Mitigating Bias in Machine Learning

<p>1 Beyond Algorithmic Bias<br/>1.1 Introduction<br/>1.2 Beyond Ethics in AI<br/>1.3 What Is Algorithmic Justice?<br/>1.4 Definitions of Algorithmic Fairness<br/>1.5 Fairness Metrics<br/>1.6 Methods for Fair Machine Learning<br/>1.7 Tools to Help Detect and Mitigate Bias in Machine Learning Models<br/>1.8 Best Practices to Build a Fairer Application<br/>1.9 Chapter Summary</p><p>2 Going Beyond the Technical: Exploring Ethical and Societal Implications of Machine Learning<br/>2.1 Introduction<br/>2.2 Programming Approaches<br/>2.3 Societal and Cultural Implications of Algorithms<br/>2.4 Ethical Implications of Algorithms<br/>2.5 Approaches to Mitigate Algorithmic Bias<br/>2.6 Speak Up: Communicating Ideas with Digital Storytelling<br/>2.7 Chapter Summary</p><p>3 Social Media and Health Information Dissemination<br/>3.1 Introduction<br/>3.2 MyHealthImpactNetwork: For Students by Students<br/>3.3 Results of Data Inferential Analysis<br/>3.4 Chapter Summary</p><p>4 Comparative Case Study of Fairness Toolkits<br/>4.1 Introduction<br/>4.2 Bias<br/>4.3 Fairness<br/>4.4 Applying Responsible AI<br/>4.5 Results<br/>4.6 What Are the Limitations of These Toolkits?<br/>4.7 Chapter Summary</p><p>5 Bias Mitigation in Hate Speech Detection<br/>5.1 Introduction<br/>5.2 Background<br/>5.3 Bias in Hate Speech Detection Systems<br/>5.4 Bias Mitigation in Hate Speech Detection Using Transfer Learning<br/>5.5 Bias Mitigation in Hate Speech Detection Using Transfer Learning<br/>5.6 Adversarial Methods for Bias Reduction in Hate Speech Detection<br/>5.7 Benefits and Pitfalls<br/>5.8 Other Methods<br/>5.9 Hands-on Exercise<br/>5.10 Chapter Summary</p><p>6 Unveiling Unintended Systematic Biases in Natural Language Processing<br/>6.1 Introduction<br/>6.2 Unfairness and Bias in NLP Applications<br/>6.3 Bias Taxonomy<br/>6.4 Mitigating NLP Bias and Unfairness<br/>6.5 Chapter Summary</p><p>7 Combating Bias in Large Language Models<br/>7.1 Introduction<br/>7.2 Vectorization of Stochastic Parrots<br/>7.3 Natural Language Processing: Linear Decision Making for Nonlinear Language<br/>7.4 Stage One: Data Collection<br/>7.5 Stage Two: Fight Bad Math with Better Math<br/>7.6 Stage Three: Model Constraints/Operations<br/>7.7 Chapter Summary</p><p>8 Recognizing Bias in Medical Machine Learning and AI Models<br/>8.1 Introduction<br/>8.2 Defining Machine Learning<br/>8.3 Building a Simple Machine Learning Model: Use Case<br/>8.4 Health Care Bias and Inequities: Use Case<br/>8.5 Chapter Summary</p><p>9 Toward Rectification of Machine Learning Bias in Health Care<br/>9.1 Introduction<br/>9.2 Case Study: Mitigating Bias in ML for Melanoma<br/>9.3 Defining Types of Biases and Mitigation Techniques in ML Life Cycles<br/>9.4 Machine Learning Fairness<br/>9.5 Chapter Summary</p><p>10 Applying the Wells-DuBois Protocol for Achieving Systemic Equity in Socioecological Systems<br/>10.1 Introduction<br/>10.2 Equity Framework and Tool Application<br/>10.3 Clustering Overview and Application<br/>10.4 Applying the Wells-DuBois Protocol<br/>10.5 Discussion and Future Directions<br/>10.6 Chapter Summary</p><p>11 Community Engagement for Machine Learning<br/>11.1 Introduction: Principles and Components of Community Engagement<br/>11.2 Project Initiation: Steps of Conducting Community-Driven Environmental Data Science<br/>11.3 How to Engage Communities in the Process: Case Study of the Mobile Lead Testing Unit Project in Newark, New Jersey<br/>11.4 Chapter Summary</p>