Hands-On Exercises Design

2023-11-30 18:09 UTC gpt-4 Open in ChatGPT ↗

I am designing a module in a computer science course that will be called “Data People and Society”. The module will be taught to both BSc and MSc students with the MSc curriculum going a little bit deeper in analysis and expectations. The schedule of the course is as follows:

Week 1: Introduction to Data, People, and Society Overview of the course objectives and structure. Introduction to the ethical considerations in data collection and usage. Discussion on the impact of data abstraction on individuals and marginalised groups. Example Case Study: The Cambridge Analytica Scandal Explore how the unauthorised use of Facebook data impacted individuals and influenced political outcomes, highlighting the ethical implications of data collection. Week 2: Bias in Data and Algorithmic Fairness Exploration of biases in data and algorithms. Understanding how biassed algorithms can perpetuate or exacerbate social inequalities. Discussion on Algorithmic Fairness and its role in addressing bias. Example Case Study: Predictive Policing and Racial Bias Analyse cases where predictive policing algorithms have exhibited racial bias, leading to discriminatory outcomes and raising questions about fairness in law enforcement. Week 3: Privacy, Security, and Digital Rights Examination of privacy challenges in the digital age. Techniques for preserving privacy in data-driven applications. Exploration of digital rights and their intersection with data. Note to self: Julian Oliver / clothes that make you invisible to AI / Fango Example Case Study: GDPR and Online Privacy Discuss the implementation, impact and effectiveness of the General Data Protection Regulation (GDPR) in Europe as a case study for privacy regulations and protection of digital rights. Week 4: Data Visualization for Advocacy and Awareness Techniques for creating impactful data visualisations. Application of data visualisation in advocating for sustainable development goals. Hands-on project: Creating visualisations for a societal issue aligned with SDGs. Note to self: edward tufte books Example Case Study: Gapminder and Global Development Explore how Gapminder’s data visualisations, such as Hans Rosling’s presentations, have effectively communicated complex global development trends and influenced public perception. Week 5: Data in Public Policy and Sustainable Development Goals Analysis of how data influences public policy decisions. Exploration of the role of data in achieving specific SDGs. Case studies on the integration of data-driven approaches in sustainable development initiatives. Kostas Topouzelis: cv scans regions with drones to change police making for public spaces Example Case Study: Data-Driven Healthcare in Rwanda Examine how Rwanda used data-driven approaches to improve healthcare delivery, contributing to progress in SDG 3 (Good Health and Well-being). Week 6: Ethical AI and Algorithmic Accountability Discussion on ethical considerations in AI and algorithmic decision-making. Exploration of the societal implications of deploying AI for sustainable development. Strategies for ensuring accountability in algorithmic systems. Generative AI/sagaftra strike Example Case Study: Tesla’s Autopilot and Ethical AI Analyse ethical considerations and accountability issues related to Tesla’s Autopilot system, addressing the challenges of AI in safety-critical applications. Week 7: Digital Divide, Accessibility, and Inclusion Examination of the digital divide and its impact on social and economic development. Strategies for addressing digital inclusion and accessibility challenges. Exploration of how data can be leveraged to bridge gaps and promote inclusivity Julian Oliver/Girls who code Example Case Study: One Laptop Per Child Initiative Assess the impact of the One Laptop Per Child initiative in bridging the digital divide and promoting digital inclusion, particularly in developing regions. Week 8: Social Media, Online Communities, and Global Goals Analysis of the role of data in shaping online communities and social movements. Exploration of the impact of social media on public discourse related to the SDGs. Case studies on the use of social media for sustainable development advocacy. (Extinction Rebellion, Arab Spring) Example Case Study: #FridaysForFuture and Climate Activism on Social Media Investigate how the #FridaysForFuture movement effectively used social media to mobilise global support for climate action, aligning with SDG 13 (Climate Action).

Can you help to design a hand-on exercise for each week? Ideally the exercise will be carried out in part in class and then the students will be able to go on their own and continue

Designing hands-on exercises for each week of your “Data, People, and Society” course sounds like a fantastic way to engage students in practical learning. Here are some exercise ideas for each week:

Week 1: Ethical Considerations in Data Collection

In-Class Activity: Divide students into groups. Each group reviews a different aspect of the Cambridge Analytica case, focusing on ethical issues in data collection and usage. Groups present their findings and discuss.

Independent Exercise: Students write a short essay or prepare a presentation on an additional real-world case where data collection ethics were questionable, explaining the impact on individuals and society.

