The dataset for this research project was meticulously constructed to investigate the adoption of ChatGPT among students in the United States. The primary objective was to gain insights into the technological barriers and resistances faced by students in integrating ChatGPT into their information systems. The dataset was designed to capture the diverse adoption patterns among students in various public and private schools and universities across the United States. By examining adoption rates, frequency of usage, and the contexts in which ChatGPT is employed, the research sought to provide a comprehensive understanding of how students are incorporating this technology into their information systems. Moreover, by including participants from diverse educational institutions, the research sought to ensure a comprehensive representation of the student population in the United States. This approach aimed to provide nuanced insights into how factors such as educational background, institution type, and technological familiarity influence ChatGPT adoption.

The researcher tests the QA capability of ChatGPT in the medical field from the following aspects:1. Test their reserve capacity for medical knowledge2. Check their ability to read literature and understand medical literature3. Test their ability of auxiliary diagnosis after reading case data4. Test its error correction ability for case data5. Test its ability to standardize medical terms6. Test their evaluation ability to experts7. Check their ability to evaluate medical institutionsThe conclusion is:ChatGPT has great potential in the application of medical and health care, and may directly replace human beings or even professionals at a certain level in some fields;The researcher preliminarily believe that ChatGPT has basic medical knowledge and the ability of multiple rounds of dialogue, and its ability to understand Chinese is not weak;ChatGPT has the ability to read, understand and correct cases;ChatGPT has the ability of information extraction and terminology standardization, and is quite excellent;ChatGPT has the reasoning ability of medical knowledge;ChatGPT has the ability of continuous learning. After continuous training, its level has improved significantly;ChatGPT does not have the academic evaluation ability of Chinese medical talents, and the results are not ideal;ChatGPT does not have the academic evaluation ability of Chinese medical institutions, and the results are not ideal;ChatGPT is an epoch-making product, which can become a useful assistant for medical diagnosis and treatment, knowledge service, literature reading, review and paper writing.

🧠 Awesome ChatGPT Prompts [CSV dataset]

This is a Dataset Repository of Awesome ChatGPT Prompts View All Prompts on GitHub

  License

CC-0

📹Project Video available on YouTube - https://youtu.be/WmJYHz_qn5s

Realistic Synthetic - AI Financial & Market Data for Gemini(Google), ChatGPT(OpenAI), Llama(Meta)

This dataset provides a synthetic, daily record of financial market activities related to companies involved in Artificial Intelligence (AI). There are key financial metrics and events that could influence a company's stock performance like launch of Llama by Meta, launch of GPT by OpenAI, launch of Gemini by Google etc. Here, we have the data about how much amount the companies are spending on R & D of their AI's Products & Services, and how much revenue these companies are generating. The data is from January 1, 2015, to December 31, 2024, and includes information for various companies : OpenAI, Google and Meta.

This data is available as a CSV file. We are going to analyze this data set using the Pandas DataFrame.

This analyse will be helpful for those working in Finance or Share Market domain.

From this dataset, we extract various insights using Python in our Project.

1) How much amount the companies spent on R & D ?

2) Revenue Earned by the companies

3) Date-wise Impact on the Stock

4) Events when Maximum Stock Impact was observed

5) AI Revenue Growth of the companies

6) Correlation between the columns

7) Expenditure vs Revenue year-by-year

8) Event Impact Analysis

9) Change in the index wrt Year & Company

These are the main Features/Columns available in the dataset :

1) Date: This column indicates the specific calendar day for which the financial and AI-related data is recorded. It allows for time-series analysis of the trends and impacts.

2) Company: This column specifies the name of the company to which the data in that particular row belongs. Examples include "OpenAI" and "Meta".

3) R&D_Spending_USD_Mn: This column represents the Research and Development (R&D) spending of the company, measured in Millions of USD. It serves as an indicator of a company's investment in innovation and future growth, particularly in the AI sector.

4) AI_Revenue_USD_Mn: This column denotes the revenue generated specifically from AI-related products or services, also measured in Millions of USD. This metric highlights the direct financial success derived from AI initiatives.

