SICSS-Covenant

09:00-18:00 Arrivals

18:00- Welcome Dinner

09:00-11:00 Opening Ceremony

11:00-12:15 Introduction to Computational Social Science

12:15-13:00 New Methods for Social Science Research in the Digital Age

13:00-14:00 Lunch

14:00-15:00 R for Social Sciences and Humanities

Over the last few years, free and open-source tools like R have become increasingly popular in research environments. The R programming language offers analysts a way to perform data manipulation and wrangling, analysis and modelling, and visualisation in one place. R can also be used to develop presentations, reports, books and even websites.
In this presentation, the speakers will introduce R as a tool for humanities and social science researchers. We will look at a handful of specific applications of R. We will also introduce the audience to useful resources, communities, and learning opportunities.
Finally, we will explore a case study where R was used as part of a PhD study to perform text mining on legal documents. This project also inspired the development of an open educational resource during a mentorship through Open Life Sciences (OLS) that aims to highlight the benefits of using R in the legal profession and research environments.

15:00-16:00 From social scientist to computational social scientist: Redefining research agenda in SSA

16:00-17:30 Tutorial: Introduction to R for CSS

17:30-18:00 Announcements

18:00- Dinner

09:00-09:15 Housekeeping and Announcements.

09:15-10:30 Research Happy Hour

Required Readings:

• North and South: Naming practices and the hidden dimension of global disparities in knowledge production
• The demography of the peripatetic researcher: Evidence on highly mobile scholars from the Web of Science
• Bibliometric analysis of global migration health research in peer-reviewed literature (2000–2016)
• A bibliometric analysis of COVID-19 research in Africa
• A bibliometric analysis of childhood immunization research productivity in Africa since the onset of the Expanded Program on Immunization in 1974

10:30-12:00 North and South: Naming practices and the hidden dimension of global disparities in knowledge production. [Slides, Annotated Code]

Contemporary social sciences aim to be diverse and inclusive, yet traces of historical supremacy persist in scientific practices. One such practice is geographical references in article titles. This presentation will highlight important North-South gaps in knowledge production using more than half a million social science research articles indexed by Scopus (1996 to 2020).

12:00-13:00 Group Exercises

13:00-14:00 Lunch

14:00-18:00 Group Exercises

18:00- Dinner

09:00-09:15 Housekeeping and Announcements.

09:15-10:30 Research Happy Hour

Required Readings:

• Can a 280-character message explain stock returns? Evidence from South Africa
• Characterising different communities of Twitter users: Migrants and natives
• Comparing and combining sentiment analysis methods
• Twitter-mediated enterprise–customer communication: Case of electricity distribution services in a developing country
• Systematic delineation of media polarity on COVID-19 vaccines in Africa: Computational linguistic modeling study

10:30-12:00 Can a 280-character message explain stock returns? Evidence from South Africa.

The role of investor sentiment in financial markets has been acknowledged in the literature. In particular, previous work suggests that noise traders are often driven by sentiment rather than fundamental information. This presentation will uncover the link between tweet features and market features using 140 South African companies and a dataset of firm-level Twitter messages extracted from Bloomberg from 1 January 2015 to 31 March 2020.

12:00-13:00 Tutorials

• An Introduction to Text Analysis Watch video on Youtube, Slides, Annotated Code
• Text Analysis Basics Watch video on Youtube, Slides, Annotated Code
• Dictionary-Based Text Analysis Watch video on Youtube, Slides, Annotated Code
• Topic Models Watch video on Youtube, Slides, Annotated Code

13:00-14:00 Lunch

14:00-15:30 Group Exercises

15:30-18:00 Tutorial: Getting started with academic research using the Twitter API v2

18:00- Dinner

09:00-09:15 Housekeeping and Announcements

09:15-10:30 Research Happy Hour

Required Readings:

• A scoping review on the use of machine learning in research on social determinants of health: Trends and research prospects
• Predicting the vulnerability of women to intimate partner violence in South Africa: Evidence from tree-based machine learning techniques
• Using Machine learning algorithms to predict the state of financial inclusion in Africa
• Use of machine learning techniques to identify HIV predictors for screening in sub-Saharan Africa
• Machine learning algorithms for predicting undernutrition among under-five children in Ethiopia

10:30-12:00 Predictive Analytics: An Overview with Practical Examples using R.

12:00-13:00 Tutorial: Machine Learning for Beginners

13:00-14:00 Lunch

14:00-15:30 Tutorial: Introduction to Spatial Data and Leaflet Mapping in R [Slides & Annotated Code]

This workshop introduces the sf package and creating interactive maps using the javascript library leaflet in R. At the end of the course, participants will become familiar with the basic types of spatial data and how to check the coordinate reference system using the sf package in R. Participants will also learn how to:

• Build a static map using sf and ggplot2 using geom_sf.
• Build a chloropleth map and map with points in R using the javascript library leaflet.
• Customise a plot by changing the background tile, polygon colours and fill and adding pop up labels.

15:30-18:00 Group Exercises

18:00- Dinner

09:00-09:15 Housekeeping and Announcements.

