WIP: Leveraging AI for Literature Reviews: A Guide for New Researchers

Jiawei Gong; Debalina Maitra

Download Paper | Permalink

Conference: 2025 ASEE Annual Conference & Exposition
Location: Montreal, Quebec, Canada
Publication Date: June 22, 2025
Start Date: June 22, 2025
End Date: August 15, 2025
Conference Session: New Engineering Educators (NEE) Technical Session 3 - Professional and Faculty Development
Tagged Division: New Engineering Educators Division (NEE)
Page Count: 14
Permanent URL: https://peer.asee.org/57429

Paper Authors

biography

Jiawei Gong Pennsylvania State University, Behrend College orcid.org/0000-0003-4318-9387

visit author page

Dr. Jiawei Gong is an associate professor or Mechanical Engineering at The Pennsylvania state university, The Behrend College.

visit author page

biography

Debalina Maitra Kennesaw State University

visit author page

I teach graduate-level courses in the Department of Educational Leadership. Through my academic scholarship, I center the experiences, voices, and cultural capital of marginalized students, aiming to create more inclusive and equitable educational environments. As a transdisciplinary educational researcher, my work spans three interconnected domains:
Amplifying marginalized voices across STEM and other disciplines- I aim to bring attention to their experiences and recommendations, shedding light on the challenges and barriers they face while navigating their academic journey
Professional development of educators-equipping them with the knowledge, pedagogies, and skills needed to effectively support and engage multi-marginalized students.
And finally, I investigate how teachers can integrate students' identities and cultural capital into classroom lessons, with a special focus on STEM education.
My research bridges literacy education and STEM education with an equity lens, and it is deeply rooted in critical theories, aiming for transformational change. I also extensively (formally and informally) mentor students with multi-marginalized identities.

visit author page

Download Paper | Permalink

Abstract

The importance of conducting a comprehensive literature review cannot be overstated, as it serves multiple purposes: summarizing a field to identify future research directions, finding evidence to support results and discussions, and breaking barriers in interdisciplinary studies (Ahern et al. 2019). This process is often time-consuming and demands significant effort to ensure thoroughness and accuracy, which can be challenging for researchers with limited resources, for example, novice students. AI tools can enhance the traditional manual method by automating labor-intensive tasks such as searching, summarizing, and organizing information. This allows researchers to focus more on how to critically organize the literature review done by AI in the context of the research, and critical analysis and synthesis, rather than on administrative tasks such as managing reference lists, tracking citations, formatting documents, and organizing notes. State-of-the-art AI tools like Elicit, SciSpace, Perplexity, and ChatGPT Canvas offer opportunities to streamline the literature review process, making it more efficient and accessible when using them collectively. Faculty often face significant constraints on time and resources when training novice researchers in literature review techniques. AI-assisted literature review methods can be especially valuable across all disciplines, particularly in interdisciplinary fields where locating relevant articles can be more challenging for new researchers. These tools can help streamline the research process, improve efficiency, and enhance the quality of reviews, offering critical support to both faculty and emerging scholars. This study was motivated by challenges faced during the COVID-19 pandemic, when students assigned to write a review on perovskite solar cells couldn't complete it due to high turnover and inconsistent quality. Such issues are common at research institutions with undergraduates (RUIs), where frequent student turnover and limited faculty time affect productivity and review quality. This study explores how AI can improve the generation and organization of literature reviews to address these challenges by proposing a framework and a process.

In this proposed framework, AI acts as an additional "student," handling tasks that are repetitive and data-intensive, while the real students focus on more nuanced activities. This approach enables faculty to enhance their productivity significantly and ensures that critical tasks are completed efficiently. Our framework aims to optimize research workflows by simplifying complex tasks, standardizing processes, and making them repeatable to increase both productivity and the quality of academic output. Ultimately, the integration of AI tools into the literature review process has the potential to transform academic research, particularly at institutions where faculty must balance teaching, mentorship, and research with limited support. Additionally, our findings will help novice researchers to utilize and prompt AI efficiently to populate relevant previous work as AI is going to be the future of education (Zhang and Aslan, 2021). By adopting a balanced approach we can make literature reviews more efficient, reduce the burden of labor-intensive tasks, and enable researchers to focus on generating impactful insights and advancing scholarly discourse.

