Using AI in Research

How To

Here's how to effectively use AI for research:

1. Define Your Research Goals: Clearly outline your research objectives and questions. This will guide your AI tool selection and usage. 

2. Choose the Right AI Tools: Select AI tools that align with your specific research needs. Choose tools that provide links to literature.

3. Leverage AI for brainstorming, refining the research question, locating relevant sources, data analysis, and text editing/refining.

4. Verify, Verify, Verify: Be mindful of data quality and potential biases in AI-generated results. Always validate AI output with your knowledge and expertise. 

5. Maintain Human Oversight: Don't rely solely on AI. Human oversight is crucial for ensuring the accuracy, integrity, and validity. 

6. Consider Ethical Implications: Be aware of ethical considerations, such as plagiarism, data privacy, and citing AI-generated content. 

7. Be Mindful of Limitations: AI tools should ONLY be used to augment human research, not replace it. 

By following these guidelines, you can effectively leverage AI to enhance your research process, save time, and improve the quality of your findings. 

AI Search Tools

Read more about specific tools in Chapter 5. AI Tools from Charles Sturt University Library. (2024). Digital Skills: Artificial Intelligence. Charles Sturt University. This chapter introduces a selection of AI tools that can be used in academic study, including Generative AI (GenAI) tools, AI research tools, and AI tools for teaching and learning.

• Elicit is a research assistant that automates parts of your workflow. When you ask it a research question, Elicit will show relevant papers and summaries of key information. Users can read abstracts, filter based on study type, and save and export their work. It is good for evaluating and refining research questions.

• Perplexity is a search engine that summarizes the information available with hyperlinked references (most of which are reputable sources).

• Semantic Scholar provides free, AI-driven search and discovery tools, and open resources with over 200 million academic papers sourced from publisher partnerships, data providers, and web crawls.

• Consensus is an academic research tool that limits its data search to the 200M published papers in Semantic Scholar and uses AI (ChatGPT) claims, methodology, sample size, and more, like a “consensus meter” that estimates the consensus in the published literature.

• Copilot is Microsoft’s version of Perplexity and ChatGPT in one. It can summarize information, brainstorm options, answer questions, provide links to sources, and give feedback on your work.

Data Analysis

• MIT Sloan Teaching & Learning Technologies. (2023). How to Use ChatGPT’s Advanced Data Analysis Feature.

• Philip Adu, Ph.D (2024). (2024). ChatGPT plus Research and Data Analysis [Video Playlist]. YouTube. Includes 

  • ChatGPT in Depth: Exploring AI From A Qualitative Researcher's Lens; 

  • Master Qualitative Data Analysis with ChatGPT: An 18-Minute Guide; and 

  • Mastering Qualitative Data Analysis with GPT-4o: A 40-Minute Comprehensive Crash Course

• Philip Adu, Ph.D (2024). Using AI Tools for Research and Evaluation [Podcast]. YouTube. 

• Philip Adu, Ph.D (2023). Utilizing ChatGPT and Claude AI to analyze your qualitative data [Video]. Youtube. (20:50)