Week 2: Bias in Data and Algorithmic Fairness

In-Class Activity: Analyse a set of data provided in class for potential biases. This could be a dataset used in real-world predictive policing, loan approval, or job application screening.

Independent Exercise: Students are tasked with designing a basic algorithm for a specific task (like loan approval) and then critically analyzing where biases might creep in and how they would mitigate them.

Week 3: Privacy, Security, and Digital Rights

In-Class Activity: Group discussion on the implications of GDPR, analyzing its strengths and weaknesses. Students could role-play as different stakeholders (consumers, businesses, regulators).

Independent Exercise: Students research and present a recent case where a company or government failed to protect digital rights, focusing on the consequences and potential remedies.

Week 4: Data Visualization for Advocacy and Awareness

In-Class Activity: Quick workshop on data visualization tools (like Tableau or PowerBI). Students practice by visualizing a provided dataset related to a societal issue.

Independent Exercise: Students select a societal issue aligned with SDGs and create an impactful data visualization, explaining how it could be used for advocacy.

Week 5: Data in Public Policy and Sustainable Development Goals

In-Class Activity: Discussion on the use of data in public policy. Break into groups to analyze different case studies of data-driven sustainable development initiatives.

Independent Exercise: Students choose a specific SDG and develop a policy proposal supported by data analysis, demonstrating how data can inform and drive policy decisions.

Week 6: Ethical AI and Algorithmic Accountability

In-Class Activity: Debate on the ethical implications of AI in different sectors (healthcare, automotive, etc.), using Tesla’s Autopilot as a case study.

Independent Exercise: Students investigate another AI technology in use today, analyzing its ethical implications, societal impacts, and accountability measures.

Week 7: Digital Divide, Accessibility, and Inclusion

In-Class Activity: Explore digital divide issues through an interactive simulation or game that illustrates accessibility challenges.

Independent Exercise: Students are tasked with designing a digital inclusion initiative, focusing on a specific marginalized community, and detailing how it would address the digital divide.

In-Class Activity: Analyze the role of social media in a particular social movement (like #FridaysForFuture), discussing the impact and effectiveness.

Independent Exercise: Students create a social media campaign proposal for a cause related to an SDG, detailing strategies for engagement, content creation, and measuring impact.

These activities aim to provide a balance of collaborative learning and individual research, encouraging students to engage deeply with each topic.

For Week 3 of your course, focusing on the practical aspects of cybersecurity and the contrast between being hacked and knowingly releasing private data online sounds like an engaging and informative approach. Here’s a revised plan for that week:

Week 3: Privacy, Security, and Digital Rights

In-Class Activity: Understanding Vulnerabilities and Hacking

Demonstration: Start with a controlled demonstration of a basic hacking technique, such as a phishing attack or a password cracking demonstration (using ethical hacking principles). This can be done using a dummy website or network set up specifically for the class.
Interactive Exercise: Students participate in a simulated environment where they must identify potential vulnerabilities in a mock digital system. This could include spotting phishing emails, weak passwords, or unsecured network connections.

Independent Exercise: Analyzing Data Release and Privacy

Research Assignment: Students are assigned to research real-world incidents where individuals’ private data was released online, either through hacking or by the individuals themselves (such as social media oversharing or consenting to terms and conditions without reading them).
Comparative Analysis: Each student prepares a report or presentation that compares and contrasts the different scenarios, focusing on the implications for personal privacy, the role of user awareness, and the consequences of data breaches versus voluntary data sharing.
Reflection: Encourage students to reflect on their own digital habits and how they can improve their personal data security.

This week’s activities aim to provide a hands-on understanding of cybersecurity risks and the importance of vigilant digital practices, as well as a thoughtful analysis of the differences between involuntary data breaches and voluntary data sharing. This should help students grasp the practical realities of digital privacy and security in today’s world.

Can you give me exercises for the MSc course as well? Here is the schedule

MSc Week 1: Introduction to Advanced Data Science and Research Landscape Advanced Data Science Concepts: Overview of advanced data representation techniques and probabilistic models. Exploration of emerging trends in data-driven applications. Introduction to the research landscape at the intersection of data, people, and society.

MSc Week 2: Bias in Data and Algorithmic Fairness Advanced Bias Mitigation Techniques: In-depth exploration of advanced techniques for detecting and mitigating bias in machine learning models. Critical analysis of recent research publications in algorithmic fairness.