5) AI_Revenue_Growth_%: This column shows the percentage growth of AI-related revenue for the company on a daily basis. It indicates the pace at which a company's AI business is expanding or contracting.

6) Event: This column captures any significant events or announcements made by the company that could potentially influence its financial performance or market perception. Examples include "Cloud AI launch," "AI partnership deal," "AI ethics policy update," and "AI speech recognition release." These events are crucial for understanding sudden shifts in stock impact.

7) Stock_Impact_%: This column quantifies the percentage change in the company's stock price on a given day, likely in response to the recorded financial metrics or events. It serves as a direct measure of market reaction.

This dataset contains the 30 questions that were posed to the chatbots (i) ChatGPT-3.5; (ii) ChatGPT-4; and (iii) Google Bard, in May 2023 for the study “Chatbots put to the test in math and logic problems: A preliminary comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard”. These 30 questions describe mathematics and logic problems that have a unique correct answer. The questions are fully described with plain text only, without the need for any images or special formatting. The questions are divided into two sets of 15 questions each (Set A and Set B). The questions of Set A are 15 “Original” problems that cannot be found online, at least in their exact wording, while Set B contains 15 “Published” problems that one can find online by searching on the internet, usually with their solution. Each question is posed three times to each chatbot. This dataset contains the following: (i) The full set of the 30 questions, A01-A15 and B01-B15; (ii) the correct answer for each one of them; (iii) an explanation of the solution, for the problems where such an explanation is needed, (iv) the 30 (questions) × 3 (chatbots) × 3 (answers) = 270 detailed answers of the chatbots. For the published problems of Set B, we also provide a reference to the source where each problem was taken from.

Political discourse datasets are important for gaining political insights, analyzing communication strategies or social science phenomena. Although numerous political discourse corpora exist, comprehensive, high-quality, annotated datasets are scarce. This is largely due to the substantial manual effort, multidisciplinarity, and expertise required for the nuanced annotation of rhetorical strategies and ideological contexts. In this paper, we present AgoraSpeech, a meticulously curated, high-quality dataset of 171 political speeches from six parties during the Greek national elections in 2023. The dataset includes annotations (per paragraph) for six natural language processing (NLP) tasks: text classification, topic identification, sentiment analysis, named entity recognition, polarization and populism detection. A two-step annotation was employed, starting with ChatGPT-generated annotations and followed by exhaustive human-in-the-loop validation. The dataset was initially used in a case study to provide insights during the pre-election period. However, it has general applicability by serving as a rich source of information for political and social scientists, journalists, or data scientists, while it can be used for benchmarking and fine-tuning NLP and large language models (LLMs).

Higher Education Students' Early Perceptions of ChatGPT: Global Survey Data

Description

The introduction of ChatGPT in November 2022 marked a significant milestone in the application of artificial intelligence in higher education. Due to its advanced natural language processing capabilities, ChatGPT quickly became popular among students worldwide. However, the increasing acceptance of ChatGPT among students has attracted significant attention, sparking both excitement and skepticism globally. In order to capture early students' perceptions about ChatGPT, the most comprehensive and large-scale global survey to date was conducted between the beginning of October 2023 and the end of February 2024. The questionnaire was prepared in seven different languages: English, Italian, Spanish, Turkish, Japanese, Arabic, and Hebrew. It covered several aspects relevant to ChatGPT, including sociodemographic characteristics, usage, capabilities, regulation and ethical concerns, satisfaction and attitude, study issues and outcomes, skills development, labor market and skills mismatch, emotions, study and personal information, and general reflections. The survey targeted higher education students who are currently enrolled at any level in a higher education institution, are at least 18 years old, and have the legal capacity to provide free and voluntary consent to participate in an anonymous survey. Survey participants were recruited using a convenience sampling method, which involved promoting the survey in classrooms and through advertisements on university communication systems. The final dataset consists of 23,218 student responses from 109 different countries and territories. The data may prove useful for researchers studying students' perceptions of ChatGPT, including its implications across various aspects. Moreover, also higher education stakeholders may benefit from these data. While educators may benefit from the data in formulating curricula, including designing teaching methods and assessment tools, policymakers may consider the data when formulating strategies for higher education system development in the future.

