Academics & Research – UW Graduate School Skip to content

Advice Category: Academics & Research

Effective and Responsible Use of AI in Research 

Effective and Responsible Use of AI in Research Guidance for Performing Graduate Research and in Writing Dissertations, Theses, and Manuscripts for Publications 

[lifted in its entirety from Georgia Tech (Georgia Institute of Technology), and revised in response to feedback from the UW Graduate School Council and key stakeholders across all three UW campuses[1],[2]]

The use of artificial intelligence has expanded greatly in recent years to all sectors of society. Generative AI and Large Language Models, like ChatGPT®, Microsoft Co–Pilot®, and Google Gemini® are rapidly becoming available, expanding access to this technology for use by anyone who is digitally literate.     

These tools can be used effectively in conducting research, and this guidance document is developed to assist researchers, especially graduate students, in this purpose. The guidelines presented here are recommendations only and will evolve with the rapidly changing landscape of AI.[2]

AI tools will also impact your teaching. While some of the guidance below will be relevant to your work as a scholar, please also visit this page from the Center for Teaching and Learning to learn more about AI+Teaching

Some questions that guide the discussion are as follows: 

  • What are potential equity impacts and implications for generative AI use? What are ways to reduce unintended impacts that may perpetuate equity gaps? What other ethical considerations should be considered about responsible AI use?
  • How can students use AI effectively as a tool to help generate research ideas and approaches? 
  • How can students use AI effectively as a writing or editing tool for publications and their thesis? 
  • How accurate are the results from an AI source? 
  • How confidential is the process? Is a student giving away valuable ideas or research results to an open platform (like ChatGPT) before the topic is peer reviewed and published?  Will you lose your intellectual property rights, such as patents? 
  • How can students improve their skills in using AI as a tool in research?
  • How might using AI affect the student’s development of personal knowledge and skills?
  • Are students at risk of committing research misconduct in the form of plagiarism if they use a generative AI platform to write parts of their thesis? 
  • How can students (and other researchers) transparently indicate within their written works the contribution of generative AI or other assistive technologies? 
  • What restrictions do professional societies and publishers place on the use of AI in publications and in reviewing papers or proposals?

ChatGPT® was asked similar questions, and both questions and the generated responses are given in the Appendix. Note that ChatGPT® has the following disclaimer: 

“While we have safeguards in place, the system may occasionally generate incorrect or misleading information and produce offensive or biased content. It is not intended to give advice.”

Strengths of Large Language Models and Generative AI

  • It can sort through a large amount of information quickly to synthesize content from that information.   
  • It can summarize existing information that is freely available and not behind firewalls or paywalls and is neither too old nor too recent. For example, it can summarize existing methodologies in a particular research area or positions on a topic. 
  • It may help improve the communication skills of non-native speakers. 

Challenges for AI

  • Current algorithms can summarize but do not necessarily generate accurate, unbiased, and dependable new or creative ideas.  
  • The quality of the output depends on the algorithmic approach, the quality of the training data, and the user’s understanding of the tools’ limitations and biases as they write queries.  Though the content generated may sound very plausible, it may be inaccurate such as including non-existent publications or incorrect citations of publications. There are many companies that provide generative AI platforms, and the quality is mixed. 
  • AI tools are better at summarizing information than retrieving it. Using these tools as search engines will likely result in biased results.
  • People are prone to biases in their work, and AI can pick up those biases from the training data and even amplify them or introduce its own. 
  • Confidentiality or security of data voluntarily input to a Large Language Model by users depends on the policies and practices of the company that owns that platform. For preciseness, these terms should be accessed outside of the AI platform, rather than prompt the AI platform for these terms. For your own security and confidentiality of your data, it is more prudent to assume that whatever is fed into a query is owned by that company.    

Use of AI in Graduate Student Research

Creating new knowledge and performing research is at the highest level of the educational experience of students.  Novice researchers must learn essential critical thinking skills needed in formulating a research idea, determining appropriate methods and approaches for the research plan, collecting data, summarizing results, and drawing conclusions. AI can be a valuable tool for assistance but is not an accountable entity for the research outcomes since the ultimate responsibility of research lies with the human.  

Your program, instructor, or advisor may have provided specific expectations around the use of AI in your research. As you consider the use highlighted below, ensure that you are honoring their expectations and any agreements/attestations you have made with them. There may be serious consequences for breaking academic agreements. UW’s Academic Misconduct Policy can be found here.

Guidance on the Use of Generative AI in Generating Research Ideas or Approaches

  • Brainstorming: You can use the AI tool as a brainstorming partner, where you exchange ideas whether the AI prompts you or you prompt the AI for ideas. Brainstorming is an iterative process that can be made more effective with the way that the queries are posted. For more samples or information, post this query: “How can I use AI to help me to brainstorm an idea?” 
  • Surveying Existing Approaches: Large Language Models, if trained broadly in a topic, can give an initial overview of existing approaches or existing literature on a topic.  Current research sources such as library or professional society databases are more reliable in terms of accuracy of peer-reviewed content. See the Rutgers University Library site for guidance and AI platforms for searching research databases. 
  • Prompt engineering is important: Practice the prompts used for Generative AI.  The value of the response depends on the value of the prompt. If you provide a low quality or vague prompt, you will get vague results. Critical thinking skills may be enhanced by learning how to iterate on the prompts to refine results or to use the material gathered from one result to identify new avenues of inquiry to pursue.  Examples of strategies for prompt engineering are found in the OpenAI Guide and in Ivan Allen article on prompt engineering.