Reference

Ahern, A., Dominguez, C., McNally, C., O’Sullivan, J. J., & Pedrosa, D. (2019). A literature review of critical thinking in engineering education. Studies in Higher Education, 44(5), 816–828. https://doi.org/10.1080/03075079.2019.1586325

Zhang, K., & Aslan, A. B. (2021). AI technologies for education: Recent research & future directions. Computers and Education: Artificial Intelligence, 2, 100025.

Citation
Format

Gong, J., & Maitra, D. (2025, June), WIP: Leveraging AI for Literature Reviews: A Guide for New Researchers Paper presented at 2025 ASEE Annual Conference & Exposition , Montreal, Quebec, Canada . https://peer.asee.org/57429

TY - CPAPER
AB - The importance of conducting a comprehensive literature review cannot be overstated, as it serves multiple purposes: summarizing a field to identify future research directions, finding evidence to support results and discussions, and breaking barriers in interdisciplinary studies (Ahern et al. 2019). This process is often time-consuming and demands significant effort to ensure thoroughness and accuracy, which can be challenging for researchers with limited resources, for example, novice students. AI tools can enhance the traditional manual method by automating labor-intensive tasks such as searching, summarizing, and organizing information. This allows researchers to focus more on how to critically organize the literature review done by AI in the context of the research, and critical analysis and synthesis, rather than on administrative tasks such as managing reference lists, tracking citations, formatting documents, and organizing notes. State-of-the-art AI tools like Elicit, SciSpace, Perplexity, and ChatGPT Canvas offer opportunities to streamline the literature review process, making it more efficient and accessible when using them collectively. Faculty often face significant constraints on time and resources when training novice researchers in literature review techniques. AI-assisted literature review methods can be especially valuable across all disciplines, particularly in interdisciplinary fields where locating relevant articles can be more challenging for new researchers. These tools can help streamline the research process, improve efficiency, and enhance the quality of reviews, offering critical support to both faculty and emerging scholars. This study was motivated by challenges faced during the COVID-19 pandemic, when students assigned to write a review on perovskite solar cells couldn&#39;t complete it due to high turnover and inconsistent quality. Such issues are common at research institutions with undergraduates (RUIs), where frequent student turnover and limited faculty time affect productivity and review quality. This study explores how AI can improve the generation and organization of literature reviews to address these challenges by proposing a framework and a process.

In this proposed framework, AI acts as an additional &quot;student,&quot; handling tasks that are repetitive and data-intensive, while the real students focus on more nuanced activities. This approach enables faculty to enhance their productivity significantly and ensures that critical tasks are completed efficiently. Our framework aims to optimize research workflows by simplifying complex tasks, standardizing processes, and making them repeatable to increase both productivity and the quality of academic output. Ultimately, the integration of AI tools into the literature review process has the potential to transform academic research, particularly at institutions where faculty must balance teaching, mentorship, and research with limited support. Additionally, our findings will help novice researchers to utilize and prompt AI efficiently to populate relevant previous work as AI is going to be the future of education (Zhang and Aslan, 2021). By adopting a balanced approach we can make literature reviews more efficient, reduce the burden of labor-intensive tasks, and enable researchers to focus on generating impactful insights and advancing scholarly discourse.

Reference

Ahern, A., Dominguez, C., McNally, C., O’Sullivan, J. J., &amp;amp; Pedrosa, D. (2019). A literature review of critical thinking in engineering education. Studies in Higher Education, 44(5), 816–828. https://doi.org/10.1080/03075079.2019.1586325

Zhang, K., &amp;amp; Aslan, A. B. (2021). AI technologies for education: Recent research &amp;amp; future directions. Computers and Education: Artificial Intelligence, 2, 100025.

AU - Jiawei Gong
AU - Debalina Maitra
CY - Montreal, Quebec, Canada
DA - 2025/06/22
PB - ASEE Conferences
TI - WIP: Leveraging AI for Literature Reviews: A Guide for New Researchers
UR - https://peer.asee.org/57429
ER -