NUSC Summer School in Network and Data Science 2025

1. Introduction to Coding for Quantitative and Qualitative Research with R

About: This half-day workshop provides an introduction to the R programming language for those without any previous experience with this or as a refresher if you haven't used it for a while.

The goal of the course is to provide participants with an overview of how to use R for research including data processing and visualisation. It also provides a foundation for the course on Organisational Network Analysis with xUCINET for those that haven't experience in R.

By the end of the course participants will be able to:

• Import and organise quantitative and qualitative data for analysis in R.
• Apply programming logic to transform data.
• Generate descriptive statistics and professional visualisations.
• Implement common statistical techniques.
• Export analytical results and transformed datasets.

Requirements: No prior knowledge of R is required. Ideally, participants should bring their own laptops with RStudio installed.

Instructor: Bruce Cronin

2. Introduction to Coding for Quantitative and Qualitative Research Python

About: This half-day course introduces coding with Python, tailored for those interested in quantitative and qualitative research. Participants will learn the basics of Python programming and how to apply it to various research methodologies. The course will cover fundamental coding concepts, data manipulation, and basic analysis techniques. It also provides a foundation for the course on programmatic approaches to thematic analysis for text data.

By the end of the course, participants will be able to:

• Understand the basics of Python programming.
• Perform data manipulation and cleaning.
• Apply Python to both quantitative and qualitative research tasks.
• Utilize Python libraries such as Pandas and NumPy for data analysis.

Requirements: No prior programming experience is required. Ideally, participants should bring their own laptops with Python and Jupyter Notebook installed.

Instructor: Mohit Kumar Singh

3. Introduction to Discourse Network Analysis Workshop

About: The workshop provides an introduction to Discourse Network Analysis, a software-supported set of methods for analysing the development of social relationships in discourse such as policy debates. As with other content analysis tools, discourse is manually but additionally coded with actor attributes highlighting sentiment and belief structures. The network data generated can be used to identify narrative or advocacy coalitions, key players and strategic discourse shifts.

By the end of the course participants will be able to:

• code policy debates from news items or parliamentary debates using Discourse Network Analyser software;
• export network data from the coding, visualise and analyse this in Gephi visualisation software;
• Identify discourse or advocacy coalitions and key players;
• apply the methods to their own research.

Requirements: No prior knowledge of SNA is required, though some exposure to this would be helpful. Ideally, participants should bring their own laptops with Discourse Network Analyser and Gephi installed (both are java-based multi-platform executables)

Instructor: Francisca Da Gama

4. Experimental Methods and Programming in oTree

About: This course provides an introduction to causal inference, equipping participants with the skills to critique methods used in contemporary academic work and apply these methods in their research. It begins with an overview of causality in experimental designs, covering differences between observational and experimental data, randomised experiments, and random sampling. In the second part of the course, participants will gain a hand-on experience with oTree, a flexible framework based on Python. oTree is a powerful and simple tool for developing social science experiments, enabling researchers to conduct studies both online and in laboratory settings.

The course provides a step-by-step introduction to oTree, covering everything from installation to launching an experiment. Participants will learn key experimental design principles, including causal inference, randomization, and validity assessment, before moving on to practical applications of oTree.

At the end of the course participants will be able to:

• Understand experimental methods and the distinction between observational and experimental data.
• Assess random allocation and random sampling when conducting an experiment.
• Develop and program experiments using oTree, including survey and multiplayer experiments.
• Design user interfaces with HTML and CSS within the oTree framework.
• Launch and manage experiments on a local server.

Requirements: No prior knowledge is required, though basic familiarity with experimental design concepts would be helpful. Participants should bring laptops with oTree installed.