MSc Week 3: Privacy, Security, and Digital Rights Cutting-edge Privacy-preserving Techniques: Exploration of advanced privacy-preserving techniques such as homomorphic encryption and differential privacy. Critical examination of recent advancements in AI and privacy, emphasising real-world trade-offs.

MSc Week 4: Data Visualization for Advocacy and Awareness Advanced Data Visualization: Hands-on experience with advanced data visualisation tools like D3.js. Exploring the popularisation of data visualisation for advocacy and awareness. Exploration of recent research on perceptual and cognitive aspects of data visualisation.

MSc Week 5: Data in Public Policy and Sustainable Development Goals Advanced Analytics in Policy Informatics: Exploration of advanced analytics methods, including predictive modelling and causal inference, to policy informatics scenarios. In-depth exploration of recent research at the intersection of AI, data analytics, and public policy.

MSc Week 6: Ethical AI Governance and Algorithmic Accountability Ethical AI Governance: Exploration of advanced topics in ethical AI governance, regulatory considerations, and the role of AI ethics committees. Critical evaluation of recent advancements in algorithmic accountability, transparency, and fairness.

For the MSc course, you can design exercises that are more advanced and research-oriented, aligning with the deeper analysis and higher expectations at this level. Here are suggested exercises for each week:

MSc Week 1: Introduction to Advanced Data Science and Research Landscape

In-Class Exercise: Analyze and present a recent research paper that utilises advanced data representation techniques or probabilistic models in a real-world application. This could involve a critical review of the paper’s methodology, data representation techniques, and findings.

Independent Research Project: Students choose a current trend in data-driven applications and conduct an in-depth research project. This could involve a literature review, identifying gaps in current research, and proposing potential areas for further investigation.

MSc Week 2: Bias in Data and Algorithmic Fairness

In-Class Exercise: Conduct a hands-on workshop where students apply advanced techniques for detecting and mitigating bias in a given dataset using machine learning models.

Independent Research Critique: Students select and critically analyze a recent research publication in algorithmic fairness, evaluating the methodology, bias mitigation techniques used, and the broader implications of the findings.

MSc Week 3: Privacy, Security, and Digital Rights

In-Class Exercise: Interactive workshop on implementing a privacy-preserving technique like homomorphic encryption or differential privacy on a sample dataset.

Research Analysis: Students critically examine recent advancements in AI and privacy, focusing on real-world applications and trade-offs. This could involve a detailed report or presentation on a selected case study.

MSc Week 4: Data Visualization for Advocacy and Awareness

In-Class Exercise: Advanced tutorial on using data visualization tools like D3.js, followed by a practical exercise where students create a complex visualization based on a large or intricate dataset.

Research Project: Investigate and present a recent study on the perceptual and cognitive aspects of data visualization. This could involve analyzing how different visualization techniques affect comprehension and decision-making.

MSc Week 5: Data in Public Policy and Sustainable Development Goals

In-Class Exercise: Apply advanced analytics methods, such as predictive modelling or causal inference, to a policy informatics scenario, perhaps using a relevant dataset to predict policy outcomes or model policy impacts.

Independent Study: Deep dive into recent research at the intersection of AI, data analytics, and public policy. Students could focus on a specific case study, analyzing how data-driven approaches have been applied and the outcomes achieved.

MSc Week 6: Ethical AI Governance and Algorithmic Accountability

In-Class Discussion: Facilitate a debate or roundtable discussion on advanced topics in ethical AI governance, including regulatory considerations and the role of AI ethics committees.

Research Evaluation: Students critically evaluate recent advancements in algorithmic accountability, transparency, and fairness, possibly through the lens of a specific AI application or industry. This could culminate in a comprehensive report or presentation.

These exercises are designed to challenge MSc students, encouraging them to engage with current research and apply advanced techniques in data science and AI. They should provide a good mix of practical skills and theoretical understanding.

For Week 1 of the MSc course, focusing on “Advanced Data Science and Research Landscape,” I can suggest several research papers that span various aspects of advanced data science. These papers cover topics like advanced data representation techniques, probabilistic models, and emerging trends in data-driven applications:

