Corso di laurea

Computational Social and Political Science

Università degli Studi di Milano · 12 materie · 0 file condivisi

Ecco tutti i dettagli sul corso di laurea selezionato. Sul UniDocs troverai gli appunti condivisi dagli altri studenti del tuo corso di laurea, ordinati per materia. Ricordati che per poter visualizzare il materiale devi essere registrato al sito e possedere un numero di crediti sufficiente.

Sfoglia il materiale didattico

Con UniDocs hai l'opportunità di studiare insieme a tutto il tuo corso di laurea. Guadagna subito dei crediti, carica il materiale del tuo ultimo esame!
Più condividi, più tempo avrai per studiare con tutta la community!

Materie del corso

Advanced multivariate analysis 1° anno · 2° semestre · 6 CFU · STAT-03/B · 0 file

This course contributes to the Master's programme in Computational Social and Political Sciences by providing students with advanced methodological tools for the analysis of complex social and political data. The…

Scheda dell'insegnamento

Obiettivi formativi

This course contributes to the Master's programme in Computational Social and Political Sciences by providing students with advanced methodological tools for the analysis of complex social and political data. The course introduces students to the logic of multivariate statistical reasoning and to modern approaches to quantitative data analysis used in computational social science.The course integrates theoretical understanding of statistical models with hands-on computational practice using the R statistical environment. Particular attention is devoted to the interpretation of statistical results, the evaluation of model assumptions, and the development of reproducible research workflows.Through applications to real-world datasets and simulation-based learning, the course equips students with the methodological foundations necessary to conduct independent empirical research and to critically assess quantitative evidence in academic, policy, and media contexts.

By the end of the course students will be able to:- understand and apply multivariate statistical techniques commonly used in social and political science research;- implement statistical analyses using the R programming language;- critically evaluate the assumptions and limitations of statistical models;- interpret and communicate statistical results in a clear and substantively meaningful way;- design and implement an empirical research project using quantitative data;- reproduce and document statistical analyses using transparent and replicable workflows.

Programma

By the end of the course students will be able to:- understand and apply multivariate statistical techniques commonly used in social and political science research;- implement statistical analyses using the R programming language;- critically evaluate the assumptions and limitations of statistical models;- interpret and communicate statistical results in a clear and substantively meaningful way;- design and implement an empirical research project using quantitative data;- reproduce and document statistical analyses using transparent and replicable workflows.

Modalità d'esame

Modalità di valutazione: EsameGiudizio di valutazione: voto verbalizzato in trentesimi

Codice insegnamento advanced-multivariate-analysis

Data governance: ethical and legal issues 1° anno · 1° semestre · 6 CFU · GIUR-17/A · 0 file

1. Introduzione 2. Il diritto fondamentale alla protezione dei dati personali 4. Definizioni in materia di protezione dei dati 5. Principi generali della normativa europea sulla protezione dei dati 6. I presupposti…

Scheda dell'insegnamento

Programma

1. Introduzione
2. Il diritto fondamentale alla protezione dei dati personali
4. Definizioni in materia di protezione dei dati
5. Principi generali della normativa europea sulla protezione dei dati
6. I presupposti giuridici relativi al trattamento dei dati personali;
7. La responsabilità del titolare del trattamento e gli obblighi del responsabile del trattamento
8. Sicurezza informatica e protezione dei dati
9. Approccio basato sul rischio e definizione di un piano di sicurezza informatica
10. Misure di sicurezza e protezione dei dati
11. Pseudonimizzazione e crittografia
12. Violazioni dei dati e rimedi agli incidenti di sicurezza
13. Il responsabile della protezione dei dati (parte I)
14. Il responsabile della protezione dei dati (parte II)
15. La normativa sulla sicurezza informatica nell'UE
16. Concetti chiave del diritto penale e loro applicazione nel campo della criminalità informatica
17. Normativa sulla criminalità informatica: Convenzione di Budapest e Convenzione delle Nazioni Unite
18. Responsabilità per i reati informatici: persone fisiche, società, Stati
19. Sfide dell'intelligenza artificiale nella sicurezza informatica
20. Normativa europea sui sistemi di intelligenza artificiale: l'AI Act
21. Sistemi di intelligenza artificiale e responsabilità civile
22. Sistemi di intelligenza artificiale e responsabilità penale
23. Indagini digitali e prove generate dall'intelligenza artificiale

Modalità d'esame

L'esame è orale. L'esame orale consiste in una discussione sugli argomenti trattati nei testi di riferimento obbligatori. L'esame ha lo scopo di valutare la preparazione e la capacità argomentativa dello studente.