Advice on Usage

  • Be very skeptical of the results and be sure to do your due diligence in fact-checking information. Do not trust any outputs that you do not evaluate yourself or trace back to original credible sources.  There are many stories of generative AI giving citations of articles that do not exist (see the article in the Chronicles of Higher Education by Hicks referenced below). 
  • Be scientific with your prompts (or queries): Prompting is not deterministic, so the same prompt at a different time may result in a different response. Small changes in the wording of the prompt may yield very different responses. Keep records, make small changes and see how it affects the outcome, etc. 
  • Don’t share any data or information that is confidential, proprietary, or have IP implications.  Your uploaded data or ideas might be incorporated into the learning model to be available for others in your research area, prior to you having a chance to publish it. If you intend to pursue commercialization or other Intellectual Property avenues for your work, putting the information into an open AI platform may be considered as disclosure. 

Guidance on the Use of Generative AI in Writing Publications or Theses

  • Editorial assistance: Using an AI platform for a grammar check and for editorial improvements is similar to having a person proofread a paper or essay and generally does not require acknowledgement.  An example of an AI editorial tool is Grammarly. Depending on the AI platform, keep in mind that what is intended only as a grammar check may inevitably put your ideas into a system over which you don’t have control.
  • Using AI may produce content that sounds good but would not withstand scrutiny by experts, including, for example, your thesis reading committee and peer reviewers. 
  • Substantive Generative AI assistance: Using an AI to write a portion of a dissertation or paper may constitute cheating and/or plagiarism.  
    • From language on Academic Misconduct from the Office of Community Standards and Student Conduct:
      • Artificial Intelligence (AI) content generators, such as ChatGPT, present opportunities that can contribute to your learning and academic work. However, using these technologies may also violate the academic standards of the University.
    • From the Student Conduct Code 209.7.C
      • Academic Misconduct Includes: “Cheating,” which includes, but is not limited to: The use of unauthorized assistance in taking quizzes, tests, or examinations, or completing assignments;
      • Plagiarism includes, but is not limited to: a. The use, by paraphrase or direct quotation, of the published or unpublished work of another person without full and clear acknowledgment; or b. The unacknowledged use of materials prepared by another person or acquired from an entity engaging in the selling of term papers or other academic materials.
      • Academic Misconduct Includes: Unauthorized collaboration.
    • Given the mention of assistance from AI in the discussion of plagiarism section Academic Misconduct Policy, is it ever ok to use an AI source in brainstorming or otherwise to help generate research ideas?  How does this compare to brainstorming ideas with human collaborators? Consider, for example, brainstorming done among human colleagues that results in research that is published. The contribution of the collaborators, if substantial, may result in an acknowledgement in the manuscript or authorship.  AI brainstorming can be treated similarly, to an extent. An AI session that resulted in novel ideas may be recognized in the published work, but authorship is more controversial. Sample guidelines of authorship are given in the section on Professional Societies and Publishers below. Note that all of these guidelines require that an author approve the final manuscript and be held accountable for the content. Both of these requirements would be difficult for an AI agent to fulfil in order to receive authorship recognition.

More Advice on Usage

  • Understand the AI policies for publications prior to submission: A professional society may have specific restrictions on the use of AI in the writing of a publication to be submitted and reviewed.  Make sure that you understand and abide by those restrictions before submission.  For example,
    • Generally, authors are responsible for the content of their submissions, regardless of whether they used generative AI or not.  So, authors would be responsible for errors in AI-generated content. 
  • Some publishers require full transparency and credit for the source of AI-ideas in the manuscript.  
  • Preserve confidentiality of the information: any information that you upload into a Large Language Model may become part of that model’s data and, as a result, be used to form responses to another person’s inquiries on that topic. If your paper has not yet been submitted for peer review, then you may decide to seek AI editing help only on smaller sections of the paper that don’t contain new research content.  In some cases, you may be able to opt out of your information being included in the training data.   
  • Don’t short circuit the learning process: For a graduate student, an important part of their learning processes is to gain skills on analyzing, summarizing, and discussing their research results. Inputting data into a generative AI platform and asking it to write this type of content does not give the student the experience to gain those skills Putting aside the confidentiality risk mentioned above and publishers’ restrictions, hypothetically, a researcher could ask the generative AI platform to outline a discussion points in order to gain ideas as a first step in doing their own analysis and write-up.  The researcher should be aware of the limitations and possible consequences of that action. 

Act ethically

The responsible conduct of research includes a number of practices that should be considered when using AI to assist in performing research: 

  • Authorship: Only include material in your writing that you or a co-author wrote or that you can cite from primary sources.  Note also that there is no guarantee that an AI-generated response does not include passages verbatim from other sources, so quoting an AI-generated response may crossover to traditional plagiarism. 
  • Falsification or fabrication of data: There is no guarantee that Generative AI will produce accurate results or that it will not create new false data.   
  • Responsible collection and management of data: There are ethical standards on the treatments of research subjects and their data that must be upheld. For example, you would not upload sensitive data to an open AI platform.   There’s room also to reference the question of whether use of AI generated content is ever ethical by bringing up awareness of whether authors of the training data opted in, etc.  
  • Awareness of the tools you’re using: make sure you’re aware of their terms of service, where it obtained its data, and how it will use the information you put into it. 

Sample Guidance from Professional Societies, Publishers, and Funding Agencies 

Using AI in Reviewing Proposals and Papers

As a reviewer, you generally need to attest to confidentiality of the information that you are to review, especially not sharing the information with others.  Publishers and funding agencies are starting to put restrictions on the use of AI in the review process. For example,  

“NIH prohibits NIH scientific peer reviewers from using natural language processors, large language models, or other generative Artificial Intelligence (AI) technologies for analyzing and formulating peer review critiques for grant applications and R&D contract proposals.” 

