Mentions
Extended reach
Total likes
Video views
AI synopsis
Discussions consistently praise the study’s findings, such as mentions of ChatGPT producing questions with acceptable psychometric properties, and highlight how AI can revolutionize exam development, using words like 'transformative' and 'remarkable.' The tone and choice of examples reflect a high level of engagement and recognition of the research’s importance in education and assessment fields.
Most discussions acknowledge the potential and usefulness of AI-generated questions, emphasizing the positive findings related to psychometric quality and efficiency.
Posts demonstrate high interest by highlighting studies, results, and the transformative potential of AI in exam creation, indicating enthusiasm and engagement with the topic.
Through references to specific research findings, discussions of quality, and the importance of prompts, the posts show a deep level of analysis and active involvement.
The discussions suggest this research may significantly influence educational assessments and testing practices by showcasing AI's capabilities and limitations.
Our study published today! "#ChatGPT for generating MCQs: Evidence on the use of #artificialintelligence in automatic item generation for a rational pharmacotherapy exam" It presents the first psychometric evidence for ChatGPT-generated case-based MCQs. https://t.co/NxhAuoeGA4
"... we found that ChatGPT is able to generate multiple choice questions with acceptable levels of item psychometrics. Our findings showed that the questions can effectively differentiate between students who perform at high and low levels." Ref: 10.1007/s00228-024-03649-x
There is a group of authors who has published 100+ commentaries on many diverse fields only in the last 8 months. They didn't miss our #ChatGPT paper (free read-only access via this link: https://t.co/oPTuS5E9qR) as well. Here is our reply to them: https://t.co/ADcaQxa29e https://t.co/zrwarhYhM4
"The efficiency achieved through #AI would appear remarkable to test developers from a decade ago, who were engaged in the effortful task of manually writing multiple-choice questions." #MedEd Ref: 10.1007/s00228-024-03649-x
"Despite the presence of studies that focus on providing human-generated questions to ChatGPT, there has been a lack of research focused to asking ChatGPT-generated questions to humans." Ref: 10.1007/s00228-024-03649-x This is why we conducted this study, btw.
"... [in generating MCQs using #ChatGPT] it is essential to recognize that the quality of multiple-choice questions is closely tied to prompt quality." Ref: 10.1007/s00228-024-03649-x
This presentation from St Georges University of London on April 17, 2024, discusses using ChatGPT to generate medical cases and multiple-choice questions. It highlights a customized tool for efficient, high-quality…
This presentation discusses utilizing ChatGPT to generate medical cases and questions for teaching, supported by a randomized controlled study and evidence from related research. It highlights how AI can improve…
This video explores how to use ChatGPT and specific prompts to generate medical cases and multiple-choice questions for teaching and assessment, presenting results from a randomized controlled study highlighting the…
“Bir diğer önemli dezavantaj ise yapay zeka modellerinin “kara kutu” olmasıdır. Bu, her seferinde benzersiz sorular üretmemizi sağlasa da, girdimizin çıktıyı tam olarak nasıl etkileyeceğini bilememekteyiz.” Kaynak: 10.1007/s00228-024-03649-x
"Another significant drawback is the “black box” nature of AI models. Although this enables us to generate unique questions each time, we cannot know how our input will precisely affect the output." Ref: 10.1007/s00228-024-03649-x
There is a group of authors who has published 100+ commentaries on many diverse fields only in the last 8 months. They didn't miss our #ChatGPT paper (free read-only access via this link: https://t.co/oPTuS5E9qR) as well. Here is our reply to them: https://t.co/ADcaQxa29e https://t.co/zrwarhYhM4
RT @MedEdFlamingo: Couldn't agree more! "Despite the presence of studies that focus on providing human-generated questions to ChatGPT, the…