09:15-10:30 Research Happy Hour

Required Readings:

• Using search queries to understand health information needs in Africa
• Google trends and water conservation awareness: the internet’s contribution in South Africa
• National population mapping from sparse survey data: A hierarchical Bayesian modeling framework to account for uncertainty
• High-resolution population estimation using household survey data and building footprints
• Characterizing low effort responding among young African adults recruited via Facebook advertising
• Evaluating sampling biases from third-party reporting as a method for improving survey measures of sensitive behaviors
• Using an online sample to estimate the size of an offline population
• Collecting data on HIV-related mortality during household surveys: a randomized validation study in Malawi
• YouTube videos: Survey Research in the Digital Age, Probability and Non-Probability Sampling, Combining Surveys and Big Data, Moving Beyond Simple Experiments

10:30-11:00 Open science and reproducible research in the digital age

11:30-12:30 Collecting mortality data via mobile phone surveys in countries with limited civil registration and vital statistics (CRVs).

A key goal of HIV prevention and treatment programs worldwide is to end the epidemic of HIV/AIDS by 2030. However, there are limited representative data on HIV/AIDS mortality in many African countries. This presentation will highlight a novel method for collecting representative data on mortality in countries with limited civil registration and vital statistics.

12:30-13:00 Reflections

13:00-14:00 Lunch

14:00-16:00 Tutorial: Linking demographics and geography: Using gridded population to gain spatial insights in R

Access to high-resolution population counts is key for local, national and international decision-making and intervention. It supports data-driven planning of critical infrastructures, such as schools, health facilities and transportation networks. WorldPop has developed modelling techniques to estimate population in grid cells of 100m by 100m by disaggregating census-based population totals for the entire world, leveraging the growing availability of products derived from satellite imagery. This level of detail offers the advantage of flexible aggregation of the population estimates within different administrative and functional units, for instance, school catchment areas and health zones. This session will cover the notion of gridded population, a data format at the crossroad of demography and geography. We will then have a brief overview of openly available satellite-imagery-based products that can be used for modelling gridding population and beyond, such as settlement maps. Finally, we will have some hands-on to extract information from a gridded population covering the following r packages for geospatial analysis: sf and tmap

16:00-18:00 Group Exercises

18:00- Dinner

09:00-09:15 Housekeeping and Announcements.

09:15-10:30 Tutorial: {sfnetwork}: Tidy Geospatial Networks in RSpatial networks in R [Slides, Annotated Code]

Geospatial networks are graphs embedded in geographical space. That means that both the nodes and edges in the graph can be represented as geographic features: the nodes most commonly as points and the edges as linestrings. The structure and characteristics of geospatial networks go beyond standard graph topology, and therefore it is crucial to explicitly take space into account when analyzing them. The sfnetworks R package is created to facilitate such an integrated workflow. It brings together the sf package for spatial data science and the tidygraph package for standard graph analysis. The core of the package is a data structure that can be provided as input to both the graph analytical functions of tidygraph as well as the spatial analytical functions of sf, without the need for conversion. Additionally, it offers a set of geospatial network-specific functions, such as routines for shortest path calculation, network cleaning and topology modification.

10:30-13:00 Group Exercises

13:00-14:00 Lunch

14:00-16:00 Group Exercises

16:00-18:00 SICSS-Africa + African Descendants Inaugural Joint Panel (with: SICSS-JIAS/IPATC, SICSS-West/Central Africa & SICSS-Howard/Mathematica): Interrogating Data Collection Methods Focused on African and African Descendents Around the World: Problems, Realities, And Future Opportunities.

For Development interventions to solve current and future crises data must be reliable and of high quality. The reality is, concerns about data validity pose a significant bottleneck for generating theoretical insights into the complexity of issues peculiar to peoples of Africa and the African diaspora. Previous attempts at circumventing data challenges in Africa have relied on surveys, estimates, or models that often do not reflect the reality in many African countries. In order to have a robust discussion, certain questions must be asked:

• What challenges exist in the collection of precise data?
• How do these challenges affect how poverty indices and reports are generated?
• What can stakeholders do to improve data quality?
• What unique tools are available to collect more precise data that includes the perspectives of the communities studied?
  
  This panel will discuss key challenges in the collection of precise data as well as how these challenges influence how African and African diaspora populations are studied and economic indices are generated. The panelists will draw from their unique expertise and experiences working with different forms of data to critically reflect/challenge current data collection methods, while highlighting innovative strategies for collecting data about Africans and the African diaspora.

18:00- Dinner

09:00-09:15 Housekeeping and Announcements.

09:15-12:00 Group Exercises

12:00-14:00 Tutorial: Becoming a package developer: An Introduction [Slides & Annotated Code]

R packages are an ideal way to package and distribute R code and data for re-use by others. In this session, with a live demo, we shall demystify the creation of an R package using automated tools like usethis. We will also uncover why to create a package (or not), how to improve your R package and your package development skills. The session will also highlight how to solve the challenges you will encounter in developing an R package. Lastly, we will discuss how to find your happy place in the world of R package development – as a devoted maintainer of one package or a valued contributor to dozens of packages.

14:00-15:00 Lunch

15:00-16:00 Group Exercises

16:00-17:00 Building a Reproducible Workflow

17:00- Dinner

09:00-09:15 Housekeeping and Announcements.

09:15-13:00 Group Exercises

13:00-14:15 Break

13:15-15:15 Group Exercises

15:15- Closing Dinner and Goodbye.