Generative AI in Psychological Research: Course Overview
This course explores the transformative impact of generative AI technologies on psychological research methods. Below is an overview of the complete lecture series, organized into three comprehensive modules.
Module 1: Foundations of AI in Psychology
Lecture 01.1 – Introduction to Generative AI in Psychology
Overview of generative AI capabilities relevant to psychological research
Evolution from traditional to AI-augmented research methodologies
The spectrum of LLM applications in psychology
Key ethical and methodological considerations
Case study: The emergence of “Silicon Samples”
Lecture 01.2 – Survey Design with Large Language Models
Traditional challenges in survey design
How LLMs can enhance question generation and refinement
Response scale optimization using AI
Bias detection and cultural adaptation
Practical implementation through human-AI collaboration
Optimizing LLM prompts for survey design
Case example: Developing a Likert-scale measure of climate anxiety
Lecture 01.3 – Synthetic Respondents: Simulation and Supplementation
The promise of synthetic respondents for data generation
Empirical findings on synthetic respondent fidelity
Technical artifacts vs. true understanding in LLM responses
Appropriate use cases and critical limitations
Case study: Depression prediction from synthetic clinical interviews
Best practices for working with synthetic respondents
Module 2: AI-Driven Data Collection
Lecture 02.1 – Interactive AI Surveys
The promise of conversational AI surveys
Adaptive questioning and improved engagement
Empirical evidence on AI interview effectiveness
Implementation considerations for conversation design
Case study: An AI-driven mental health assessment
Ethical considerations for interactive AI surveys
Future directions in AI-driven data collection
Lecture 02.2 – Privacy Considerations
Understanding the privacy landscape in psychological research
Comparison of closed API LLMs vs. open-source models
Performance vs. privacy trade-offs
Practical privacy preservation strategies
Hybrid approaches to balance capability and privacy
Documentation and transparency requirements
Case study: Privacy-preserving clinical assessment
Lecture 02.3 – Additional Privacy Considerations
Understanding privacy regulations (GDPR, HIPAA)
IRB requirements and obtaining informed consent
Data minimization and anonymization techniques
Privacy-preserving model deployment options
Synthetic data approaches for confidentiality
Lecture 02.4 – BFITraitTalk_AI Tutorial
Overview: A working prototype that delivers the Big Five Inventory via a conversational AI interviewer
Installation and setup: Running a local LLM for privacy-preserving surveys
Codebase walkthrough: Flask app architecture and component interactions
LLM integration: Using Gemma 3 for natural language understanding
Survey logic: Managing the adaptive conversation flow
Backend structure: Data flow and state management
Psychological design considerations: Balancing conversational engagement with measurement validity
Ethical considerations: Privacy, transparency, and participant experience
Customization and extension ideas: Adapting the framework for other survey types