“Deep Learning with Differential Privacy” by Martín Abadi et al.
- This paper presents an approach to training deep neural networks with differential privacy guarantees, balancing privacy concerns with the efficacy of deep learning models. It’s a significant contribution to the intersection of advanced data science and privacy.
“Variational Inference: A Review for Statisticians” by David M. Blei, Alp Kucukelbir, and Jon D. McAuliffe.
- This paper is a comprehensive review of variational inference, a method in Bayesian machine learning. It covers the theory behind variational inference and its applications, making it a great resource for understanding probabilistic models.
“BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding” by Jacob Devlin et al.
- BERT (Bidirectional Encoder Representations from Transformers) represents a significant leap in the ability of machines to understand natural language. This paper details the methodology and impact of BERT in natural language processing, a key area in data science.
“Distributed Representations of Words and Phrases and their Compositionality” by Tomas Mikolov et al.
- This paper introduces advancements in word embedding techniques, crucial for natural language processing. It discusses the efficiency of these representations and their ability to capture syntactic and semantic word relationships.
“Fairness and Abstraction in Sociotechnical Systems” by Selbst et al.
- This paper discusses the challenges of abstracting social contexts in the design of algorithmic systems. It’s a crucial read for understanding the societal implications of data science and algorithmic decision-making.
“Explanatory Model Analysis: Explore, Explain, and Examine Predictive Models” by Przemysław Biecek and Tomasz Burzykowski.
- This paper dives into the methods for exploring, explaining, and examining complex predictive models, which is vital for understanding model behavior and ensuring transparency.

These papers provide a broad view of the current landscape in advanced data science and offer students insights into various cutting-edge topics. Assigning any of these for detailed study and presentation would offer a deep dive into the complexities and challenges of modern data science research.

Detecting and mitigating bias in datasets using machine learning is a critical step in ensuring fairness and objectivity in AI systems. Here’s a simplified guide with steps and examples that you can use for Week 2 of your MSc course:

Detecting Bias in Datasets

Understanding the Data Source and Collection Process:
- Begin by examining where and how the data was collected. Ask questions like:
  - Were there any systematic exclusions?
  - Is there underrepresentation or overrepresentation of certain groups?
  - Was the data collected in a way that might introduce bias?
Exploratory Data Analysis (EDA):
- Use statistical tools to explore the data. This includes analyzing distributions, correlations, and summary statistics.
- For example, if you’re working with a dataset on loan approvals, examine if certain demographic groups (like a particular race or gender) are underrepresented.
Visualize the Data:
- Create plots and graphs to visually inspect for potential biases.
- In our loan approval example, you might plot approval rates across different demographic groups.
Testing for Statistical Bias:
- Conduct statistical tests to check for biases. This might include tests for independence, correlation tests, etc.
- For instance, perform a chi-square test to see if loan approval is independent of gender or ethnicity.

Mitigating Bias in Machine Learning Models

Pre-processing the Data:
- Modify the dataset to reduce bias before feeding it into the machine learning model.
- Techniques include re-sampling the dataset to balance classes, or using techniques like SMOTE (Synthetic Minority Over-sampling Technique) for imbalance correction.
Algorithmic Fairness:
- Choose or design algorithms that are less likely to produce biased outcomes.
- Implement fairness constraints or regularization techniques that penalize the model for biased outcomes.
Post-processing the Model’s Predictions:
- Adjust the model’s predictions to ensure fairness.
- This might include changing classification thresholds for different groups to ensure similar false positive/negative rates.
Validation with Disaggregated Data:
- Test the model’s performance separately across different groups.
- Ensure that metrics like accuracy, precision, and recall are consistent across groups.
Continuous Monitoring and Updating:
- Regularly review and update the model to ensure it remains unbiased over time, especially as new data comes in.

Example: Loan Approval Dataset

Detecting Bias: Analyze the dataset for the distribution of loan approvals across different demographics. Check if certain groups have significantly lower approval rates.
Mitigating Bias: If a particular group is underrepresented or shows lower approval rates, use pre-processing techniques like re-sampling to balance the dataset. While building the model, apply fairness constraints. After training, adjust thresholds if necessary to ensure that the false positive/negative rates are balanced across groups.

This approach helps students understand the practical aspects of handling bias in data science projects, balancing technical skills with an understanding of ethical implications.

Certainly! For Week 3 of your MSc course on “Privacy, Security, and Digital Rights,” focusing on cutting-edge privacy-preserving techniques, the in-class exercise could be expanded as follows:

Week 3 In-Class Exercise: Implementing and Analyzing Advanced Privacy-Preserving Techniques

Objective

The exercise aims to provide hands-on experience with advanced privacy-preserving techniques such as homomorphic encryption and differential privacy. Students will gain practical insights into how these techniques are implemented and understand their implications in real-world data scenarios.

