How to Use ChatPDF to Quickly Summarize and Extract Information from Research Articles
I used ChatGPT to write parts of this blog post, specifically the definition and features of ChatPDF. This blog post is the first of a series on how I will use AI-based tools to develop and enhance an academic writing course I will teach this fall.
I recently wrote a blog post about how to use ChatGPT for academic purposes, which sent me down a rabbit hole in learning how to use other AI-based tools. As an educator, I’m interested in learning how AI-based tools can facilitate teaching and learning. Do I have concerns about students using these tools to cheat and plagiarize? Yes, of course. But I also see opportunities for educators and students to embrace these tools.
I am currently developing an academic writing course for doctoral students and believe that tools such as ChatGPT, ChatPDF, and Elicit can be used to teach and facilitate academic writing and research. I conducted a preliminary literature search using Google Scholar and identified numerous editorials, commentaries, and research articles on the uses of ChatGPT.
I eventually located a recently published systematic review by Sallam (2023) on ChatGPT’s utility in healthcare education, research, and practice. I learned that ChatGPT has been found to improve scientific writing and health literacy, efficiently analyze datasets and literature reviews, and personalize learning. Limitations identified within the literature included risk of bias, incorrect citations, and inaccurate content with a risk of hallucination. Read more on AI hallucinations here.
Here’s how I used ChatPDF to help me digest the information published in the articles I identified on the use of ChatGPT for academic purposes.
First, what is ChatPDF? ChatPDF is a web-based platform that allows users to convert their PDF files into editable documents that can be easily modified, annotated, and shared with others. ChatPDF can be used to help students and researchers to make the most of their time by increasing their efficiency and productivity when working with PDF files. ChatPDF works by analyzing text in a PDF file and summarizing relevant information. Users can ask questions to quickly extract information.
According to the ChatPDF website, it can be used for the following purposes:
-
Summarize information included in PDF files to aid in comprehension.
-
Answer questions about text included in a PDF file.
-
Analyze documents to aid in the quick extraction of information.
-
Interpret and translate PDF files in any language.
Here is an example of how I used ChatPDF to extract information from the systematic review by Sallam (2023).
First, I uploaded the PDF and ChatPDF immediately generated the following:
ChatPDF: Hello there! I am the ChatGPT Utility PDF file and I am here to help you with your healthcare education, research, and practice needs. In this systematic review, we explore the promising perspectives and valid concerns of using ChatGPT in the healthcare industry. Here are three example questions you can ask about the file:
– What are some of the promising perspectives of using ChatGPT in healthcare education?
– How does ChatGPT benefit healthcare research?
– What are some of the valid concerns associated with using ChatGPT in healthcare practice?
I then asked ChatPDF the following questions, some of which I know it wasn’t designed to answer, and here are the responses:
How does ChatGPT benefit healthcare research?
ChatPDF: According to the systematic review on ChatGPT utility in healthcare education, research, and practice, ChatGPT benefits healthcare research by providing efficient analysis of datasets, code generation, literature reviews, saving time to focus on experimental design, and drug discovery and development. This can help researchers streamline their workflow and save time while conducting their research. (Page 1)
What I found: This information is correct and located in the abstract on page 1.
How many articles addressed scientific writing?
ChatPDF: According to the systematic review on ChatGPT utility in healthcare education, research, and practice, 31 records (51.7%) addressed scientific writing as a benefit of ChatGPT. (Page 12)
What I found: This information is correct and located on page 12.
Who were the participants of the studies that focused on scientific writing?
ChatPDF: I’m sorry, but the systematic review on ChatGPT utility in healthcare education, research, and practice does not provide information on the participants of the studies that focused on scientific writing. The review mainly focuses on the benefits and possible applications of ChatGPT in healthcare education, practice, and research. (Page 3, 12)
What I found: The article does not contain a summary or list of participants in the records reviewed. However, study participants were included in Table 3. The reader would need to manually extract information to answer this question.
How many primary sources were reviewed by the author?
ChatPDF: The systematic review on ChatGPT utility in healthcare education, research, and practice reviewed a total of 60 records eligible for inclusion in the current review. (Page 3)
What I found: The types of records included in the review are presented in Figure 2, but the term “primary source” is not mentioned within the text. The reader would need to manually extract information to answer this question.
Are there any examples of passive voice within the text?
ChatPDF: I’m sorry, but the given pages of the PDF as information source do not contain any examples of passive voice. The text mainly focuses on the benefits and possible applications of ChatGPT in healthcare education, practice, and research. (Page 3, 6, 12)
What I found: I recognize that ChatPDF is not designed to answer this question but was curious to see its response, as this is a task that I assigned to my students in the writing course.
As you can see, ChatPDF is incredibly useful for quickly extracting information from a journal article. However, its applications are limited. For instance, it cannot analyze text and produce information beyond what is already stated within the text. This was evident when I asked it to tell me how many primary sources were reviewed by the author. It would be useful to be able to upload multiple PDFs to compare results across several studies. I plan to further explore Elicit for these purposes. Stay tuned!
Reference: Sallam, M. (2023) ChatGPT utility in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns. Healthcare, 11, 887. https://doi.org/10.3390/healthcare11060887