Testi di riferimento

1. Handbook on European data protection law - 2018 edition, available at https://www.coe.int/en/web/data-protection
2. G. Fuster - L. Jasmontaite, Cybersecurity Regulation in the European Union: The Digital, the Critical and Fundamental Rights, 2020, available in Open Access at https://link.springer.com/chapter/10.1007/978-3-030-29053-5_5
3. Website on EU Digital Strategy with a focus on cybersecurity regulation: https://digital-strategy.ec.europa.eu/en/policies/cybersecurity-policies
4. P.G. Chiara, Towards a Right to Cybersecurity in EU Law? The Challenges Ahead, 2023, available on SSRN at https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4537093
5. A. Gascón Marcén, The Budapest Convention and the UN Cybercrime Convention negotiations, in A. Segura Serrano (ed.), Global Cybersecurity and International Law, Routledge, 2024
6. S. Gless - E. Silverman - T. Weigend, If robots cause harm, who is to blame? Self-driving cars and criminal liability, in New Criminal Law Review, Vol. 19, Number 3, 2016, 412 ss. [link SSRN: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2724592]
Additional references will be provided during the classes.

Codice insegnamento data-governance-ethical-and-legal-issues-0

Foundations of statistical modelling for social and political sciences 1° anno · 1° semestre · 9 CFU · STAT-03/B · 0 file

This course offers an introduction to the foundational principles of statistical science, a discipline that underpins much of modern data analysis and decision-making. The focus is on providing a comprehensive…

Scheda dell'insegnamento

Obiettivi formativi

This course offers an introduction to the foundational principles of statistical science, a discipline that underpins much of modern data analysis and decision-making. The focus is on providing a comprehensive understanding of the core concepts and methods that form the basis of statistical thinking and practice.Designed for students in the social and political sciences, this course aims to equip participants with the essential tools and knowledge to effectively understand and apply statistical methods within their fields. Emphasis is placed on mastering the fundamentals of statistical science, which are crucial for analyzing and interpreting data rigorously and meaningfully.The course combines theoretical lessons on statistical techniques with practical sessions that emphasize their empirical application using R software. Topics will primarily follow a frequentist approach, with introductory notions of Bayesian methods included to broaden students' perspectives.

By the end of the course, students will have acquired a solid set of skills in quantitative research from both a theoretical and practical perspective. They will be able to conduct univariate, bivariate, and multivariate analyses, and apply the fundamental principles of statistical inference. Additionally, students will be proficient in using the statistical software R and capable of independently carrying out a research project.Specifically, students will learn to:· Enter and manage their own datasets for analysis;· Identify appropriate statistical methods to address theory-driven research questions;· Conduct their own analyses using R;· Interpret the results of data analysis.

Programma

Durante le sessioni teoriche e pratiche verranno trattati i seguenti argomenti:
· Statistica descrittiva: metodi per riassumere e visualizzare i dati al fine di individuare strutture sottostanti.
· Distribuzioni di probabilità: fondamenti teorici per comprendere aleatorietà e variabilità dei dati.
· Statistica inferenziale: tecniche come gli intervalli di confidenza e i test di ipotesi, che consentono di trarre conclusioni da dati campionari.
· Approcci di modellazione: modelli lineari e modelli lineari generalizzati.

Modalità d'esame

L'esame può essere svolto secondo due modalità.
Opzione A: Lavoro di gruppo e prova scritta integrativa
Gli studenti si suddivideranno in gruppi gruppi (massimo 5 /6 persone per gruppo) con lo scopo di raccogliere e analizzare dati riguardanti tematiche attuali. Dovranno preparare una presentazione da esporre in aula davanti ai loro compagni di corso.
Si richiede la creazione di un report dettagliato sul lavoro svolto, con chiara indicazione del contributo individuale di ciascun membro.
Saranno programmati momenti in aula per verificare lo stato di avanzamento del lavoro di gruppo.
Esame scritto
La prova sarà composta da due parti:
Parte 1 - Domanda aperta
La prova includerà 3 domande generali relativa agli argomenti trattati nel corso.
Punteggio massimo 5 punti
Parte 2 - Domande a risposta multipla
La prova comprenderà 5 di domande a scelta multipla sui concetti chiave del corso.
Punteggio per le domande a scelta multipla:

  • +1 punto per ogni risposta corretta
  • −0,25 punti per ogni risposta errata
  • 0 punti per le domande lasciate senza risposta
    Gli studenti potranno utilizzare una calcolatrice non programmabile.
    Durata della prova:
    60 minuti.
    Il punteggio finale sarà la somma dei seguenti tre elementi:
    Valutazione della presentazione (10 punti)
    Valutazione del report (10 punti)
    Risultato della prova scritta (10 punti)
    La lode sarà assegnata agli studenti che non solo ottengono il massimo punteggio, ma dimostrano anche un coinvolgimento significativo e attivo nelle attività proposte.
    Opzione B: Report singolo e prova scritta integrativa
    Gli studenti dovranno presentare un report riguardante l'analisi dettagliata di un caso studio di lor scelta. Posso utilizzare dati raccolti presenti sul libro di testo, in articoli pubblicati online o provenienti da banche dati. Si richiede la preparazione di un report che descriva i risultati ottenuti.
    Dovranno preparare una presentazione da esporre se possibile in aula davanti ai loro compagni di corso oppure al docente .
    Esame scritto
    La prova sarà composta da due parti:
    Parte 1 - Domanda aperta
    La prova includerà 3 domande generali relativa agli argomenti trattati nel corso.
    Punteggio massimo 5 punti.
    Parte 2 - Domande a risposta multipla
    La prova comprenderà 5 domande a scelta multipla sui concetti chiave del corso.
    Punteggio per le domande a scelta multipla:
    +1 punto per ogni risposta corretta
    −0,25 punti per ogni risposta errata
    0 punti per le domande lasciate senza risposta
    Gli studenti potranno utilizzare una calcolatrice non programmabile.
    Durata della prova: 60 minuti.
    Il punteggio finale sarà la somma dei seguenti tre elementi:
    Valutazione della presentazione (10 punti)
    Valutazione del report (10 punti)
    Risultato della prova scritta (10 punti)
    La lode sarà attribuita solo nel caso in cui venga raggiunto il punteggio massimo e il lavoro sviluppato e/o la presentazione mostrino elementi di originalità e dimostrino un elevato livello di impegno.
    Gli studenti non frequentanti possono scegliere una delle due opzioni previste. Nel caso in cui scelgano l'Opzione A, dovranno partecipare alla discussione finale in aula del progetto di gruppo.