Part 1: Homomorphic Encryption Workshop

Overview and Theory:
- Begin with a brief lecture explaining the concept of homomorphic encryption — a form of encryption that allows computation on ciphertexts, producing an encrypted result that, when decrypted, matches the result of operations performed on the plaintext.
- Discuss various types of homomorphic encryption (partially, somewhat, and fully homomorphic encryption) and their use-cases.
Practical Implementation:
- Provide a dataset and a simple homomorphic encryption library or tool. Python libraries like PySEAL or Microsoft’s SEAL can be used for this purpose.
- Guide students through a hands-on task where they encrypt the dataset, perform a series of calculations (e.g., sum, average), and then decrypt the results to verify accuracy.
Discussion:
- Facilitate a discussion on the practical challenges, such as computational complexity and limitations in the types of operations that can be performed.
- Discuss potential applications where homomorphic encryption is particularly beneficial, such as in cloud computing or secure data aggregation.

Part 2: Differential Privacy Demonstration

Conceptual Understanding:
- Introduce differential privacy, which is a system for publicly sharing information about a dataset by describing patterns of groups within the dataset while withholding information about individuals in the dataset.
- Explain key concepts like ε-differential privacy, noise addition, and trade-offs between privacy and data utility.
Implementing Differential Privacy:
- Use a simple dataset (perhaps a modified version of a public dataset) and a differential privacy library, such as Google’s Differential Privacy library or IBM’s diffprivlib in Python.
- Demonstrate how to apply differential privacy to a data analysis task, such as calculating the mean or frequency of a particular attribute, and how to adjust the privacy loss parameter (epsilon).
Analyzing Trade-offs:
- Have students observe how changes in the privacy parameter affect the accuracy of the results.
- Engage the class in a discussion about the trade-offs between data utility and privacy. Address questions like how much noise is too much and how to decide on the privacy parameter.

Conclusion: Real-world Trade-offs and Ethical Considerations

Conclude the session by emphasizing the real-world applications and ethical considerations of these privacy-preserving techniques. Discuss scenarios where these techniques are essential and how they align with broader digital rights and privacy concerns.

This expanded exercise offers students a blend of theoretical knowledge and practical skills, crucial for understanding and applying advanced privacy-preserving techniques in data science.

Certainly! Expanding on the in-class activity for Week 5 of your BSc course, which focuses on “Data in Public Policy and Sustainable Development Goals,” here’s a detailed plan along with some real-world case studies that can be used:

Week 5 In-Class Activity: Analyzing Case Studies of Data-Driven Sustainable Development Initiatives

Objective

The goal of this activity is to illustrate the practical application of data in informing and shaping public policy, particularly in the context of sustainable development goals (SDGs).

Preparation

Prior to the class, select a range of case studies that cover different SDGs and geographical regions. Provide a brief overview of each case study to the students along with any relevant data or reports.

Case Studies Suggestions

Rwanda’s Use of Data in Healthcare:
- Focus: SDG 3 (Good Health and Well-being)
- Description: How Rwanda has leveraged data to improve healthcare delivery, including the use of electronic health records and mobile health initiatives.
Singapore’s Smart Nation Initiative:
- Focus: SDG 11 (Sustainable Cities and Communities)
- Description: Singapore’s integration of data analytics and IoT technologies in urban planning, transportation, and public services to create a more livable, efficient, and sustainable city.
Kenya’s M-KOPA Solar Project:
- Focus: SDG 7 (Affordable and Clean Energy)
- Description: An innovative pay-as-you-go solar energy system for low-income households, using data to track usage and payments.
Australia’s Murray-Darling Basin Plan:
- Focus: SDG 6 (Clean Water and Sanitation)
- Description: A comprehensive approach to water management in one of Australia’s largest river basins, utilizing data for environmental monitoring and water allocation.
India’s Aadhaar Program:
- Focus: SDG 1 (No Poverty) & SDG 16 (Peace, Justice, and Strong Institutions)
- Description: The world’s largest biometric ID system aimed at providing a digital identity to citizens, improving access to government services and reducing corruption.

In-Class Activity Breakdown

Group Formation and Case Assignment:
- Divide students into small groups and assign each group one of the case studies. Ensure that each group has access to relevant data and reports for their case study.
Analysis and Discussion:
- Instruct each group to analyze their assigned case study focusing on:
  - How data was used in the initiative.
  - The impact of data-driven decisions on policy outcomes.
  - Challenges faced in data collection, analysis, and implementation.
  - Lessons learned and potential applications in other contexts.
Group Presentations:
- Have each group present their findings to the class. Encourage other students to ask questions and offer insights.
Class Discussion:
- Facilitate a class-wide discussion to synthesize learning from all the case studies. Focus on common themes, differences in approaches, and insights into the role of data in sustainable development.