From NIH NOT-OD-23-149

Authorship and AI: 

Below are several links to authorship guidelines from societies and publishers. The additional guidelines on authorship listed below have a common element: an author is responsible for the content of their work. So, it would not be acceptable for an author to excuse inaccuracies in their published results as “AI wrote it.”  

Cited and Additional References and Resources 

Sample policies and guidance at other universities

Appendix A: Questions input to ChatGPT and CoPilot and the corresponding AI generated answers.  (The UW Graduate School added sections 2,4,6 to provide an example of the variability of output received from the same question)

“How should I use ChatGPT in doing research” (dated July 12, 2023)

Response: When using ChatGPT for research, here are some general guidelines to keep in mind:
1.     Clearly define your research question: Clearly articulate the specific topic or problem you are investigating. This will help you communicate your needs more effectively to ChatGPT and get relevant responses. 
Break down complex questions: If you have a complex research question, consider breaking it down into smaller sub-questions. This can make it easier to handle and analyze the information provided by ChatGPT. 
3.     Provide context and background information: When asking a question, provide relevant context and any necessary background information. This will help ChatGPT better understand your query and provide more accurate responses. 
4.     Evaluate and validate information: Remember that ChatGPT generates responses based on patterns it has learned from training data. While it can provide useful insights, it’s important to critically evaluate and validate the information it provides. Cross-reference the responses with reliable sources and use ChatGPT as a tool to complement your research, rather than relying solely on it. 
5.     Ask for sources and citations: When requesting information from ChatGPT, explicitly ask for sources or citations whenever applicable. Although ChatGPT doesn’t have direct access to external sources, it can still provide general references or suggest search terms to help you find relevant information. 
6.     Experiment with prompts and iterations: Experiment with different phrasings and prompts to refine your questions and get more precise responses. Iterate on your queries to narrow down the scope or explore different angles of your research topic. 
7.     Exercise critical thinking: While ChatGPT can provide helpful suggestions and insights, it’s crucial to apply critical thinking skills to evaluate the quality and reliability of the information. Verify facts, check for bias, and consider multiple perspectives. 
8.     Supplement with external research tools: Utilize external research tools and resources alongside ChatGPT. Online databases, academic journals, search engines, and domain-specific resources can provide additional information and help validate the insights gained from ChatGPT. 
9.     Be aware of limitations: Remember that ChatGPT has limitations. It may generate plausible sounding but incorrect or misleading information. Be cautious when dealing with sensitive or controversial topics and verify information from reliable sources. 
10.  Provide feedback: If you encounter errors or inaccuracies in ChatGPT’s responses, provide feedback to OpenAI. This helps them improve the model and provide more reliable information in the future.
Overall, ChatGPT can be a valuable tool for research, but it’s important to use it as part of a broader research process that includes critical thinking, validation, and utilization of other reliable resources. 

“How should I use CoPilot in doing research” (dated November 27, 2024)

Using Copilot for research can be incredibly efficient and helpful! Here are some steps to get you started:

  1. Define Your Research Topic: Clearly outline what you want to research. This helps in asking precise questions.
  2. Ask Specific Questions: Break down your topic into specific questions. For example, instead of asking “Tell me about climate change,” you could ask “What are the main causes of climate change?”
  3. Use Web Search: If you need the latest information or specific data, ask me to perform a web search. I can find up-to-date articles, studies, and reports.
  4. Summarize Information: I can help summarize lengthy articles or papers, making it easier for you to grasp the main points quickly.
  5. Organize Your Findings: I can assist in organizing your research into categories or outlines, which can be very useful for writing reports or papers.
  6. Check Facts: If you need to verify information, I can cross-check facts from multiple sources.
  7. Generate Ideas: If you’re stuck, I can help brainstorm ideas or provide different perspectives on your topic.

“How can I use ChatGPT in writing a dissertation?” 

Response: Using ChatGPT as a tool to assist you in writing your dissertation can be beneficial in several ways. Here are some steps you can follow to effectively incorporate ChatGPT into your dissertation writing process:
1.     Familiarize yourself with the tool: Spend some time exploring and experimenting with ChatGPT to understand its capabilities, limitations, and prompts it responds well to. This will help you maximize its utility during the dissertation writing process. 
2.     Identify specific areas where ChatGPT can be helpful: Consider the sections or topics in your dissertation where ChatGPT can provide valuable insights, generate ideas, or help you refine your arguments. For example, you can use it to brainstorm ideas, ask for alternative perspectives, seek clarification on complex concepts, or request suggestions for references.
3.     Craft clear and specific prompts: When interacting with ChatGPT, provide detailed and precise prompts to get the most relevant responses. Clearly specify the information or assistance you are seeking to ensure ChatGPT understands your requirements accurately. 
4.     Use ChatGPT for idea generation and expansion: If you’re experiencing writer’s block or need help generating ideas, ChatGPT can serve as a valuable resource. Ask it open-ended questions about your topic or specific aspects you’re exploring, and let it provide insights or alternative perspectives that can stimulate your thinking. 
5.     Verify and fact-check responses: While ChatGPT can generate creative and thought-provoking responses, it’s essential to remember that it may also produce inaccurate or unreliable information. Always verify the responses provided by ChatGPT by cross-referencing them with credible sources and academic literature.
6.     Employ critical thinking and synthesis: As you receive responses from ChatGPT, critically evaluate and analyze the information. Assess the relevance, validity, and coherence of the generated content. Incorporate the insights provided by ChatGPT into your writing only after careful consideration and integration with your existing knowledge and research. 
7.     Maintain academic integrity: While ChatGPT can be a valuable tool, it’s crucial to acknowledge its role and limitations. Clearly distinguish the content generated by ChatGPT from your original work, giving appropriate credit to the tool when necessary. Ensure that your use of ChatGPT aligns with your institution’s guidelines on academic integrity and plagiarism. 
8.     Seek human feedback and guidance: While ChatGPT can provide assistance, it’s important to remember that it’s an AI language model and not a substitute for human expertise. Engage with your advisor, professors, or peers to receive feedback, guidance, and suggestions on your dissertation. They can provide valuable insights, offer constructive criticism, and help you refine your arguments.
By following these steps, you can effectively utilize ChatGPT as a supportive tool throughout your dissertation writing process. Remember to balance its assistance with your own critical thinking and scholarly efforts to produce a well-researched and original piece of academic work. 