Testi di riferimento

Agresti, A., & Kateri, M. (2022). STATISTICA PER DATA SCIENTISTS CON R E PYTHON
Agresti A. & Franklin C. Statistica: L'arte di imparare dai dati, Pearson
Slide e note a cura del docente rese disponibili su myAriel

Codice insegnamento UC25743

Policy design 1° anno · 6 CFU · GSPS-02/A · 0 file

This course supports the CSPS mission to equip students with the analytical and practical competences needed to deliver empirically grounded, theoretically informed explanations of political and social phenomena relevant…

Scheda dell'insegnamento

Obiettivi formativi

This course supports the CSPS mission to equip students with the analytical and practical competences needed to deliver empirically grounded, theoretically informed explanations of political and social phenomena relevant to public policy.

It offers a comprehensive introduction to policy design, integrating core theoretical foundations with practical applications. Students will develop the capacity to model, assess, and improve policy designs using contemporary approaches, including behavioral and institutional perspectivesBy the end of this course, students will be able to:- Knowledge and Understanding:Understand key theories of policy design—including institutional analysis, behavioral economics, and mechanistic approaches; analyze different types of policy problems and their structural characteristics; comprehend the link between policy tools and behavioral assumptions; apply concepts of causation to evaluate policy designs. - Applying Knowledge and Understanding:Design policy interventions using logic models and theories of change; use Coleman's boat framework to decompose complex policy problems; select appropriate policy tools based on behavioral assumptions; develop valid indicators for representing policy designs. - Making Judgements:Evaluate the effectiveness and appropriateness of different tools; critically assess the ethical implications of various policy instruments, especially nudges; judge the strength of evidence for causal claims; balance trade-offs between policy effectiveness and democratic values. - Communication Skills:Present policy designs using professional frameworks and visual tools; facilitate group discussions on controversial policy choices; communicate behavioral insights to non-specialist audiences. - Learning Skills:Conduct independent research on emerging approaches to policy design; synthesize insights from multiple disciplines; develop skills for lifelong learning in rapidly evolving policy environments.