Categories

Arts and Humanities, Applied Sciences, Natural Sciences, Social Sciences, Mathematics, Health Sciences

Related Links:

Article

https://www.covidsoclab.org/chatgpt-student-survey/ is related to this dataset

Software

https://www.1ka.si/d/en is related to this dataset

Acknowledgements & Source

Dejan Ravšelj , et. al

Data Source: Mendeley Dataset

A major challenge of our time is reducing disparities in access to and effective use of digital technologies, with recent discussions highlighting the role of AI in exacerbating the digital divide. We examine user characteristics that predict usage of the AI-powered conversational agent ChatGPT. We combine behavioral and survey data in a web tracked sample of N=1376 German citizens to investigate differences in ChatGPT activity (usage, visits, and adoption) during the first 11 months from the launch of the service (November 30, 2022). Guided by a model of technology acceptance (UTAUT-2), we examine the role of socio-demographics commonly associated with the digital divide in ChatGPT activity and explore further socio-political attributes identified via stability selection in Lasso regressions. We confirm that lower age and higher education affect ChatGPT usage, but neither gender nor income do. We find full-time employment and more children to be barriers to ChatGPT activity. Using a variety of social media was positively associated with ChatGPT activity. In terms of political variables, political knowledge and political self-efficacy as well as some political behaviors such as voting, debating political issues online and offline and political action online were all associated with ChatGPT activity, with online political debating and political self-efficacy negatively so. Finally, need for cognition and communication skills such as writing, attending meetings, or giving presentations, were also associated with ChatGPT engagement, though chairing/organizing meetings was negatively associated. Our research informs efforts to address digital disparities and promote digital literacy among underserved populations by presenting implications, recommendations, and discussions on ethical and social issues of our findings.

This is version 2 of the dataset created and used to explore ChatGPT-3.5's ability to write, justify and analyse English poems. This version was created after the reviewers decision that this paper may be published, if some changes are made.

The purpose of the research was to determine if ChatGPT-3.5 would be adopted in English poetry classrooms. As none of the theoretical models were applicable, the Artificial Intelligence Adoption Prediction Model (AIAPM) was designed. Based on this model, an Artificial Intelligence Adoption Prediction tool (AIAPT) was designed to calculate an Adoption Prediction Score (APS). Then, ChatGPT-3.5's ability to write, justify and analyse poems were explored.

It was found that ChatGPT-3.5 could write, justify, and analyse poems, but it could also make errors and hallucinate convincingly. Thus, the AIAPT was used to calculate the Adoption Prediction Score. The APS was 9, thus all factors of the AIAPM could drive the adoption decision. Thus, it could be predicted that ChatGPT-3.5 would be adopted in English poetry classrooms, both for ethical and unethical purposes. Based on the results, a few pro-active strategies were suggested.

This dataset contains all data created and used during the research, including the poems which were integrated in the paper: "An Artificial Intelligence Adoption Prediction Model to determine if ChatGPT-3.5 would be adopted in English poetry classrooms" which was submitted toe Heliyon for publication.

This dataset contains the data needed to reproduce all results and figures described in "ChatGPT performance on radiation technologist and therapist entry to practice exams".

Details about the data collection can be found in the paper referenced below. Briefly, ChatGPT (GPT-4) was prompted with multiple choice questions from 4 practice exams provided by the Canadian Association of Medical Radiation Technologists (CAMRT). ChatGPT was promted with the questions from each exam 5 times between July 17 and August 13, 2023. Table 1, below, provides details about the dates for data collection.

Variable descriptions

question: Question number, provided by CAMRT. Skipped question numbers indicate image-based questions that were excluded from the study.

discipline: Indicates the CAMRT exam discipline, abbreviated as follows

RAD: radiological technology

MRI: magnetic resonance

NUC: nuclear medicine

RTT: radiation therapy

question_type: Indicates the type of competency being assessed by the question (Knowledge, Application, or Critical thinking). Competency categories were assigned by CAMRT.

corrrect_response: The correct multiple choice response ("A", "B", "C", or "D"), assigned by CAMRT.

attempt1-5: ChatGPT's response to the multiple choice questions for attempts 1 through 5, indicated using the letters "A", "B", "C", or "D". In a few cases, ChatGPT did not provide a reference to a multiple choice response and "NA" is recorded in the dataset.