Conclusion

Wrap up the activity by emphasizing the critical role of data in shaping effective public policies and achieving sustainable development goals. Discuss the ethical implications and the need for responsible data use in policy-making.

This activity should provide students with a comprehensive understanding of the real-world application of data in public policy, particularly in the context of sustainable development and societal well-being.

Certainly! Here’s an expanded plan for the in-class activity in Week 1 of your BSc course, centered around the Cambridge Analytica case and focusing on the ethical implications of data collection and usage:

Week 1 In-Class Activity: Exploring the Cambridge Analytica Case

Objective

To understand the ethical considerations in data collection and usage, using the Cambridge Analytica scandal as a case study. This activity aims to highlight the impact of data practices on individuals and society.

Preparation

Provide a brief overview of the Cambridge Analytica scandal, including its background, key events, and outcomes.
Prepare resources for students to refer to during the activity. This could include articles, documentaries, and reports on the case.

Activity Breakdown

Group Formation and Topic Assignment:
- Divide the class into small groups, each focusing on a different aspect of the Cambridge Analytica case. Possible topics include:
  - Data Collection Methods: How data was collected and the ethics of these methods.
  - Data Usage: How the collected data was used, particularly in political campaigns.
  - Impact on Individuals: How individuals were affected, including privacy concerns.
  - Regulatory Response: The legal and political aftermath, including changes in policies or regulations.
  - Technological and Business Implications: How this case affected the tech industry and business practices.
Research and Analysis:
- Allow time for each group to research their assigned topic using the provided resources.
- Each group should analyze their topic, focusing on ethical implications and the broader societal impact.
Group Presentations:
- Have each group present their findings to the class. This should include a summary of their topic, key ethical considerations, and any conclusions or personal perspectives they have formed.
Class Discussion:
- After all presentations, facilitate a class-wide discussion. Encourage students to reflect on the ethical responsibilities of data scientists and technologists.
- Discuss how similar situations can be prevented in the future and the role of regulation and self-governance in the tech industry.
Reflection:
- Conclude the activity by asking students to write a brief reflection on what they learned and how they view the role of ethics in data science.

Conclusion

Wrap up the session by emphasizing the importance of ethical considerations in all aspects of data science. Highlight the need for responsible data handling and the potential consequences of negligence or malicious intent in data practices.

This expanded activity will provide students with a comprehensive understanding of the ethical complexities in data science, using a real-world case that had significant societal impacts. It should foster critical thinking and ethical awareness in future data professionals.

Certainly, the concept of a simulation where students collect and share personal information can be a powerful tool for teaching about the implications of data sharing. Here are a couple of examples of how this idea can be implemented in a classroom setting:

Objective: To simulate the experience of sharing personal information on social media and understand the potential consequences and ethical considerations.

Setup:
- Create a mock social media platform for the classroom or use a controlled, private online group.
- Assign each student a role or persona, complete with background information and interests.
Information Sharing:
- Students interact on this platform, sharing information as per their assigned personas. This can include posting about hobbies, personal interests, or opinions on various topics.
Data Analysis:
- After a period of interaction, reveal that all the shared information has been collected for analysis.
- Conduct an analysis of this data in front of the class, demonstrating how seemingly innocuous information can be used to infer personal details, habits, and preferences.
Discussion:
- Discuss the implications of this data analysis, drawing parallels to real-world social media data collection and usage.
- Highlight issues like targeted advertising, data privacy breaches, and the psychological impact of social media surveillance.

Example 2: Personal Data Trading Game

Objective: To demonstrate the value of personal data in the digital economy and the implications of data sharing and selling.

Game Setup:
- Create a game where students earn points by completing tasks that involve sharing personal data. This can range from basic information (like name and email) to more sensitive data (like phone numbers or personal preferences).
- Include ‘buyers’ in the game, roles played by either the instructor or other students, who offer points in exchange for this data.
Data Collection and Exchange:
- Students engage in this marketplace, making decisions on what data to share and with whom, in exchange for points.
- Introduce scenarios where the shared data is used for different purposes, both positive (like custom service offers) and negative (like data leaks or unwanted marketing).
Debrief and Discussion:
- After the game, discuss the decisions students made and the consequences of those decisions.
- Relate these experiences to real-world data trading practices, discussing ethical considerations, privacy concerns, and the value of personal data.
Reflective Learning:
- Encourage students to reflect on their own data sharing practices online and how the simulation has impacted their views on personal data privacy.