Programma

A public policy is, at bottom, a set of causal theories — a bet that if we intervene on something we can control, given some assumptions about how people behave and institutions work, we can improve something. This course treats policy as an object that is designed, and design as a discipline that can be taught, applied, and assessed.
Over forty hours you move through the full arc of the designer's craft. You learn to diagnose a policy problem by reconstructing the social mechanisms that produce it; to design an intervention by matching instruments to the behavior of target populations; and to formalize that intervention as rules whose constraints can be read, coded, and even simulated.
**Module I — Diagnose**
Reconstruct why a policy problem persists: institutions, behavior, and the social mechanisms of Coleman's micro-macro boat. Ends with a theory of change.
*S01 - The design stance*
If a policy is a bet about cause and effect, what exactly are we betting on?
Public policy reframed as a set of causal theories rather than a bundle of intentions or documents. We separate the instrument, its objectives, and the assumptions that link them, and adopt the designer's stance: getting something we want by intervening on something we can control. The course map, the portfolio you will build, and the standards by which a design is judged.
Read Easton (1957), An approach to the analysis of political systems.
*S02 - Structuring policy problems*
Does a policy problem exist in the world, or in the way we frame it?
How framing and boundary work turn a diffuse social condition into a governable problem — and how each framing quietly pre-commits a family of solutions. Wicked problems and their resistance to any definitive formulation. Choosing a target population and a point of attack, and why that choice is already half the design.
Read Schmidt (2010), Taking ideas and discourse seriously.
*S03 - Institutions & behavior*
Why do people follow rules?
The two great answers: the calculus account, where rules stabilize expectations and reshape payoffs, and the culture account, where rules furnish taken-for-granted scripts and identities. The four neoinstitutionalisms as complementary lenses on the same behavior. How each lens locates the causes a designer can actually act on.
Read Falleti & Lynch (2009), Context and causal mechanisms.
*S04 - Social mechanisms I — the micro-macro link*
How can a macro-level problem be explained without a macro-level cause?
Coleman's boat as the engine of a diagnosis: descend from a macro condition to the situation actors face, cross to how they form action, and ascend to the macro outcome their choices produce. The three mechanisms — situational, action-formation, transformational — laid out in turn. Why a macro correlation demands micro-foundations to be more than description.
Read Hedström & Ylikoski (2010); Coleman (1990), ch. 1.
*S05 - Social mechanisms II — compliance & transformation*
When individual compliance adds up, does it always add up the way we expect?
Action formation under formal institutions through belief-desire-opportunity(-capacity) schemes. The transformational step reconsidered as the aggregation of (non-)compliance rather than institution-free emergence. Compliance cascades, tipping and threshold effects that produce surprising aggregate outcomes.
Read Olejniczak & Sliwowski (2015), Behaviourally informed interventions.
*S06 - Theories of change & logic models*
What has to be true for this intervention to work — and how would we know if it isn't?
Program theory as the explicit chain from inputs and activities to outputs, outcomes and impact. Surfacing the assumptions and risks on which each link depends, and reading them as testable claims. The crucial distinction between an implementation failure and a theory failure.
Read Funnell & Rogers (2011), Purposeful Program Theory, ch. 1-2.
*S07 - Studio I — a policy diagnosis*
Can you defend every arrow in your own boat?
A working session on Deliverable 1: each group presents a Coleman's-boat diagnosis of a self-chosen problem for structured peer critique. Clinics on identifying a homogeneous target population, justifying each mechanism from the literature, and drawing a diagram that genuinely improves readability. Common failure modes — implicit populations, hand-waved links, cyclical boats — diagnosed live.
Read — studio; bring a candidate problem.
**Module II — Design**
Move from problem to intervention. The full toolbox — sticks, carrots and sermons, plus organization and procedure — matched to how target populations behave.
*S08 - The instruments of public action*
Given a problem, how many genuinely different ways does government have to act on it?
The move from problem to intervention. Carrots, sticks and sermons as the organizing typology of substantive tools; McDonnell & Elmore's reading of tools as situational triggers; and Schneider & Ingram's insight that every instrument rests on a behavioral assumption about the target's capacity and willingness. Choosing a tool by matching, not by default or habit.
Read Bemelmans-Videc et al. (2010), Carrots, Sticks & Sermons, ch. 1; Salamon (2001).
*S09 - Sticks — mandates & regulation*
When is coercion the right instrument rather than the lazy one?
Prohibiting and prescribing under authority — standards, rules and mandates that assume capacity but not willingness. The costs they carry: monitoring and enforcement, uniformity imposed across heterogeneous cases, and adversarial state-citizen relations. The conditions under which a stick is both effective and legitimate, and the temptation to over-use it.
Read Schneider & Ingram (1990), Behavioral assumptions of policy tools.
*S10 - Carrots — taxation & expenditure*
If we can't forbid a behavior, can we simply make it cost more?
Rewarding and penalizing to reshape the payoffs of alternative actions. Negative externalities, and the routes to internalizing a cost. Incentive design and its characteristic pathology — goal displacement, where actors optimize the metric rather than the aim.
Read Bemelmans-Videc et al. (2010), Carrots, Sticks & Sermons, part II.
*S11 - Sermons — information & nudges*
Can telling people stories, or rearranging their choices, count as governing?
Persuasion, mandatory disclosure and choice architecture as instruments in their own right. Behaviorally-informed interventions, and the ethical line between helping a choice and manipulating it. John's provocation that, in an information age, every tool is becoming informational — and what that does to the older typologies of public action.
Read John (2013), All tools are informational now.
*S12 - Organization & system-changing tools*
What do we reach for when carrots, sticks and sermons all fail?
Direct provision and public organization; capacity-building that widens what actors are able to do; and meta-tools that reshuffle the game itself — reallocating authority, creating agencies, changing who decides. The uncertain payoffs of building capacity.
Read Howlett (2000), Managing the hollow state.
*S13 - Procedural tools & participation*
Who gets to be in the room, and does it change what comes out?
Tools that shape how a policy is made rather than what it directly does. The democracy cube — who participates, how they communicate and decide, and with what consequence for public action. Co-design, deliberation and the democratic-deficit critique. Why procedure can decide the legitimacy and effectiveness of every substantive tool deployed through it.
Read Fung (2006), Varieties of participation.
*S14 - Studio II — tool mixes & packaging*
Does your instrument actually trigger the mechanism you diagnosed?
A working session on Deliverable 2. Matching each tool to the specific mechanism it is meant to fire; calibrating its intensity; and sequencing and bundling instruments into a coherent package free of internal contradiction. Peer critique focused squarely on the fit between the behavioural assumptions invoked and the change the design expects.
**Module III — Formalise - Institutional grammar & the anatomy of constraints**
Render the instrument precise. Read policy instruments as rules, parse them with institutional grammar, and analyze how their constraints configure the action situation — text made coded, comparable and computationally tractable.
*S15 - Policy tools as rules*
What is the difference between a rule you must obey and a suggestion you may ignore?
The substantive tools designed in Module II, seen up close, are rules — and every rule has an anatomy: if X, then you must or may (not) do Y, or else Z, unless X′, and each slot does distinct work. Constraints as the raw material every design manipulates.
Read Schauer (1991); Ostrom (2009), ch. 5; Damonte & Bazzan (2024).
*S16 - Institutional grammars*
Can a paragraph of law be parsed as precisely as a sentence of grammar?
Decomposing an institutional statement into its slots. From Crawford & Ostrom's ADICO to Institutional Grammar 2.0, and the revisions driven by computational tractability.
Read Crawford & Ostrom (1995); Frantz & Siddiki (2021).
*S17 - Coding the law*
When two coders read the same statute, will they extract the same rules?
The codebook in practice. Fixing the atomic statement as the unit of analysis; using the Boolean operators within and between statements; capturing 'or else' consequences. Inter-coder reliability as the discipline that makes rules-as-data replicable.
Read Brady et al. (2018); course codebook.
*S18 - How rules configure action*
How do a handful of rules add up to a whole situation actors must navigate?
The Institutional Analysis and Development typology, and how functions they constitute an action situation — cooperative, competitive, mixed or tragic. Assigning functions from the coded aIm and its verb family. Reading the resulting constraints as the levers a designer actually pulls.
Read Ostrom (2005), Understanding Institutional Diversity, ch. 7.
*S19 - Institutions in time — synthesis*
Rules rarely die outright — so how do they actually change?
Diachronic analysis of institutional statements: establishment, redefinition, abrogation and delegation tracked across successive versions of a text. Gradual change through layering and drift, and the quiet 'unrules' — dispensations and carve-outs — that relax obligations without formal repeal.
Read Walter et al. (2021); Mahoney & Thelen (2010).
*S20 - Q&A*
PN The program is provisional; changes will be visible on the Ariel platform