“How can I use CoPilot in writing a dissertation?  (dated November 27, 2024)

Writing a dissertation is a significant undertaking, and Copilot can be a valuable tool throughout the process. Here’s how you can leverage Copilot effectively:

  1. Topic Selection:
    • Brainstorm Ideas: I can help you brainstorm potential topics based on your interests and field of study.
    • Narrow Down: Once you have a broad topic, I can assist in narrowing it down to a specific research question or hypothesis.
  2. Literature Review:
    • Find Sources: I can help you locate relevant academic papers, articles, and books.
    • Summarize: I can summarize key points from these sources to help you understand the existing research landscape.
    • Organize: I can assist in organizing your literature review by themes or chronological order.
  3. Research Design:
    • Methodology: I can provide information on different research methodologies and help you choose the most appropriate one for your study.
    • Data Collection: I can suggest data collection techniques and tools.
  4. Writing:
    • Outline: I can help you create a detailed outline for your dissertation.
    • Drafting: I can assist in drafting sections of your dissertation, ensuring clarity and coherence.
    • Editing: I can help with editing and proofreading to improve the quality of your writing.
  5. Data Analysis:
    • Statistical Analysis: I can provide guidance on statistical methods and help interpret your data.
    • Visualization: I can suggest ways to visualize your data effectively using charts and graphs.
  6. Citations and References:
    • Formatting: I can help format your citations and references according to the required style guide (e.g., APA, MLA, Chicago).
    • Managing Sources: I can assist in organizing and managing your bibliography.
  7. Final Review:
    • Feedback: I can help you incorporate feedback from your advisor or peers.
    • Polishing: I can assist in the final polishing of your dissertation to ensure it is ready for submission.
  8. The best way to determine confidentiality of data or information that you voluntarily input into a platform is to examine the terms and conditions of the platform, accessed outside of the model.  For curiosity, the following question was entered in ChatGPT (highlight added later for emphasis):  

“If I shared data with ChatGPT during a conversation, will that data be shared with others?” 

Response: As of my knowledge cutoff in September 2021, as an AI language model, I don’t have the ability to store conversations or share information with others. I can only provide responses based on the input given to me during the current session. However, please note that while I don’t store the conversations, OpenAI may collect and store conversations for research and improvement purposes, but they are generally anonymized and stripped of personally identifiable information. 
It’s always a good practice to avoid sharing sensitive or personally identifiable information while interacting with AI systems.
If you have any concerns about privacy or data security, I recommend reviewing the privacy policy or terms of service of the platform or application you are using to access ChatGPT, as they may provide more specific information on how your data is handled.

If I shared data with Co-Pilot during a conversation, will that data be shared with others? (dated November 27, 2024)

No, any data you share with me during our conversation is not shared with others. Your privacy and confidentiality are very important. The information you provide is used solely to assist you during our interaction and is not stored or shared with third parties. If you have any concerns about privacy or data security, feel free to ask! How can I assist you further?

Appendix B. An incomplete list of 20 AI tools for research and writing, generated by CoPilot;

Here’s the updated list of 20 AI tools that are particularly useful for writing and research, including Gemini:

  1. Elephas: Summarizes research papers, rewrites content in various tones, and organizes your research in a central “Super Brain” for easy access.
  2. ChatGPT: Summarizes news articles and answers research questions.
  3. Typeset.io: Streamlines academic writing with templates and citation management.
  4. Quillbot: Paraphrases text and summarizes complex materials for research.
  5. Wordvice.ai: Ensures clarity, grammar, and originality in your academic writing.
  6. Consensus AI: Searches vast databases and filters research papers for quality.
  7. Scite.ai: Provides real citations and measures the credibility of research claims.
  8. Scholarcy: Summarizes complex articles and builds a searchable research library.
  9. ProofHub: Manages research projects with tasks, collaboration tools, and scheduling.
  10. Research Rabbit: Builds a research library and recommends new papers.
  11. Grammarly: Checks grammar, punctuation, and style, and offers suggestions for clarity and conciseness.
  12. CoPilot: Assists with code writing, debugging, and documentation, making it useful for technical research.
  13. Gemini: Provides insights and analytics for research data, helping to visualize and interpret results.
  14. Elicit: Uses semantic search to find relevant literature and answer research questions.
  15. SciSpace: Conducts literature reviews through advanced semantic search capabilities.
  16. PaperPal: Streamlines academic writing and journal submission with integration into Microsoft Word.
  17. ExplainPaper: Helps users understand complex language in peer-reviewed papers.
  18. Julius AI: Simplifies data analysis and visualization for research.
  19. Writefull: Provides language feedback and suggestions for academic writing.
  20. EndNote: Manages references and citations, making it easier to organize research sources.

[1] This content was gathered from experts at Georgia Tech in the areas of AI, in ethics, and in graduate education and edited by Bonnie Ferri. Specific groups of contributors include: Office of Graduate Education, Graduate Student Government Association, Office of Research, Responsible Conduct of Research Office, and Directors of Graduate Programs. 