These simulations not only actively engage students in the learning process but also provide tangible experiences that can help them understand the complexities and consequences of data sharing in the digital age.

Finding datasets related to the case studies for Week 5 of your BSc course on “Data in Public Policy and Sustainable Development Goals” can be an excellent way for students to get hands-on experience. However, accessing specific datasets used in these initiatives might be challenging due to privacy, confidentiality, or proprietary reasons. Nevertheless, I can guide you on where to look for similar datasets or related public datasets:

Rwanda’s Use of Data in Healthcare:
- Look for health-related datasets on platforms like the World Health Organization (WHO) or the Global Health Observatory. These might not be specific to Rwanda but can provide insights into healthcare data.
- The Rwanda Ministry of Health or the Rwanda Biomedical Centre might have public health datasets available.
Singapore’s Smart Nation Initiative:
- The Singapore government’s Data.gov.sg offers a wide range of datasets related to urban planning, transportation, and public services.
- Smart Nation Sensor Platform or similar initiatives might have publicly available datasets.
Kenya’s M-KOPA Solar Project:
- While M-KOPA’s specific data might be proprietary, datasets on solar energy adoption in Kenya or general energy usage statistics can be found on energy-related portals like the International Renewable Energy Agency (IRENA) or the World Bank’s World Development Indicators.
Australia’s Murray-Darling Basin Plan:
- The Murray-Darling Basin Authority might have relevant environmental and water management datasets.
- Australian government portals like the Bureau of Meteorology or the Department of Agriculture, Water and the Environment may have related data.
India’s Aadhaar Program:
- Specific data from Aadhaar is unlikely to be publicly available due to privacy concerns. However, the Unique Identification Authority of India (UIDAI) might have some aggregated data or reports.
- Data on Indian government services, demographics, and social programs can be found on India’s Open Government Data (OGD) Platform.

When using these datasets, it’s crucial to be aware of and respect privacy and ethical considerations, especially when dealing with sensitive or personal information. These datasets can be used for analysis and to draw parallels with the case studies, helping students understand the real-world application of data in public policy.

Certainly! Here are some alternative case studies for Week 5 of your BSc course, where related datasets might be more readily available:

1. New York City’s Open Data Initiative

Focus: Urban Planning, Transportation, Public Services

Case Study: Explore how New York City uses its Open Data portal to inform policy decisions, improve city services, and encourage civic engagement.
Datasets: NYC Open Data provides a wealth of datasets on various topics like crime rates, public transportation usage, housing, and environmental data.

2. European Union’s Copernicus Programme

Focus: Environmental Monitoring and Climate Change

Case Study: Analyze how data from the Copernicus Programme is used for environmental monitoring and policy-making in areas like air quality, land use, and climate change.
Datasets: The Copernicus Open Access Hub offers satellite data that can be used for environmental analysis and research.

3. Chicago’s Array of Things (AoT)

Focus: IoT and Urban Sensing

Case Study: Examine how Chicago’s AoT project, a network of interactive, modular sensor boxes, collects real-time data on the city’s environment, infrastructure, and activity.
Datasets: The AoT provides accessible data on temperature, air quality, traffic, and more, useful for understanding urban living conditions and planning.

4. UK Biobank

Focus: Healthcare and Epidemiology

Case Study: Understand how the UK Biobank collects and uses data from 500,000 participants for research in various diseases and health-related issues.
Datasets: While access requires an application and is subject to approval for research purposes, this large-scale biomedical database offers a rich resource for health data analysis.

5. The World Bank’s World Development Indicators (WDI)

Focus: Global Development and Economics

Case Study: Utilize WDI to understand how global development data is used in shaping policies for economic growth, poverty reduction, and sustainable development.
Datasets: The WDI provides a comprehensive set of data on global development, including economic, social, and environmental indicators.

6. UCI Machine Learning Repository

Focus: Various, including Environment, Healthcare, and Social Sciences

Case Study: This repository offers a variety of datasets used in published machine learning papers. Students can explore how these datasets have been used in research and policy-making.
Datasets: The UCI repository contains datasets on a wide range of topics and is a popular source for academic and research purposes.

These case studies not only offer rich and diverse insights into the use of data in public policy but also provide easier access to corresponding datasets. Students can directly interact with these datasets, enhancing their understanding of the practical applications of data in real-world policy-making.

