paper studies the impact of exposure to war violence on individuals' willingness to comply with the law. We investigate this question by studying individual tax compliance in Italy's aftermath of World War I. Using newly digitized historical administrative records on individual tax declarations, we find that having a family member who died on the battlefield during World War I significantly decreases tax compliance compared to both families that did not suffer any loss and families that had some relatives that died for other reasons (e.g., accident or disease) while enrolled in the army during the war. To account for the potential endogeneity of the relationship between war violence exposure and tax compliance, we use a fixed effects model and an instrumental variables strategy that exploits the plausibly exogenous allocation of soldiers to more/less risky military units. Our findings are consistent with the idea that war can undermine individuals' trust in the state and political institutions, reducing their willingness to comply with state regulations. This research adds to the growing body of evidence on the ways in which wars can affect states' development.
  • The effect of the 1918 Influenza Pandemic on Income Inequality: Evidence from Italy
    Item type: Working Paper
    Galletta, Sergio; Giommoni, Tommaso (2020)
    SSRN
    In this paper, we estimate the effect of the 1918 Influenza pandemic on income inequality in Italian municipalities. Our identification strategy exploits the exogenous diffusion of influenza across municipalities due to the presence of infected soldiers on leave from World War I operations at the peak of the pandemic. Our measures of income inequality come from newly digitized historical administrative records on Italian taxpayer incomes. We show that in the short-/medium-run (i.e., after five years), income inequality is higher in Italian municipalities more afflicted by the pandemic. The effect is mostly explained by a reduction in the share of income held by poorer people. Finally, we provide initial evidence that these differences in income inequality persist even after a century.
  • A Machine Learning Approach to Analyze and Support Anti-Corruption Policy
    Item type: Journal Article
    Ash, Elliott; Galletta, Sergio; Giommoni, Tommaso (2025)
    American Economic Journal: Economic Policy
    Can machine learning support better governance? This study uses a tree-based gradientboosted classifier to predict corruption in Brazilian municipalities using budget data as predictors. The trained model offers a predictive measure of corruption, which we validate through replication and extension of previous corruption studies. Our policy simulations show that machine learning can significantly enhance corruption detection: compared to random audits, a machine-guided targeted policy could detect almost twice as many corrupt municipalities for the same audit rate.
  • How Cable News Reshaped Local Government
    Item type: Working Paper
    Galletta, Sergio; Ash, Elliott (2019)
    Center for Law & Economics Working Paper Series
  • Estimating the severity of COVID-19: evidence from the Italian epicenter
    Item type: Working Paper
    Buonanno, Paolo; Galletta, Sergio; Puca, Marcello (2020)
    Center for Law & Economics Working Paper Series
Publications1 - 10 of 37