Modalità d'esame

Assessment is a cumulative portfolio, not a single exam: working in small groups, students carry one self-chosen policy problem through the whole arc — diagnosis, design, and formalization — each deliverable scaffolded in a studio and the final brief defended individually. Students leave with three linked artefacts that contribute to illustrating proficiency.
*Deliverable 1 - Diagnose* (30%)
A written analysis of a self-chosen policy problem reconstructed through Coleman's boat — its situational, action-formation and transformational mechanisms — with an annotated diagram and each mechanism justified from the literature.
*Deliverable 2 - Design* (30%)
A theory of change intervening on the same problem: selection and calibration of carrots, sticks, sermons and procedural tools against the behavioural assumptions each invokes, a model figure, and the ethical and practical trade-offs.
*Deliverable 3 - Formalise & Defend* (30%)
The core rule of the design rendered in institutional-grammar form, a reading of how its constraints configure the action situation, and the gaps or loopholes the coding exposes — presented and defended orally at the final colloquium.
*Studio participation* (10%)
Continuous, all modules
Engaged contribution to the two studios and to structured peer critique, including a written review of another group's diagnosis.
**Grading criteria.**
Each deliverable is assessed on the coherence of its reasoning, the fit between the instruments or rules it chooses and the behavioral assumptions they invoke, the clarity and accuracy of its models and diagrams, and the quality of written and visual communication.

Testi di riferimento

Foundations & mechanisms
Easton, D. (1957). An approach to the analysis of political systems. World Politics.
Falleti, T. & Lynch, J. (2009). Context and causal mechanisms in political analysis. Comparative Political Studies.
Schmidt, V. (2010). Taking ideas and discourse seriously. European Political Science Review.
Funnell, S. & Rogers, P. (2011). Purposeful Program Theory. Jossey-Bass.
Instruments of public action
Schneider, A. & Ingram, H. (1990). Behavioral assumptions of policy tools. Journal of Politics.
Salamon, L. (2001). The new governance and the tools of public action. Fordham Urban Law Journal.
Bemelmans-Videc, M. et al. (2010). Carrots, Sticks & Sermons. Transaction.
John, P. (2013). All tools are informational now. Policy & Politics.
Howlett, M. (2000). Managing the hollow state. Canadian Public Administration.
Institutional grammar & the anatomy of constraints
Ostrom, E. (2005). Understanding Institutional Diversity. Princeton UP.
Crawford, S. & Ostrom, E. (1995). A grammar of institutions. American Political Science Review.
Frantz, C. & Siddiki, S. (2021). Institutional Grammar: Foundations and Applications. Springer.
Ferber, J., Gutknecht, O. & Michel, F. (2004). From agents to organizations. LNCS 2935.
Mahoney, J. & Thelen, K. (2010). A Theory of Gradual Institutional Change. Cambridge UP.
Damonte, A. & Bazzan, G. (2024). Rules as Data. Regulation and Governance.
A full reading pack with chapters, articles and lab notebooks is distributed session by session on the course platform.

Codice insegnamento policy-design

Programming for social data science 1° anno · 1° semestre · 6 CFU · GSPS-02/A · 0 file

This course supports the mission of CSPS to equip students with the technical and practicalcompetences needed to access, manage, and analyze real-world data, enabling them to applycomputational methods and data-driven…

Scheda dell'insegnamento

Obiettivi formativi

This course supports the mission of CSPS to equip students with the technical and practicalcompetences needed to access, manage, and analyze real-world data, enabling them to applycomputational methods and data-driven insights using Python and R.