To make the Week 8 in-class activity more hands-on and less theoretical, focusing on the role of social media in social movements like #FridaysForFuture, you can incorporate practical tasks and active analysis. Here’s an expanded version of the activity:

Objective

To provide a hands-on understanding of how social media platforms influence and drive social movements, using #FridaysForFuture as a case study.

Preparation

Gather a variety of resources related to the #FridaysForFuture movement, such as social media posts, hashtags, videos, news articles, and impact reports.
Ensure access to social media analytics tools (like TweetDeck, Social Blade, or Hootsuite) for real-time data analysis.

Activity Breakdown

Introduction and Group Formation:
- Briefly introduce the #FridaysForFuture movement, its origins, and objectives.
- Divide the class into small groups, each focusing on a different aspect of the movement’s social media strategy (e.g., Twitter campaigns, Instagram visuals, Facebook groups).
Data Collection:
- Each group uses social media analytics tools to collect real-time data on their assigned aspect. This includes tracking hashtag usage, engagement rates, follower growth, and the spread of the movement across different regions.
Content Analysis:
- Students analyze the content of posts and messages, looking at factors like messaging strategy, visual elements, and call-to-action phrases.
- Discuss how these elements contributed to the movement’s visibility and engagement.
Impact Assessment:
- Groups assess the impact of social media efforts on the movement’s goals. This might involve looking at rally turnouts, policy changes, public awareness levels, or media coverage.
- Encourage students to compare social media metrics with these real-world impacts.
Group Presentations and Discussion:
- Each group presents their findings, focusing on the effectiveness of different social media strategies and their overall impact.
- Facilitate a discussion on the strengths and weaknesses of social media in driving social movements, drawing on insights from the group presentations.
Real-Time Interaction (Optional):
- If feasible, engage students in a live social media exercise, such as creating a supportive post for the movement or analyzing the movement’s current social media activities.
Reflection and Conclusion:
- Conclude with a reflection session where students share their thoughts on the power and limitations of social media in social advocacy.
- Discuss ethical considerations and the responsibility of digital citizenship in the context of online activism.

This hands-on approach will enable students to actively engage with the material, apply analytical skills to real-world scenarios, and understand the dynamic role of social media in shaping public discourse and driving social change.

Yes, analyzing other movements or initiatives like Extinction Rebellion can provide a diverse perspective on the role of social media in driving social and environmental change. Here’s how you can structure an in-class activity around this:

Objective

To explore how Extinction Rebellion (XR) has utilized social media to mobilize support, spread awareness, and influence public discourse on environmental issues.

Preparation

Gather resources and media related to Extinction Rebellion, including social media posts, campaign videos, and news articles.
Arrange access to social media analytics tools for tracking engagement, reach, and the spread of hashtags and content.

Activity Breakdown

Overview of Extinction Rebellion:
- Begin with a brief introduction to Extinction Rebellion, its goals, tactics, and major campaigns.
- Discuss its unique approach to environmental activism and the role of civil disobedience.
Group Assignment:
- Divide the class into groups, each focusing on different aspects of XR’s social media strategy. For instance, one group might focus on Twitter campaigns, another on Instagram visuals, and another on the use of Facebook for event organization.
Data Collection and Analysis:
- Each group uses social media analytics tools to collect data on XR’s activities on their respective platforms.
- Analyze key elements such as content themes, engagement strategies, frequency of posts, and audience responses.
Comparative Impact Assessment:
- Assess the impact of XR’s social media activities. Look at indicators like growth in followers, engagement rates, and offline activities such as protests or policy discussions triggered by online campaigns.
- Compare the social media strategy of XR with other movements like #FridaysForFuture to understand different approaches and their effectiveness.
Group Presentations and Class Discussion:
- Groups present their findings, focusing on the effectiveness of XR’s social media strategies.
- Engage in a class-wide discussion on the strengths and weaknesses of these approaches, and the ethical considerations involved in XR’s often disruptive methods.
Reflection on Social Media Activism:
- Encourage students to reflect on the role of social media in modern activism. Discuss how digital platforms can be used responsibly and effectively for social and environmental causes.
Current Trends Analysis (Optional):
- If possible, involve the class in a live analysis of current XR social media activities, discussing recent posts, ongoing campaigns, and real-time public engagement.

This activity not only provides insights into the strategies and impacts of environmental movements like Extinction Rebellion but also encourages critical thinking about the use of social media in advocacy and activism. It highlights the power of digital platforms in mobilizing for change while also underscoring the responsibilities that come with such influence.