10:30–11:00  |  In-person

Welcome & Introduction to SICSS Melbourne

Organisers: Bogdan Mamaev, Kateryna Kasianenko

11:00–12:30  |  In-person  |  Keynote Dialogue

What is Computational Social Science and Why It Matters in Australia?

Speakers: Daniel Angus, Olga Boichak, Svetha Venkatesh

Explore the foundational principles of Computational Social Science (CSS) and its growth within the Australian context. We will examine how CSS transforms our understanding of society and provides unique value for modern research. This is an interactive session — we will introduce ourselves and answer any questions.

13:30–14:30  |  In-person

Research Speed Dating

Learn about the future of computational social science by getting to know your fellow participants. You will speak to several particpants for 2 minutes, and will share with the group your take on the tendencies and intersections in the research interests of the cohort that you observed.

15:15–16:30  |  Hybrid  |  Keynote

Social Bias in Computational Social Science

Speakers: Ahrabhi Kathirgamalingam

Learn about common sources of social bias in digital media data, and those that stem from data collection strategies, computational methods, and research designs that incorporate digital data and methodologies. This session contributes to one of our main discussions: what are the limitations and opportunities of CSS and digital methods?

09:00–10:30  |  In-person  |  Talk

Ethics in Computational Social Science

Speakers: Dominique Carlon, Ehsan Dehghan, Olga Boichak

The panel will facilitate a discussion on one of the most important issues when working with digital data — ethics, complying with legislation and terms of service, the issues of consent when working with participant data, and satisfying human research ethics committee requirements.

11:00–12:30  |  In-person  |  Workshop

Data Donations and Participant-Centric Research

Speakers: Kellie Vella, Lauren Hayden, Michael Esteban

We will present approaches to data donation, including data download packages and screen capture using mobile phones and browser extensions. We will discuss how to conduct studies that require participants to share their own digital platform data, focusing on ethical considerations, linked methods, and AIO tools.

13:30–14:30  |  In-person

Demystifying Publishing in Computational Social Science

Speakers: Olga Boichak, Kateryna Kasianenko

Computational social science is a highly interdisciplinary field. The same cannot be said about many academic publishing avenues, such as journals and conferences. This means that findings from CSS studies need to be translated in ways that persuade peer reviewers. The speakers will draw from their experience to discuss how this challenge can be overcome.

15:00–16:00  |  In-person

Nectar: Australian Research Infrastructure for Computational Analysis

Speakers: Sonia Ramza

In this session, we will explore what cloud infrastructure is and how it can support your research in the Australian context. We will show you how to access additional compute on demand and discuss the unique benefits and opportunities of working with remote infrastructure like Nectar.

09:00–10:30  |  In-person  |  Workshop

Does Computational Social Science Lack Theory?

Speakers: Ehsan Dehghan

Critics argue that CSS lets the methodological tail wag the substantive dog; that its predictive success masks explanatory weakness, and that it imports questions to fit available data. This session engages such critiques and examines what researchers can take from them when designing their own projects.

11:00–12:30  |  In-person  |  Talk

The AIReD platform for Australia-wide Social Media Discovery and Usage

Speakers: Richard Sinnott

This talk focuses on the Australian Internet Research Dashboard (AIReD), a platform comprising extensive data resources (over 500 million posts) from many social platforms offering an API, including BlueSky, FlickR, GDELT, Mastodon, YouTube, as well as historic data from X/Twitter. The talk covers how the platform came into being, demonstrates its core capabilities, and describes how researchers can access and use the platform for their own social media research needs.

13:30–15:00  |  In-person  |  Workshop

Collecting and Analysing Data Download Packages

Speakers: Kellie Vella, Lauren Hayden, Michael Esteban, Dan Tran

We will introduce data download packages as an ethical and participant-centred approach to accessing digital trace data. Participants will learn how researchers are currently using DDPs, set up a data donation project, and explore donated datasets using computational tools developed or supported by the AIO.

15:30–17:00  |  In-person  |  Workshop

Working with Text Using Computational Techniques

Speakers: Kim Doyle, Daniel Russo-Batterham

The web is full of text data relevant to social science research, but collecting and analysing it has traditionally required serious programming skills. This hands-on session shows how modern large language models lower that barrier. Participants will learn to use LLM-powered tools to scrape and extract text from real websites, then see how the same approach can be used for typical textual analysis tasks, such as sentiment analysis. Participants will leave with tools and resources to apply in their own research.

09:00–10:30  |  In-person  |  Workshop

Screen Capture for Data Collection

Speakers: Dan Tran, Daniel Angus

Using the AIO Mobile Screen Capture tools as an example, we will discuss when and how to collect and analyse images, text and other data from users' screens. We will cover the technical and ethical requirements for this form of data collection and how to approach the subsequent analysis.