By the end of this course, students will be able to independently acquire, manage, andanalyze data using both Python and R. They will develop practical proficiency in workingwithin interactive environments such as Jupyter and RStudio, enabling them to applyfundamental programming concepts across different platforms. Learners will be equipped tohandle a variety of data formats, perform essential cleaning and transformation tasks, andimplement strategies for integrating and organizing heterogeneous datasets. These skills willprepare them to engage confidently with data-driven problems in real-world contexts.In addition, students will gain experience in accessing and utilizing publicly available datarepositories, applying appropriate preprocessing techniques to prepare datasets for analysis.They will learn to address common data challenges, such as missing values andinconsistencies, and to create effective visual representations to better understand their data.Finally, students will be introduced to basic machine learning methods, including bothsupervised and unsupervised approaches, and will acquire the ability to critically evaluatemodel performance using standard metrics. Collectively, these objectives ensure that studentsnot only build technical competence but also develop the analytical mindset needed totranslate raw data into meaningful insights.

Programma

By the end of this course, students will be able to independently acquire, manage, andanalyze data using both Python and R. They will develop practical proficiency in workingwithin interactive environments such as Jupyter and RStudio, enabling them to applyfundamental programming concepts across different platforms. Learners will be equipped tohandle a variety of data formats, perform essential cleaning and transformation tasks, andimplement strategies for integrating and organizing heterogeneous datasets. These skills willprepare them to engage confidently with data-driven problems in real-world contexts.In addition, students will gain experience in accessing and utilizing publicly available datarepositories, applying appropriate preprocessing techniques to prepare datasets for analysis.They will learn to address common data challenges, such as missing values andinconsistencies, and to create effective visual representations to better understand their data.Finally, students will be introduced to basic machine learning methods, including bothsupervised and unsupervised approaches, and will acquire the ability to critically evaluatemodel performance using standard metrics. Collectively, these objectives ensure that studentsnot only build technical competence but also develop the analytical mindset needed totranslate raw data into meaningful insights.

Modalità d'esame

Modalità di valutazione: EsameGiudizio di valutazione: voto verbalizzato in trentesimi

Codice insegnamento programming-social-data-science-0

Research design and experimental methods in the social sciences 1° anno · 2° semestre · 12 CFU · GSPS-05/A · 0 file

This course introduces students to the fundamentals of research design and experimental methods for studying, understanding and explaining social and political dynamics. It consists of two modules. The 'Research…

Scheda dell'insegnamento

Obiettivi formativi

This course introduces students to the fundamentals of research design and experimental methods for studying, understanding and explaining social and political dynamics. It consists of two modules. The 'Research Design' module combines traditional social science research methods with modern computational tools and big data techniques. Students will explore the fundamental principles of research design in sociology and political science, learning how to adapt these approaches to the challenges and opportunities presented by computational methodologies. Through practical in-class exercises, students will hone their ability to formulate research questions, design studies and apply state-of-the-art computational tools to analyse large-scale social and political data. The emphasis will be on practical application to foster the ability to conduct rigorous, data-driven research in today's digital age. The 'Experimental Methods' module provides an overview of methods and techniques for designing experimental treatments for various purposes, including research and policy evaluation, in different contexts such as laboratories, the field, and online environments. Survey, vignette, conjoint and strategic interaction methods and examples will be presented. Students will become familiar with open-source software and statistical packages for experimental data analysis. Real-life case studies and in-class experiments will demonstrate how to translate ideas into concrete outcomes.

Upon completion of this course, students will be expected to be able to:- Develop and formulate research questions; - Create precise, researchable questions that are relevant to both traditional social science enquiries and contemporary computational contexts, addressing complex issues in political and social research.- Select appropriate computational tools. Students will learn to critically evaluate and select suitable computational tools and techniques based on the nature of the research question, the characteristics of the data, and the desired outcomes.- Assess methodological fit: Students will learn to evaluate the alignment between their research designs and chosen computational methods to ensure their approach is well suited to their research goals.Design experiments. Students will learn how to transform hypotheses into coherent experimental designs to produce actionable results.- Exploit different infrastructures. Students will learn how to use existing lab, field and online resources, or how to create bespoke contexts for experimental data collection.Communicating ongoing research effectively: Students will practise articulating their research projects clearly and concisely, including their design, methodologies, and the rationale behind their choices, even while the research is still in progress.

Programma

Upon completion of this course, students will be expected to be able to:- Develop and formulate research questions; - Create precise, researchable questions that are relevant to both traditional social science enquiries and contemporary computational contexts, addressing complex issues in political and social research.- Select appropriate computational tools. Students will learn to critically evaluate and select suitable computational tools and techniques based on the nature of the research question, the characteristics of the data, and the desired outcomes.- Assess methodological fit: Students will learn to evaluate the alignment between their research designs and chosen computational methods to ensure their approach is well suited to their research goals.Design experiments. Students will learn how to transform hypotheses into coherent experimental designs to produce actionable results.- Exploit different infrastructures. Students will learn how to use existing lab, field and online resources, or how to create bespoke contexts for experimental data collection.Communicating ongoing research effectively: Students will practise articulating their research projects clearly and concisely, including their design, methodologies, and the rationale behind their choices, even while the research is still in progress.