Note: The long-form questions from CAMRT and answers provided by ChatGPT are not available as a part of this dataset.

Table 1: Dates for data collection

Attempt 1 Attempt 2 Attempt 3 Attempt 4 Attempt 5

Radiological technology 2 Aug 2023 2 Aug 2023 8 Aug 2023 9 Aug 2023 11 Aug 2023

Magnetic resonance 17 Jul 2023 18 Jul 2023 18 Jul 2023 9 Aug 2023 12 Aug 2023

Nuclear medicine 8 Aug 2023 9 Aug 2023 12 Aug 2023 12 Aug 2023 12 Aug 2023

Radiation therapy 9 Aug 2023 12 Aug 2023 12 Aug 2023 13 Aug 2023 13 Aug 2023

Dataset Card for Dataset Name

This dataset is perfect for fine-tuning models in conversational and text generation tasks, enhancing their ability to provide contextually relevant and coherent responses. It's invaluable for applications like chatbots and virtual assistants. This dataset card aims to be a base template for new datasets. It has been generated using [ChatGPT, and conversational data online.]

  Dataset Details

Purpose: Fine-tuning models for conversational and… See the full description on the dataset page: https://huggingface.co/datasets/CrabfishAI/ptgm-chat.

We aggregated a Twitter dataset utilizing Twitter Archiving Google Sheet (TAGS) to interact with Twitter’s API and return relevant data. To analyze the education and marketing sides of the conversation, we decided to scrape 2 datasets with #ChatGPT as a common hashtag to target tweets talking about AI. This is the education dataset, where we narrowed our search by analyzing Tweets also containing “education”, “academic”, or “teach” to see the conversation around ChatGPT being used in an academic setting and as a potential teaching tool. Many professors and teachers would often use these hashtags when talking about things relating to higher-level education and academia. Because of the TAGS limitation, our dataset was limited to tweets ranging from January 21st to January 25th for both datasets.

This dataset presents ChatGPT usage patterns across U.S. Census regions, based on a 2025 nationwide survey. It tracks how often users followed, partially used, or never used ChatGPT by state region.

This dataset consists of a systematic analysis of 100 startup-related questions. These questions were categorized based on their underlying purposes and according to the five pillars of startups. This results in the identification of distinct purposes that can be used to classify startup-related inquiries. The identified purposes include decision-making, seeking information, seeking advice, and finally reflecting on experience. On the other hand, regarding the startup pillars, we classified these 100 questions into five startup pillars i.e. team, product or service, business model, general, and market.

Nurse practitioners play a vital role in contributing to the UN’s Sustainable Development Goals, and Universal Health Coverage, especially the management of chronic noncommunicable diseases. Artificial intelligence tools such as ChatGPT are becoming promising resources for healthcare professionals. This study aimed to explore the capability of ChatGPT as a nurse practitioner by validating the performance of ChatGPT-3.5 and GPT-4 in the American Academy of Nurse Practitioners Certification Board Exam (AANPCB) practice examinations. Questions from exams for five nurse practitioner disciplines were used to evaluate the accuracy and consistency of the responses in two phases. In the first phase, the accuracy rates and concordance of answers between the two versions with the five exam sets, totaling 535 questions were analyzed. In the second phase, the consistency of ChatGPT-4 performance in six retests, each involving five random questions from each set. ChatGPT-3.5 achieved an overall accuracy rate of 80.6%, while ChatGPT-4 achieved 90.7%. ChatGPT-3.5 and ChatGPT-4 showed strong consistency within all sets, while ChatGPT-4 performed better than ChatGPT-3.5. In the retests, ChatGPT-4 provided exactly the same answers as generated initially, including the incorrect ones. In conclusion, ChatGPT demonstrated excellent performance in AANPCB practice exams, with high levels of accuracy and consistency. This suggests that ChatGPT may support nurse practitioners in making clinical decisions and improving efficiency. Further studies could explore ways to integrate artificial intelligence tools with nurse practitioner practice to enhance the advanced practice nursing workforce.