11:00–12:30  |  In-person  |  Workshop

Using LLMs to Create Data Analysis Pipelines for Text-as-Data Research

Speakers: Seraphine F. Maerz

Learn about the use of LLMs for text-as-data research. We will explore how LLMs streamline large-scale analysis and facilitate the creation of automated data analysis pipelines. Finally, we'll put LLMs into practice using the Quallmer R package.

13:30–14:30  |  In-person  |  Workshop

RAG Systems in Research

Speakers: Futoon Abushaqra, Sachin Pathiyan Cherumanal

This session will introduce participants to the fundamentals of Retrieval-Augmented Generation (RAG), a framework that combines information retrieval with large language models (LLMs) to produce more accurate and context-aware responses. It will provide a high-level overview of how RAG systems work.

14:45–16:15  |  In-person  |  Workshop

Image Analysis for Qualitative and Quantitative Research

Speakers: Kunal Chand, Lauren Hayden

This session discusses large-scale image analysis using computational techniques. We introduce key concepts in machine vision and guide participants through a manual image classification activity. We will demonstrate the "Image Machine," a tool designed to cluster visually similar images and identify patterns, and "2D UMAP" as an alternative approach to plotting graphical similarities in images. The presentation will draw on illustrative examples from recent research to demonstrate how machine vision techniques can be effectively applied to social science analysis.

09:00–10:30  |  In-person  |  Panel

Cross-Disciplinary Collaboration: Bringing Social Science and Computational Analysis Together

Speakers: Oleg Zendel, Johanne Trippas, Hiruni Kegalle, Oliver Eklund

We will talk about what it means to be part of an interdisciplinary team and how to make sure that such collaboration works well. Drawing from individual experiences, the panel members will discuss how hard or easy it can be for researchers from different backgrounds to collaborate with each other and what considerations should be taken when working on a big project.

11:00–12:30  |  In-person  |  Panel

Working With and In the Industry

Speakers: Laura Gartry, Ariel Kuperman, Indigo Holcombe-James, Andrew McMahon, Stephen Wan

Laura Gartry and Ariel Kuperman discuss how newsrooms can collaborate with data scientists and AI specialists to develop responsible, editorially grounded uses of AI. Drawing on applied experience, the session explores practical collaboration models that align technical capability with journalistic goals, and the challenge for public-service media of balancing (mis)trust in AI with the principles of trust and accuracy that are fundamental to good journalism, using localised news as an illustrative context. Drawing on her experience as Head of Research at ACMI—Australia's national museum of screen culture, Indigo Holcombe-James reflects on how qualitative research is conducted in a cultural context. Working primarily through ethnographic methods mixed with statistics, she discusses the boundary between academic methods and applied, audience-centred practice. Stephen Wan speaks of his experience of leading a team of computational linguists at CSIRO who developed an approach to extract information from scientific literature, and the journey the team undertook to try to pitch the approach as a product to industry.

13:30–15:00  |  In-person  |  Workshop

Career Success

Speakers: Johanne Trippas

The workshop equips HDR candidates and ECRs with strategies for project planning, timeline management, supervisor communication, milestone navigation, and building a strong research profile suitable for different pathways in Australia.

15:15–16:15  |  In-person  |  Workshop

Grant Writing in Computational Social Science

Speakers: Daniel Angus

Securing research funding is an essential skill for any academic career, but computational social science researchers face particular challenges when navigating funding schemes. This session will explore practical strategies for positioning interdisciplinary work so it resonates with reviewers, avoids falling between disciplinary boundaries, and builds a coherent funding trajectory over time.

Tue 30 Jun  ·  10:00  | In-person  |  Talk

Music Score Analysis through Natural Language Interfaces

Speaker: Daniel Russo-Batterham

This session presents a natural language interface for analysing music scores encoded in the MEI (Music Encoding Initiative) format. The system allows users to query encoded music collections through plain-language questions, which are automatically translated into tool calls that retrieve and visualise results. This tool is an example that makes computational analysis accessible to researchers without programming expertise.

Wed 1 Jul  ·  09:00  |  In-person  |  Workshop

Validation in Computational Social Science

Speakers: Matteo Vergani

We focus on rigorous validation techniques essential for producing trustworthy CSS research outputs. Participants will explore methods for validating findings, human evaluation, and strategies for addressing validity threats.

Ongoing across Days 6–9  |  In-person

Collaborative Research Project Work

Support: Drop-in experts, organisers, and mentors

Participants work exclusively in their formed groups on their collaborative research projects. Drop-in experts, organisers, and mentors will be available to provide technical assistance, theoretical guidance, and feedback throughout each day.

Morning & Afternoon  |  In-person

Group Presentations, Final Feedback & Closing

Participants will present the preliminary findings, methodologies, and proposed solutions from their collaborative week-long projects. The program will conclude with final feedback, networking, and closing remarks.