Modalità d'esame

Modalità di valutazione: EsameGiudizio di valutazione: voto verbalizzato in trentesimi

Codice insegnamento UC25746

Survey methods for public opinion research 1° anno · 9 CFU · GSPS-07/A · 0 file

The course is structured around three key pillars: Survey Methodology, Measurement in the Social Sciences, and Public Opinion Research. In particular, survey methodology is presented both as a scientific field, devoted…

Scheda dell'insegnamento

Obiettivi formativi

The course is structured around three key pillars: Survey Methodology, Measurement in the Social Sciences, and Public Opinion Research. In particular, survey methodology is presented both as a scientific field, devoted to understanding and improving the production of survey-based evidence, and as a professional practice, concerned with the design, implementation, and management of high-quality surveys. The course aims to prepare students for both dimensions, providing the methodological foundations required for academic research as well as the practical competences needed in professional survey organizations and research agencies.The intellectual backbone of the course is the concept of measurement in the social sciences. By placing measurement at the centre of survey research, the course explores how theoretical concepts are translated into empirical indicators, how measurement instruments are designed and validated, and how measurement choices shape the interpretation of survey-based evidence.The course also presents survey research as a rapidly evolving field. Particular attention is devoted to methodological innovation, including online probability panels, survey experiments, adaptive survey design, and the integration of emerging technologies such as artificial intelligence into survey practice.Finally, the course highlights the growing importance of survey research infrastructures in contemporary social science. Students are introduced to the role of large international comparative programmes, such as the European Social Survey (ESS), the European and World Values Studies (EVS/WVS), and the International Social Survey Programme (ISSP), as fundamental resources for the production, dissemination, and secondary analysis of high-quality survey data.

By the end of the course, students will have acquired the theoretical knowledge and practical skills necessary to understand, design, implement, and critically evaluate survey research in both academic and professional settings.Students will develop a comprehensive understanding of the Data Production Process in Survey Research, from the formulation of a research question to the construction, documentation, and dissemination of a high-quality dataset. They will become familiar with all major stages of the process, including conceptualization, questionnaire design, sampling, interviewing, data management, documentation, and archiving.Using survey data available for secondary analysis, students will develop a rigorous understanding of measurement in the social sciences. They will learn how theoretical concepts are translated into empirical indicators, how measurement instruments are constructed and validated, and how issues of dimensionality, reliability, and validity influence the quality and interpretation of survey data.These methodological skills will be applied to the study of public opinion, with particular attention to social and political attitudes, electoral behaviour, and contemporary societal issues. Students will also become familiar with the major international survey infrastructures and data sources used in comparative social and political research.Upon completion of the course, students will be able to manage the entire survey research process, from conceptualization to empirical analysis, and to interact effectively with research agencies, survey organizations, and multidisciplinary research teams. More broadly, they will acquire the methodological skills necessary to produce, evaluate, and responsibly use survey-based evidence in scientific, policy, and professional contexts.

Programma

Corso erogato in inglese.
Per il programma si veda la sezione in inglese.

Modalità d'esame

Corso erogato in inglese.
Per il programma si veda la sezione in inglese.

Testi di riferimento

Corso erogato in inglese.
Per il programma si veda la sezione in inglese.

Codice insegnamento survey-methods-public-opinion-research

Agent-based modelling 2° anno · 6 CFU · GSPS-05/A · 0 file

This course forms part of the Master's programme in Computational Social and Political Sciences, equipping students with the necessary expertise in agent-based modelling and computer simulation approaches for…

Scheda dell'insegnamento

Obiettivi formativi

This course forms part of the Master's programme in Computational Social and Political Sciences, equipping students with the necessary expertise in agent-based modelling and computer simulation approaches for understanding social and political dynamics. The course includes a focus on theory and hypotheses finalised for the design of formal computational models that encapsulate causal mechanisms. The key concepts related to modelling purposes are understanding, explanation, prediction and decision-making support. Students will learn how to design, implement, run, test, analyse and communicate agent-based models, paying particular attention to different audiences, including policymakers and stakeholders. The course will use only open-source and open-science software, tools, and workflows to ensure autonomy, adaptability, and long-term capabilities.Through applications to real-world datasets and problems, practical simulation design exercises and familiarity with different statistical techniques for model testing, the course will equip students with the epistemological and methodological foundations necessary to conduct independent agent-based empirical research.

By the end of the course, students will be able to:- design an agent-based model to study emergent socio-political dynamics;- analyse simulation output using appropriate statistical models;- incorporate agent-based models in complex, multi-methodological projects;- communicate their research findings to a variety of audiences.

Programma

By the end of the course, students will be able to:- design an agent-based model to study emergent socio-political dynamics;- analyse simulation output using appropriate statistical models;- incorporate agent-based models in complex, multi-methodological projects;- communicate their research findings to a variety of audiences.