Couldn't agree more! "Despite the presence of studies that focus on providing human-generated questions to ChatGPT, there has been a lack of research focused to asking ChatGPT-generated questions to humans." Ref: 10.1007/s00228-024-03649-x https://t.co/DQuHuIzIyq
RT @MedEdFlamingo: "... while it is efficient to generate questions with #ChatGPT, constructing an entire exam without any revisions can be…
"... while it is efficient to generate questions with #ChatGPT, constructing an entire exam without any revisions can be challenging." #MedEd Ref: 10.1007/s00228-024-03649-x
RT @MedEdFlamingo: "... [in generating MCQs using #ChatGPT] it is essential to recognize that the quality of multiple-choice questions is c…
RT @MedEdFlamingo: "... [in generating MCQs using #ChatGPT] it is essential to recognize that the quality of multiple-choice questions is c…
"... [in generating MCQs using #ChatGPT] it is essential to recognize that the quality of multiple-choice questions is closely tied to prompt quality." Ref: 10.1007/s00228-024-03649-x
RT @MedEdFlamingo: "The efficiency achieved through #AI would appear remarkable to test developers from a decade ago, who were engaged in t…
RT @MedEdFlamingo: "The efficiency achieved through #AI would appear remarkable to test developers from a decade ago, who were engaged in t…
"The efficiency achieved through #AI would appear remarkable to test developers from a decade ago, who were engaged in the effortful task of manually writing multiple-choice questions." #MedEd Ref: 10.1007/s00228-024-03649-x
Ref: ChatGPT for generating multiple‑choice questions: Evidence on the use of artificial intelligence in automatic item generation for a rational pharmacotherapy exam Here is the link for accessing to a view-only version of the paper: https://t.co/p3OLk1mxQT
"This [#AI] transformation is readily observable in our new ability, as humans, to produce appropriate case-based MCQs with minimal human efforts, accomplished by the simple process of inputting a prompt and hitting the enter key." #MedEd Ref: 10.1007/s00228-024-03649-x
RT @MedEdFlamingo: "... we found that ChatGPT is able to generate multiple choice questions with acceptable levels of item psychometrics. O…
RT @MedEdFlamingo: "... we found that ChatGPT is able to generate multiple choice questions with acceptable levels of item psychometrics. O…
Ref: ChatGPT for generating multiple‑choice questions: Evidence on the use of artificial intelligence in automatic item generation for a rational pharmacotherapy exam Here is the link for accessing to a view-only version of the paper: https://t.co/p3OLk1mxQT
"... we found that ChatGPT is able to generate multiple choice questions with acceptable levels of item psychometrics. Our findings showed that the questions can effectively differentiate between students who perform at high and low levels." Ref: 10.1007/s00228-024-03649-x
ChatGPT for generating multiple-choice questions: Evidence on the use of artificial intelligence in automatic i @HandsomeKinoko #note https://t.co/WbwL3tTsyp
RT @MedEdFlamingo: "Despite the presence of studies that focus on providing human-generated questions to ChatGPT, there has been a lack of…
ChatGPT for generating multiple‑choice questions: Evidence on the use of artificial intelligence in automatic item generation for a rational pharmacotherapy exam Here is the link for accessing to a view-only version of the paper: https://t.co/oPTuS5E9qR
"Despite the presence of studies that focus on providing human-generated questions to ChatGPT, there has been a lack of research focused to asking ChatGPT-generated questions to humans." Ref: 10.1007/s00228-024-03649-x This is why we conducted this study, btw.
RT @MedEdFlamingo: Our study published today! "#ChatGPT for generating MCQs: Evidence on the use of #artificialintelligence in automatic i…
RT @MedEdFlamingo: Our study published today! "#ChatGPT for generating MCQs: Evidence on the use of #artificialintelligence in automatic i…
Our study published today! "#ChatGPT for generating MCQs: Evidence on the use of #artificialintelligence in automatic item generation for a rational pharmacotherapy exam" It presents the first psychometric evidence for ChatGPT-generated case-based MCQs. https://t.co/NxhAuoeGA4
doi:10. professions education. Part 2: tools and practical application: 1007/s00228-024-03649-x ... doi:10.1007/978-3-031-72315-5_20 review. Smart Learn ...
MP
TE
PA
TH
S
MM
I
RP