Part IX: Capstone Projects
Introduction
The three capstone projects in Part IX represent the culmination of this textbook's pedagogical arc. From the foundational epistemology of Part I through the advanced topics of Part VIII, you have built knowledge and developed skills across a wide range of domains: cognitive science, media history, platform economics, misinformation taxonomy, detection methodology, critical thinking, political analysis, intervention design, and AI ethics. The capstone projects give you the opportunity to demonstrate that this knowledge and these skills are genuinely yours — that you can apply them to complex, real-world problems that do not come with pre-specified answers.
Each capstone project is designed as a substantial, multi-week undertaking that integrates material from across the textbook. They are not chapter reviews or comprehension checks. They are the kind of work that professional researchers, journalists, data scientists, and policy analysts actually do. They require you to make decisions, confront ambiguity, encounter failure, revise your approach, and produce work you can stand behind. They are, in short, the closest approximation this textbook can provide to the actual practice of the field.
The Three Projects
Capstone Project 1: Building a Misinformation Detection Pipeline is a data science project that takes students through the full lifecycle of building, evaluating, and critically assessing a machine learning system for classifying news content. Students will collect and label data, engineer features, train multiple models from logistic regression through fine-tuned transformer architectures, evaluate their systems rigorously, and reflect on the ethical dimensions of automated misinformation detection. This project is most directly grounded in the material of Part IV (detection methods) and Part VIII (AI and ethics), but it also requires engagement with Part III's taxonomy of misinformation types (which shapes how you define your classification problem), Part V's critical thinking about evidence quality (applied to evaluating your own system's outputs), and Part VI's awareness of the political stakes of automated content moderation.
Capstone Project 2: Network Analysis of a Real Information Operation applies the social network analysis methods of Chapter 23 to real, publicly available platform transparency data released by Twitter, Meta, and other companies. Students will construct account networks and content similarity networks, apply community detection algorithms, analyze temporal patterns of coordinated activity, and develop an intelligence assessment of the operation's structure, goals, and likely attribution. This project integrates material from Part III (propaganda and state-sponsored disinformation), Part IV (network analysis and bot detection), and Part VI (political dimensions and state-sponsored disinformation), and it requires the evidence evaluation skills of Part V to navigate the ambiguity of attribution analysis.
Capstone Project 3: Designing and Evaluating a Media Literacy Intervention takes students through the research and design process of creating a media literacy curriculum for a specific target audience, grounding every design choice in the theoretical and empirical literature covered in the textbook. Students will conduct a needs assessment, design a five-session curriculum using inoculation theory and constructivist principles, create a rigorous evaluation plan, analyze simulated pre/post intervention data, and produce a professional report suitable for presentation to a school district, community organization, or foundation. This project integrates material from Part I (cognitive science of belief), Part V (media literacy frameworks), Part VII (education interventions and prebunking), and Part VIII (ethics of epistemic intervention).
Choosing Your Project
Unless your instructor specifies otherwise, you should select the capstone project that best aligns with your existing skills, academic background, and professional aspirations. Project 1 is most appropriate for students with programming experience in Python and an interest in data science or computational social science. Project 2 requires Python programming and will be particularly rewarding for students interested in investigative journalism, national security, or platform policy. Project 3 is most appropriate for students in education, communication, public health, or policy fields, though it also includes a quantitative data analysis component using Python.
That said, we encourage ambitious students to tackle a project that stretches beyond their comfort zone. Project 1 provides extensive code scaffolding that makes it accessible to students with limited prior programming experience who are willing to invest the learning time. Project 3's quantitative component is designed to be approachable for students without a statistics background. The capstone projects are learning experiences, not auditions — the goal is growth, not flawless performance.
How to Approach the Capstone Projects
Each project is structured in phases, with clear deliverables at each phase. We strongly recommend submitting work phase by phase and seeking feedback before proceeding rather than completing all phases and submitting at the end. The phases are designed so that early work builds the foundation for later work; errors in early phases, if uncorrected, will compound.
Approach each project with intellectual honesty. You will encounter situations where your data do not support the conclusion you expected, where your model performs worse than you hoped, where your curriculum design has gaps you did not anticipate, or where the evidence you find about an information operation is ambiguous. These moments are not failures — they are the most valuable learning experiences in the project. The temptation to paper over negative results or to overstate the certainty of your findings is a real temptation that professional researchers face constantly. Resisting it is part of what it means to do rigorous work.
Each project includes a detailed grading rubric. Read the rubric before you begin, consult it as you work, and use it to evaluate your own work before submitting. The rubrics reward not just technical correctness but intellectual honesty, quality of reasoning, depth of engagement with the relevant literature, and clarity of communication.
What These Projects Demonstrate
Successfully completing a capstone project from this textbook demonstrates something that is valuable and increasingly rare: the capacity to engage with the problem of misinformation rigorously, practically, and ethically. The labor market for people with this combination of skills is substantial and growing. Fact-checking organizations, platform trust-and-safety teams, investigative journalism outlets, academic research groups, government intelligence and policy offices, nonprofits focused on media literacy education, and technology companies developing content moderation systems all need people who can think carefully about these problems and act effectively on that thinking.
Beyond the labor market, the skills these projects develop make you a more effective citizen, a more reliable source of information in your community, and a more thoughtful participant in the collective epistemic project of democratic society. Those outcomes are less measurable than employment but no less important. That is, ultimately, why this textbook exists.
The pages that follow contain the three capstone project specifications in their full detail. Read them carefully, ask questions early, start sooner than you think you need to, and do work you are genuinely proud of. The problem of misinformation in the digital age is one of the defining intellectual and civic challenges of the present moment. Your engagement with it matters.