[2] The current version of this document is dated December 10, 2024. For suggested modifications to the content, contact the Graduate School Office of Academic Affairs at gsacad@uw.edu.

 

Getting Started in a Lab

If you are a new graduate student in the sciences, you will rotate through several labs during your first year at the University of Washington. Your challenge is to find the right lab for you — one that best matches your intellectual interests and that helps prepare you for your career.

How to get started in a lab

  • Sample a range of lab environments and cultures. Find a lab that will help you develop as a researcher.

Find out what the ground rules and expectations are.

  • How many hours are you expected to be in the lab? (Remember that research is not a 9 to 5 job; you should look forward to hanging out in the lab—but also make sure you know specific expectations for your time).
  • What’s the definition of “progress” in lab work? What’s the definition of progress in graduate work in your discipline?

Look for opportunities that will benefit your career.

  • Will you have an opportunity to publish?
  • Will you get credit—as an author, co-author—for the work you do in the lab? Will your intellectual work really be your own? Seek a lab that gives ownership of your ideas to you.
  • Will you have a chance to push beyond the boundaries of particular grants?
  • Will you be able to collaborate with other labs?

Be smart.

  • The best lab is not necessarily the one that pays the most.
  • Success is not always about being comfortable— so look for a lab where you will be pushed a bit.

How to evaluate labs

Both established and new labs have great merit.

  • In an established lab, find out: What’s the lab’s track record? Where have people ended up working after their lab experience?
  • Recognize that some younger faculty—who do not have well established labs and therefore do not have the same track record as established labs—often bring the newest ideas to the discipline and are often willing to spend time with graduate students. Such labs might be a better place to try new things.
  • Where do people in the lab publish? In top-tier journals?
  • Ask other students about the labs.
  • Trust your instincts.

Be clear about your own expectations for mentorship in a lab.

  • How often would you like to meet with faculty mentors? (Make sure that the time you request is for the most pressing matters; don’t waste time on minor details that you can find out elsewhere).
  • Can you get on the mentor’s calendar? (Ask other graduate students in the lab about the nature and extent of mentorship).

Make good use of your lab work: Publish early and publish often.

  • Publications are the currency of success.
  • Publications are a guaranteed path to a relatively carefree thesis preparation.

How to succeed in a lab

  • Participation is the key to any successful lab. A successful lab draws on a variety of skills, so contribute.
  • Recognize that a good lab is one with mutual mentorship; that means you need to contribute, too. As a first-year student, you may well have expertise that others in the lab don’t have. Be a good citizen; contribute the work. Recognize that you have the potential to be a valuable contributor from the very first day you walk in the door.
  • Learn from others and support others in the lab. Recognize the expertise of all of your lab colleagues (faculty, visiting scientists, postdocs, graduate students, undergraduates, and even high school students).
  • During your first year, complete at least one research paper.

by Tom Daniel, professor, Biology

Succeeding in a Graduate Seminar

Some of your most important and impression-forming interactions with your classmates and professors occur in graduate seminars. Your stellar performance in graduate seminars is paramount to your success in the graduate program. Graduate seminars are the building blocks for your knowledge in the field and in graduate school.

How to succeed in a graduate seminar

Prepare for class

Do the reading. All of it. But don’t stop there. Annotate your reading. Ask questions of the text in the margins. Maybe even type up your notes. Always consider what’s at stake in the reading, how the reading informs your understanding of the class themes, other course materials, the methods, the content. How does the reading relate to your own burgeoning research questions?

Come to class with questions and discussion points. If you are reticent about speaking in class, recruit a friend to chat about your ideas for five minutes the day before class. Do not, however, memorize one point in the reading so that you make your one perfunctory comment in class. Everyone is on to that game!

In class

Do your part to help foster community. This means: Listen. Participate fully. Be respectful.

Showcase your intellectual curiosity by engaging with all types of ideas, not just the ones in your designated area of study.

When you speak, remember to look at your classmates, not exclusively at the professor.

Use your breadth of knowledge — connect the readings to other readings in your class and other out-of-class readings. Feel free to apply the readings or theme of the day to your project, but don’t be so focused on utilitarian knowledge that you fail to engage fully with all of the issues at hand.

Do not fall into the trap of wholesale skewering the reading of the week. This is intellectually lazy. The work must have some redeeming value if the professor has chosen to assign it. Even if you want to make a serious critique of the reading you should attempt to articulate its contributions/interventions as well as limitations.

Writing

Turn in all writing assignments on time. Do not save your seminar papers for the last week of class. Begin generating ideas the first week of class. Talk about your ideas with your classmates and your professor. If the professor has not given you a series of deadlines, create deadlines for yourself (i.e., identify paper topic in the third week of class, generate working bibliography in the fourth week of class, create abstract in the fifth week, write your first draft in the sixth week, etc.).

Graduate seminars are your first practice attempts at being a scholar. It should be fun to engage with ideas. Be prepared to spar respectfully — and always be prepared!

by Ralina Joseph, professor, Communication

Forming an Interdisciplinary Dissertation Committee

Doctoral students in interdisciplinary programs face unique challenges in forming dissertation committees. Based on our experience as directors of three such programs (Public Health Genetics, Urban Design and Planning, and Astrobiology), we offer the following suggestions.

Your first challenge

Find the optimal set of members — especially the right chair (or two co-chairs) for your committee. Committee members need to:

  • be the best match for your intellectual interests
  • have the expertise to help you succeed in designing and completing your dissertation
  • be able to help you prepare for your career

In planning for a dissertation, you should consult extensively with faculty members in your program for guidance about:

  • potential research questions
  • planning/timing methodology
  • potential committee members

The role of the committee

The final decision about the appropriate content of your project rests with the dissertation supervisory committee. You should work closely with the committee (especially the chair) to determine your project’s scope and content. The committee will guide your research and should meet regularly with you. Being sure you and your committee agree on what is meant by “regular” meetings is also a good idea. You may find it useful to meet individually with the members and obtain their feedback at several stages of your dissertation process. The interdisciplinary nature of your work may require that feedback at an advanced stage of your dissertation will be provided by the committee in an integrated form. You may want to discuss with your chair how the committee could produce a collective memo integrating their shared feedback.

