After decades developing methods to model and characterize social networks, we are now in a position to use rigorous probabilistic approaches to make predictions from network data. For example, using network approaches we can anticipate conflict between team members, or predict whether individuals will cooperate or defect when facing a social dilemma. In this session, we will discuss the fundamentals and learn some Python tools for network inference.

In this workshop, the instructors will use lecture, discussions, and software demos to introduce a new area, Computational Psychometrics (CP; Cipresso, 2015; von Davier, 2015), and the best assessment practices for data logging, data mining (DM), visualization, and machine learning (ML) techniques, as well as methods for evaluating results from the analyses of Big Data, even using virtual reality (VR). The session is designed for researchers with a background in measurement but less experience with data mining or machine learning.

Within a well-designed graph or data visualization, the eyes can be a powerful tool for understanding patterns in data. But within a poorly-designed depiction of the same data, the same tasks can be inefficient, or even overwhelming. In this workshop Psychology Professor Steven Franconeri will combine an overview of data visualization techniques with hands-on exercises to illustrate how to clearly present your data to both your research colleagues and to non-technical audiences.

The Web of Science Core Collection is a vast citation network representing the global landscape of science since 1900. For decades, researchers have explored this rich dataset to answer key questions about the nature of scientific discovery and innovation and to empower big data analytics. The Web of Science Core Collection contains metadata on the entire scholarly publishing landscape including over 20,000 peer reviewed journals, 180,000 conferences, and 80,000 books across all sciences, social sciences, and arts & humanities. It contains over a billion cited references, forming a giant network of interconnections between scientists, their institutions, and their disciplines. The data represent science globally, enabling the exploration of changing R&D patterns as emerging economies grow their research footprint and collaboration trends evolve. Big data techniques have opened the analytical possibilities for citation data beyond the traditional bibliometric studies into network analyses that combine citation data with datasets from other disciplines. Citation data are used by researchers in information science, computer science, business, economics, public policy, and network studies to answer questions related to scientific funding, innovation, scientific workforce, team science, etc. We will discuss the characteristics of Web of Science Core Collection data, how it is structured, and common types of analysis conducted. A sample of the raw data will be provided in advance. Participants are encouraged to explore the data in advance and bring questions to the workshop. The instructor will run through common use cases using the data.

Shiny is an R package that lets you build interactive web applications that can stand alone on a web page, function as a dashboard, or be incorporated into R Markdown documents. You can share your data and research in engaging ways or create tools to help students explore statistical concepts and data analysis. In this workshop we’ll explore what you can do with Shiny, and you’ll create your first Shiny application. Workshop attendees should be familiar with R and bring their laptop with R, RStudio, and packages Shiny and tidyverse installed and up to date.

In this hands-on workshop, participants will learn to build multi-level agent-based models in NetLogo with the recently developed LevelSpace Extension. The workshop is led by members of the Center for Connected Learning and Computer-Based Modeling, and directed by Prof. Uri Wilensky, the inventor of NetLogo. We will run the workshop to accommodate a wide range of experience levels. No programming or modeling experience is required.

Multi-level Agent-Based Modeling (ML-ABM) enables modelers to easily expand on models by connecting them to other models. Typical use cases for ML-ABM include modeling interactions between levels by delegating each representational level to each own model, e.g. representing an organization as a collection of individual departments, each represented by a model; zooming in on particular event by designing higher spatial or temporal granularity event-specific models, e.g. a model for simulating a shipping accident embedded inside a larger time-scale logistics model; or connecting different types of models like agent based models and systems dynamics models.

LevelSpace is a recently developed ML-ABM extension to NetLogo, one of the most widely used ABM environments. In this workshop, participants will learn about ML-ABM, and use NetLogo and LevelSpace to build and/or expand on models. Participants are encouraged to bring their own models if they have them, but we will provide interesting models for participants as well.