Instructor: Martina Testori

General References:

• Cunningham, S. (2021). Causal Inference: The Mixtape. Yale University Press. https://doi.org/10.2307/j.ctv1c29t27
• Llaudet, E., & Imai, K. (2022). Data analysis for social science: a friendly and practical introduction. Princeton University Press.
• Hernán MA, Robins JM (2020). Causal Inference: What If. Boca Raton: Chapman & Hall/CRC
• Chen, D. L., Schonger, M., & Wickens, C. (2016). oTree—An open-source platform for laboratory, online, and field experiments. Journal of Behavioral and Experimental Finance, 9, 88-97.
• oTree Documentation: https://otree.readthedocs.io/en/latest/install.html

5. Doing Research with Social Network Analysis: Tools, Theories, and Applications

About: The goal of the course is to provide attendees with a general overview of the field of social network analysis, confidence in using its key analytical tools in practice, and insight into how it can be used in scholarly practice in the social, economic, managerial and political disciplines. The focus is on research design and how SNA elements can be successfully integrated into a research project, paper, or dissertation. Participants will be introduced to UCINET and Netdraw software via practical exercises.

At the end of the course participants will be able to:

• independently design a research programme requiring SNA in their own field of research;
• collect and manage network data;
• analyse, interpret and visualise fundamental network measures at the individual, group and network level;
• confidently use UCINET and NetDraw to perform network analysis and visualise network data.

Requirements: All social science backgrounds are welcome, and participants are assumed not to have any previous knowledge of SNA, or of any analytical or statistical software. No previous experience with the software is expected. Ideally, participants should bring their own laptops with Ucinet installed (Ucinet is windows-based so Mac users need a windows compatibility layer such as Wine or dual boot).

General references:

• Borgatti, SP, Everett, MG and Johnson, JC (2018) Analysing Social Networks, 2nd Edition. London: Sage.

Instructors: Anna Piazza, Dr Srinidhi Vasudevan and Dr Balint Diószegi

6. Programmatic Approaches to Thematic Analysis for Text Data

About: With the proliferation of large corpora of text data, manual thematic/content analysis is no longer effective to extract common topics and key themes. Furthermore, text data is multifaceted, and it is challenging to derive the sentiment of the authors in an accurate way. To cope with that issue, machine learning-based topic modelling and sentiment analysis are well-known techniques to explore prominent topics and their sentiment from a big collection of texts.

This course aims to provide a basic knowledge about text pre-processing, sentiment extraction using HuggingFace and an introduction of the most common topic model Latent Dirichlet Allocation (LDA) using the Python-programming language. The participants will have an opportunity to practise on real customer review dataset from Amazon.

At the end of the course participants will be able to:

• holistically diagnose the sources of noises and challenges from unstructured abstract data.
• design a customised pipeline of text processing methods to address the noise and produce a ready-to-use collection of documents (i.e., corpus).
• extract customers' sentiment through pre-trained model from Huggingface or from other well-known models such as Vader, TextBlob, etc.
• employ topic modelling for identifying the prevailing themes in your research domain.

Requirements: Participants should have an elementary knowledge of the Python-programming language; course 2 in the Summer School is sufficient grounding.

Instructor: Dr Quang (James) Duong

7. Textual Analysis with Generative AI

About: This full-day course covers the use of Generative AI for text analysis. Participants will explore advanced techniques for analysing and generating text using AI models. The course will cover topics such as natural language processing (NLP) and sentiment analysis with state-of-the-art AI tools.

By the end of the course participants will be able to:

• Understand the principles of Generative AI and its applications in text analysis.
• Perform sentiment analysis and named entity recognition (NER).
• Generate text using AI models like Chat-GPT.
• Apply AI techniques to real-world text data.
• Use offline GenAI models.

Requirements: Participants should have a basic understanding of Python programming; course 2 in the Summer School is sufficient grounding. Prior experience with NLP is beneficial but not required. Participants should bring their own laptops with Python installed.

Instructor: Dr Mohit Kumar Singh

8. Generative AI for Social Network Analysis Without Coding

About: This workshop introduces social scientists to the application of Generative AI (GenAI) for exploring, analysing and visualising social networks. Traditionally, social network analysis (SNA) has required specialised programming skills or dedicated software packages that present a steep learning curve. This session demonstrates how GenAI tools can transform the accessibility of network analysis techniques, allowing researchers to focus on substantive research questions rather than technical implementation.