The composition of dissertation committees

The dissertation supervisory committee must have at least four members, including the chair and the Graduate School representative (GSR). At least three committee members (including the chair and the GSR) must be UW graduate faculty members with an endorsement to chair doctoral committees; a majority of your committee members must be graduate faculty members, identifiable through the Graduate Faculty Locator.

Committee members should include faculty expertise in your dissertation’s core fields. You might consider having five members, especially if your project involves different disciplines requiring advice and guidance in all areas. Four committee members must attend general and final exams — so having five on your committee provides flexibility if one member cannot attend. However, having more than four committee members may make it more difficult for them to find time to work together.

Selecting a Graduate School representative

You must select the Graduate School representative for your committee by consulting with your chair, other committee members, and/or program directors. The GSR votes and represents the interests of the Graduate School. GSR requirements:

  • be a graduate faculty member
  • have an endorsement to chair doctoral committees
  • no conflict of interest with you or your committee chair

Also, the GSR may not have an official faculty appointment within your committee chair’s department(s) or the department in which your program is housed. This can be challenging for students in interdisciplinary programs. Exceptions to this rule can be made, with appropriate justification, by petition to the dean of the Graduate School.

by Professor Emeritus Melissa Austin, Public Health Genetics; Marina Alberti, professor, Urban Design and Planning; and Woody Sullivan, professor, Astrobiology

What You Need to Know about Human Subjects and Animal Subjects for Dissertations

Research involving animals or humans is an essential component of many dissertation research projects. Knowing how to comply with regulations governing human and animal research is critically important to many graduate students. These regulations enhance academic integrity while also protecting research subjects.

The first step: Be advised of compliance mandates

The Graduate School requires submission of a completed “Use of Human and Animal Subjects for UW Graduate Student Theses and Dissertations” form to ensure that students have been advised about the need to comply with UW requirements for research before beginning their dissertation research. These compliance mandates are from the UW Human Subjects Division and Institutional Animal Care Use Committee. The form must be signed by both the dissertation committee chair and the student, and must be kept on file by your program.

Factoring timelines into your planning

In developing timelines for dissertation completion and graduation, be sure to factor in the time necessary to receive approval from the UW Human Subjects Division or the Animal Care Committee, and the need to comply with any other departmental or collaborating institutions’ requirements. Time required for review and approval ranges widely. Allocate enough time for the entire review process, including the possibility of resubmission and reconsideration.

You may NOT proceed with the human subjects or animal care research component of your dissertation until you have a UW approval number. This rule includes approval for exempt, minimal risk, or full review applications. Failure to obtain approval is quite serious, and could jeopardize completion of your dissertation, graduation plans, and any publications derived from the dissertation.

Resources for dealing with human subjects and animal subjects issues

The UW Human Subjects Division website includes many helpful sources of information, including:

  • Introduction to the Human Subjects Review Process, from the UW Human Subjects Division
  • Locations and instructions for completing the human subjects/animal subjects application
  • Helpful links and instructions about specific issues that may arise in your research, including a checklist for preparing a consent form

by Professor Emeritus Melissa Austin, Public Health Genetics; Marina Alberti, professor, Urban Design and Planning; and Woody Sullivan, professor, Astrobiology

Review of Graduate Student Research by the Institutional Review Board (IRB)

What is the IRB?

The IRB is a committee of scientists, non-scientists and community members. At the UW and other universities, the IRB reviews research proposals to protect the rights and welfare of human research subjects who participate in research activities conducted under the auspices of the University.

When is IRB review required?

If the proposed study meets the federal definition of research…

“A systematic investigation, including research development, testing and evaluation, designed to develop or contribute to generalizable knowledge.”

and…

If the proposed study involves “human subjects,” defined as “a living individual about whom an investigator (whether professional or student) conducting research obtains: 1) data through intervention or interaction with the individual; or 2) identifiable private information.”

Why is IRB review necessary?

IRB reviews help ensure the safety and protection of research subjects, as well as the ethical conduct of research that involves human subjects.

The IRB review must determine that all of the following requirements are satisfied.

  • Risks to subjects are minimized.
  • Risks to subjects are reasonable in relation to anticipated benefits.
  • Selection of subjects is equitable.
  • Informed consent will be sought from each prospective subject or the subject’s legally authorized representative.
  • Informed consent will be appropriately documented, in accordance with, and to the extent required by HSS regulation 46.117.
  • The research plan makes adequate provision for the monitoring of data collected to ensure the safety of subjects.
  • There are adequate provisions to protect the privacy of subjects and to maintain the confidentiality of data. When some or all of the subjects are likely to be vulnerable to coercion or undue influence, such as children, prisoners, pregnant women, mentally disabled persons or economically disadvantaged persons, additional safeguards have been included in the study to protect the rights and welfare of these subjects.

How does the IRB evaluate research proposals?

The IRB reviews and responds to proposals at three levels, depending on the type of research proposed.

Exempt: Six categories of research involving human subjects qualify for exemption from federal regulations governing the protection of human subjects. A determination of eligibility for exemption must be made by the IRB or its designee. Exempt research must also comply with state laws, UW policy, and conform to sound research ethics/principles.