Modalità d'esame

Modalità di valutazione: EsameGiudizio di valutazione: voto verbalizzato in trentesimi

Codice insegnamento agent-based-modelling-0

Causal inference in social and political science 2° anno · 6 CFU · GSPS-02/A · 0 file

Learning different statistical techniques to make causal inference using observational data and learning how to plan and implement a causal inference research design about social and political phenomena. By the end of…

Scheda dell'insegnamento

Obiettivi formativi

Learning different statistical techniques to make causal inference using observational data and learning how to plan and implement a causal inference research design about social and political phenomena. By the end of the course students will master the causal inference toolkit of quantitative research based on observational data.

Reach proficiency in various types of causal analyses. Become competent in assumptions and techniques for different methods and being able to apply the causal inference methods to relevant research questions. Be able to produce advanced statistical analyses of quantitative data independently using R.

Programma

Reach proficiency in various types of causal analyses. Become competent in assumptions and techniques for different methods and being able to apply the causal inference methods to relevant research questions. Be able to produce advanced statistical analyses of quantitative data independently using R.

Modalità d'esame

Modalità di valutazione: EsameGiudizio di valutazione: voto verbalizzato in trentesimi

Codice insegnamento causal-inference-social-and-political-science-0

Final exam 2° anno · 15 CFU · 0 file
Social network analysis 2° anno · 6 CFU · GSPS-05/A · 0 file
Scheda dell'insegnamento

Modalità d'esame

Modalità di valutazione: EsameGiudizio di valutazione: voto verbalizzato in trentesimi

Codice insegnamento social-network-analysis-0

Text analytics and machine learning and large language models 2° anno · 12 CFU · GSPS-02/A · 0 file

The course aims to provide students with both theoretical and practical knowledge of contemporary text analytics, machine learning techniques, neural network architectures, and Large Language Models (LLMs), with…

Scheda dell'insegnamento

Obiettivi formativi

The course aims to provide students with both theoretical and practical knowledge of contemporary text analytics, machine learning techniques, neural network architectures, and Large Language Models (LLMs), with particular attention to their applications in Computational Social Science. Students will be introduced to the evolution of computational approaches to text analysis, from traditional bag-of-words representations and topic modelling techniques to advanced embedding methods and Transformer-based architectures that underpin contemporary LLMs.The course will cover the implementation and use of machine learning and neural architectures on a variety of textual datasets, enabling students to understand how different models behave across different research tasks and analytical settings. Particular emphasis will be placed on practical experimentation through programming activities in both R and Python, using tools such as TensorFlow, Keras, and the Hugging Face ecosystem.Students will learn how to preprocess textual data, implement supervised and unsupervised machine learning algorithms, validate and evaluate model performance, and critically assess model robustness. The course will also introduce methods for both local and global model interpretation, enabling students to understand, explain, and evaluate algorithmic decision-making processes in computational social science applications.In addition, students will explore semantic representation techniques through static and dynamic word embeddings, with a special focus on encoder-based architectures and their role in modern natural language processing pipelines. They will also learn how to access, fine-tune, evaluate, save, and deploy pretrained models using the Hugging Face ecosystem, including adaptation to downstream tasks and domain-specific datasets.The course will further address the growing importance of interpretability, explainability, and transparency in AI systems. Students will explore methods for validating and interpreting model outputs in order to critically assess reliability, fairness, and potential biases in machine learning systems applied to social science research.

By the end of the course, students will be able to:- Understand the theoretical foundations of Text Analytics- Understand the theoretical foundations of Machine Learning algorithms - Apply explainability and interpretability techniques to assess and validate machine learning outputs and validate the results for computational social science applications- Understand the theoretical foundations and differences between Recurrent Neural Networks, Convolutional Neural Networks, and Transformer architectures- Explain the principles underlying Large Language Models and their relevance to Computational Social Science research- Develop practical skills for integrating machine learning and LLMs into computational social science workflows and research projects- Critically evaluate the limitations, biases, and ethical implications of LLM-based systems.

Programma

By the end of the course, students will be able to:- Understand the theoretical foundations of Text Analytics- Understand the theoretical foundations of Machine Learning algorithms - Apply explainability and interpretability techniques to assess and validate machine learning outputs and validate the results for computational social science applications- Understand the theoretical foundations and differences between Recurrent Neural Networks, Convolutional Neural Networks, and Transformer architectures- Explain the principles underlying Large Language Models and their relevance to Computational Social Science research- Develop practical skills for integrating machine learning and LLMs into computational social science workflows and research projects- Critically evaluate the limitations, biases, and ethical implications of LLM-based systems.

Modalità d'esame

Modalità di valutazione: EsameGiudizio di valutazione: voto verbalizzato in trentesimi

Codice insegnamento UC25751

Recensioni del corso

Studi qui? Accedi per lasciare la tua recensione e aiutare altri studenti a scegliere.

★

Nessuna recensione per ora — e la prima è la più preziosa. Condividi la tua esperienza e orienta le future matricole.