Participants will discover how to leverage AI assistants to process relational data, calculate network metrics, identify structural patterns, and create compelling visualisations—all through natural language instructions. The session covers fundamental SNA concepts including centrality measures, community detection, and network visualisation through practical examples relevant to contemporary social science research.

This hands-on workshop provides a foundation for researchers interested in incorporating network perspectives into their work without requiring extensive technical training. Participants will gain practical skills for analysing various forms of relational data, from interpersonal connections to organisational networks and digital interactions.

By the end of the course participants will be able to:

• Transform relational data into formats suitable for network analysis using AI tools.
• Generate and interpret essential network metrics including degree, betweenness, and closeness centrality.
• Identify cohesive subgroups and communities within networks through AI-assisted analysis.
• Create publication-quality network visualisations that effectively communicate structural patterns.
• Implement basic statistical models for testing hypotheses about social networks.
• Critically evaluate the strengths and limitations of AI-generated network analyses.

Requirements: Some familiarity with social network analysis concepts is not required but useful. Participants should bring a laptop with internet access. The session is designed specifically for social scientists new to network analysis who wish to incorporate relational perspectives into their research. While the focus is on accessibility, the workshop will provide sufficient methodological grounding for participants to critically engage with network concepts and findings.

Instructor: Dr Guido Conaldi

9. Generative AI for statistical Analysis Without Coding

About: Generative Artificial Intelligence (GenAI) tools have transformed how researchers approach statistical analysis, making sophisticated quantitative methods accessible without extensive programming knowledge. This workshop introduces social scientists to the capabilities of GenAI coding assistants for conducting statistical analyses using natural language prompts rather than writing code themselves.

During this intensive one-day session, participants will discover how to leverage GenAI tools to translate prompts into code for functional statistical analyses. The workshop takes a practical approach, demonstrating how researchers can focus on research design and interpretation while AI handles the technical implementation of analyses.

This hands-on session is designed to equip social scientists with a principled framework to conduct quantitative analysis independently regardless of their coding background. Participants will learn to inspect, modify and understand AI-generated code, developing essential skills for creating well-documented and replicable research.

By the end of the course participants will be able to:

• Formulate effective prompts that generate statistical code.
• Understand the fundamentals of programming logic to evaluate AI-generated solutions.
• Use AI assistants to import, clean and transform research data.
• Generate descriptive statistics and professional visualisations through natural language requests.
• Implement common statistical techniques.
• Troubleshoot and refine AI-generated code to meet specific research needs.
• Develop strategies for assessing the quality and reliability of AI-generated analysis.

Requirements: No prior programming experience is required, though familiarity with basic statistical concepts is helpful. Participants should bring a laptop with internet access. The workshop is designed specifically for social scientists seeking to enhance their quantitative research capabilities without investing substantial time in learning programming languages.

Instructor: Dr Guido Conaldi

10. Organisational Network Analysis with xUCINET in R

About: This course provides an introduction to social network analysis applied to the study of organisational networks. These social networks are shaped and influenced by organisational tasks and structures and various methods of accounting for these effects are considered in the course. The course also builds on elementary understanding of the UCINET software package by examining how many repetitive analytical tasks, common in organisational network analysis, can be automated using the new R-based version of the software, xUCINET.

By the end of this course participants will be able to:

• confidently execute UCINET commands in RStudio;
• write simple scripts to execute and repeat a series of SNA tasks;
• import organisational network data from a variety of formats and export results in various formats;
• analyse a variety of inter-organisational relationships appropriately;
• isolate and analyse organisation-specific effects on social interactions;
• customise network visualisations.

Requirements: Participants should have an elementary understanding of Social Network Analysis and R; course 1 in the Summer School is sufficient grounding. Participants should bring their own laptops with RStudio installed. No prior knowledge of UCINET is needed.

Instructor: Bruce Cronin is Professor of Economic Sociology at the University of Greenwich, where he is co-director of the Networks and Urban Systems Centre.

General references: Borgatti, SP, Everett, MG, Johnson, JC, and Agneessens, F. (2022) Analysing Social Networks Using R. London: Sage.