Expedited (minimal risk): An “expedited” review procedure can be used when research has been determined to be of “minimal risk” to subjects (i.e., “poses no more risk to subjects than would be encountered by the average person in his/her daily activities”) and involves only the procedures listed in the federally described categories of expedited review. All federal, state and local regulations must be taken into consideration. The standard requirements for informed consent (or its waiver or alteration) apply.

Expedited reviews may be carried out by the IRB chair, an IRB co-chair, or by one or more experienced reviewers designated by the chair from among members of the IRB.

Full IRB review: Research that does not qualify as exempt or for expedited review must undergo a full review by a quorum of IRB members. The application process is the same as for expedited review; however, it is recommended that researchers allow two to four months from the time of submission until approval. Researchers should also be aware that the initial full review process frequently does not result in an outright approval of the research; minor or major revisions and written clarifications are often requested.

How can I get help?

The Human Subjects Division (HSD) website is designed to help you decide whether or not you need review and has detailed instructions on how to apply.

If you have questions or need additional assistance, you can contact HSD directly.

This Mentor Memo was developed in collaboration with the Human Subjects Division.

Presenting Your Research at Academic Conferences

Academic conferences allow you to:

  • Start developing your research agenda. Get useful feedback on your research as you convert conference papers into journal articles.
  • Gain visibility with future colleagues, employers, and future collaborators.
  • Start networking and meet people (other graduate students, future colleagues and mentors, researchers you admire).
  • Interview for jobs.

Which conferences?

Most UW departments are well-represented at key national academic conferences.

Many professional associations have divisions that may reflect your department’s areas of expertise. Graduate students also find it useful to present their research at topic-specific conferences. Check with faculty to see which organizations hold conferences where it would be appropriate for your research to be presented.

When and how?

Deadlines for conferences are usually noted on academic organizations’ websites. When considering how to submit your research, be sure to check submission requirements. Some conferences require full papers, while others will consider only abstracts. Be sure to adhere to these details and all deadlines, and be sure to submit your work to a relevant division! (What constitutes “relevant?” Check abstracts and programs from previous years’ conferences.)

At the conference…

Some departments provide funds that allow you to travel to conferences to present your research. In addition to talking about your research in a variety of ways, take advantage of being at the conference to learn about the field, meet other people, and participate.

Presenting your research

You will be judged first and foremost on your research, which means that you should strive for a great presentation. In other words:

  • Know what attendees at this particular conference expect, e.g., reading your paper vs. summarizing your paper? PowerPoint slides?
  • Know your research and what it contributes to the larger body of research.
  • Never, ever, exceed the allotted time! Think of your presentation as a headline service. You cannot cover all points, so select the ones you believe are most important.

How to navigate the conference

Read the conference program; attend the sessions that interest you, but don’t plan every hour.

Be ready with a brief “elevator talk” about your research. Conferences are very busy times, and people will not have time to hear a full explication of all your research projects.

Identify the individuals you would like to meet and ask your mentor/adviser to introduce you.

Introduce yourself to people. Many graduate students feel as if they know no one, so you’re not alone. If you are interested in meeting faculty and “big names,” walk up to them when they appear to have a spare moment, and talk about how you are using their research in your own work. Chances are they will want to learn more about you and your work.

Attend graduate forums and receptions.

Socialize at receptions held by various departments and schools.

Regardless of the sessions you attend and the people you meet, always remain professional. You want to be remembered for your research and professional demeanor, not anything else!

Turning Your Dissertation into a Book

Interested in publishing your dissertation as a book? You will likely need to revise it extensively so it will appeal to a wider audience and compete in the literary marketplace. Here are some guidelines to help you in this process.

Timeline

  • Allow plenty of time!
  • The review process can easily take up to a year, as it entails a peer review of your manuscript, potential revisions, further peer review and then approval.
  • The editing process can easily take a year to a year and a half as it entails copyediting, design, typesetting and proofreading, preparation of the index, printing and binding.

Dissertations differ from books in several ways

  • Dissertations are highly specialized, while books are geared to general readers.
  • Dissertation audiences are usually fewer than 100 readers — books are about 500 or more, in general.
  • In a dissertation, the author’s authority must be proven; in books, it is assumed.
  • Dissertations contain extensive documentation (to prove authority), while books document to credit sources and help the reader.
  • Dissertations can run long; books are often far shorter.

Elements that make a good book

  • A concise, memorable and intriguing title that includes essential key words
  • Clear and effective organization
  • A succinct introduction
  • Illustrations that enhance the text
  • Sections that are meaningful either alone or as part of the total book
  • Navigational aids, such as chapter titles, running heads, subheads, notes, bibliography, index
  • A voice (relationship of author to reader) that functions like an invisible tour guide or creative storyteller, and avoids sounding like a lecturer at a podium

The revision process

Basics

  • Forget your dissertation. Forget your committee.
  • Be bold!
  • Clarify your modified topic and audience.
  • Determine how to present it in a dynamic way.

Details

  • Remove unnecessary references to yourself.
  • Delete conspicuous chapter intros and summaries.
  • Make style parallel in chapter titles, captions, chapter openings and closings, subheads.
  • Revisit the introduction and conclusion.
  • Remove unnecessary notes; condense or combine others.
  • Eliminate most cross-references.
  • Cut unnecessary examples and data.
  • Make chapter openings strong, clear, and inviting.
  • Add definitions of jargon, foreign terms, biographical and historical dates.
  • Brainstorm several possible titles and subtitles.
  • Tighten prose.
  • Use active verbs.
  • Begin and end sentences with words you want to emphasize.

Resources

The Chicago Manual of Style. 15th ed. (2003). Chicago: University of Chicago Press.

German, William. (2005). From dissertation to book. Chicago: University of Chicago Press.

Harmon, Eleanor, et al., ed. (2003). The thesis and the book: A guide for first-time academic authors. 2nd ed. Toronto: University of Toronto Press.

Lucy, Beth, ed. (2004). Revising your dissertation: Advice from leading editors. Berkeley: University of California Press.

by Lorri Hagman, executive editor, University of Washington Press

Managing Large Writing Projects

Large projects, such as an master of arts degree thesis, dissertation, book, or just a long paper, can be daunting. For some of us, myself included, project management can be a challenge for any article written from scratch. This memo can help you break down your writing project into smaller, less intimidating parts. I will focus on the writing of a thesis or dissertation, but the same basic logic applies to even smaller writing tasks.

Getting started: Clarify purpose, argument, audience

Purpose: A thesis or dissertation should yield a high quality document that adds to the body of scholarly knowledge and is worthy, eventually, of publication in a peer- reviewed journal. Or your writing may address a public controversy or develop a creative insight that could change how people view a phenomenon of interest.

Argument: With your purpose clarified, think about your argument. Create a main argument that carries you through your thesis or dissertation. (There may be many other points along the way, but a core message will help you stay focused from beginning to end).

Audience: Keep a particular audience in mind. For academic work, identify a target journal. Think about who would want to read your work; this will motivate you to write and clarify your message.

Outlining, setting deadlines

One of the causes of vertigo with large writing projects is the sense that the work before you is too big or too much for you to handle given all your existing responsibilities and pressures. So break the project into manageable parts, and make the immediate task a two- or three-page mini-paper.

How to start: Outline your project carefully. Start with a one-page handwritten outline that is simply the main sections or chapter titles.

Then move to a more thorough outline, with detail under each of the points in the first version. At this point, each part of the outline is no more than a few pages.

Refine your outline to indicate how many pages and what kind of work each part will require. For instance, I might have a line in my outline that reads, “Introduce self-perception theory (two pages; brief literature review).” Your daunting, massive thesis or dissertation has now been reduced to a series of manageable, “do-able” tasks.

Set a schedule for completing each piece of the outline. Make sure that each chunk is small enough to be do-able in just a week or two, or even just a day or two.

Procrastination

First-time procrastination problems? You may just be tired, so relax and don’t be hard on yourself.

Persistent procrastination? Break your task into even smaller pieces.

One option: Identify a one-hour block of time. Work on your next writing task for just 15 minutes, followed by a five-minute stretching/social break. Repeat two more times, and in one hour you will have done 45 minutes of work. If that works, then schedule your next writing period for 80 minutes, and so on, until you can set aside three hours at a time for writing. You may find that taking the break after 15 minutes is hard to do because you get a rhythm and can’t stop working. That’s a good thing.

Another option: Schedule writing appointments with fellow students or faculty—or, form a three-to-five person study group that meets every one or two weeks to help keep each other on track.

Other options: See your adviser, commit to a scholarly conference (to create an external deadline), or set up some other writing-related appointment.

If your large writing project becomes so emotionally upsetting that you find yourself unable to do any of the above successfully, consider making an appointment for student counseling. It is easy for the different parts of our lives to get entangled, and the fear or stress you experience regarding your writing may have nothing to do with the quality of your ideas or your skill as a writer—but instead be symptomatic of other things upsetting you at home or at work.

And remember—it’s OK to ask for help.

by John Gastil, former professor, Communication

The Literature Review

From seminar paper to master of arts degree thesis to dissertation, the literature review provides both the foundation and the frame for your own research. Its preparation requires careful planning and a well-crafted presentation.

The purpose of the literature review

A literature review tells us what is known by sharing the results of prior studies related to your own.

A literature review places your study within a larger body of work. It shows how your study seeks to fill a gap in, or extend, our knowledge in this area.

A literature review offers a benchmark for assessing your own results. In the conclusion to your study you will revisit the literature review armed with your new findings.

Organizing the literature review

A good literature review is a synthesis of prior research presented in a way that adds value to our understanding of that work. So, it’s important to organize your review in a way that is coherent, relevant to your own study, and useful to other researchers. For example, you might cluster prior research by media type, communication situation, similar findings, key themes, respondent type, or other useful distinction.

Whatever organizing scheme you choose, it is typical to present the most important, relevant, or strongest collection of existing research first, and go from there. If not, there should be a narrative logic to the review presentation.

Another way to add value is to identify conceptual linkages among ideas and authors. Researchers often talk about the same processes — just in somewhat different ways.

It’s tempting to want to include every study that appeared in the key word search of your topic. Don’t. The challenge is to find the right balance between giving the reader confidence in your familiarity with literature and focusing on what’s most relevant for the study at hand.

Writing the literature review

Your synthesis of prior research should focus on key findings or conclusions with just enough information for the reader to discern the question and approach: “In her ethnographic study of Muslim immigrants’ perception of mainstream British media, Gillespie concluded…” The exception being if the study cited is significant because of its methodology — only then would you offer more methodological detail.

Not all ideas in the literature review are used to construct your study’s conceptual framework. So, at the end of each section, tell readers what key concept, finding, definition, or theme is most critical to “carry forward” into their reading of your study.

Don’t over-quote. It slows down your narrative. Direct quotations should only appear if the author said something in a unique, powerful, or precise way (e.g., a definition) that demands repeating in its exact form. Otherwise, use your own words.

Since a good review is a coherent, value-added organization of the literature, provide the reader with clear “signposts” through the instructive use of headings, introductions, transition phrases, and summary statements.

Finally, because people reading your paper or dissertation may not be familiar with your area of research, be careful not to weigh down your literature review in field-specific jargon. It is important that you write in clear and active prose.

by Nancy Rivenburgh, professor, Communication