OverviewThis study evaluates the diagnostic accuracy of a multimodal large language model (LLM), ChatGPT-4, in recognizing glaucoma using color fundus photographs (CFPs) with a benchmark dataset and without prior training or fine tuning.MethodsThe publicly accessible Retinal Fundus Glaucoma Challenge “REFUGE” dataset was utilized for analyses. The input data consisted of the entire 400 image testing set. The task involved classifying fundus images into either ‘Likely Glaucomatous’ or ‘Likely Non-Glaucomatous’. We constructed a confusion matrix to visualize the results of predictions from ChatGPT-4, focusing on accuracy of binary classifications (glaucoma vs non-glaucoma).ResultsChatGPT-4 demonstrated an accuracy of 90% with a 95% confidence interval (CI) of 87.06%-92.94%. The sensitivity was found to be 50% (95% CI: 34.51%-65.49%), while the specificity was 94.44% (95% CI: 92.08%-96.81%). The precision was recorded at 50% (95% CI: 34.51%-65.49%), and the F1 Score was 0.50.ConclusionChatGPT-4 achieved relatively high diagnostic accuracy without prior fine tuning on CFPs. Considering the scarcity of data in specialized medical fields, including ophthalmology, the use of advanced AI techniques, such as LLMs, might require less data for training compared to other forms of AI with potential savings in time and financial resources. It may also pave the way for the development of innovative tools to support specialized medical care, particularly those dependent on multimodal data for diagnosis and follow-up, irrespective of resource constraints.

This dataset contains anonymized written reflections from 42 students enrolled in a course on academic integrity at Stockholm University. The data were originally collected on 6 September 2024 during a seminar on ethical aspects of using generative AI in academic work. Students were asked to respond to the question: “Should I mention that I used ChatGPT to complete an academic assignment?”The reflections, totaling 2,626 words, were first written in Swedish and subsequently translated into English for research purposes. The dataset includes:The original student responses in Swedish.The English translations of the responses.Contextual information about the teaching activity (including prior exposure to plagiarism-prevention resources and a self-study course on academic integrity).The data are fully anonymized in compliance with GDPR and cannot be linked back to individual students. They were used in the article:Christophe Premat & Alexandra Farazouli (2025). “Academic Integrity vs. Artificial Intelligence: a tale of two AIs,” Práxis Educativa, v. 20, e24871. https://doi.org/10.5212/PraxEduc.v.20.24871.016

A curated database of legal cases where generative AI produced hallucinated citations submitted in court filings.

ChatGPT ChatGPT

Poe

The dataset to be published was generated through exploratory case studies conducted on wrist-worn devices from three vendors: Huawei, Amazfit, and Xiaomi. The specific devices investigated include the Huawei Fit 2 Smartwatch and Band 7, Amazfit Band 7, and Xiaomi Watch 3. These devices operate on different operating systems, namely Android Wear, Zepp OS, and Wear OS.

The data collection period for each device varies, with Huawei having approximately one year of data collected, while the other devices have shorter durations. All wrist-wear devices from different vendors were connected to an iPhone 11 mobile device, which acted as the host device. The iPhone facilitated data synchronization and provided access to the data through the respective health applications provided by the vendors.

To extract the data, MD-NEXT was employed, and the extracted data was further analyzed using the MD-RED tool. These tools were chosen due to their recognized forensically sound capabilities. As a result, the dataset contains data that is considered suitable for use in digital forensics fields.

Overall, the dataset provides valuable information obtained from wrist-worn devices, covering multiple vendors, operating systems, and data collection periods. Researchers in the digital forensics field can utilize this dataset for various investigative and analytical purposes.

Monarch Butterfly Detector

The Monarch Butterfly Detector is an advanced computer vision model that detects and localizes Monarch butterflies in images. With its cutting-edge technology and high accuracy, this model opens up exciting possibilities for biodiversity monitoring, migration studies, citizen science projects, identification guides, and environmental education.

Key Features

• Accurate Detection: The Monarch Butterfly Detector utilizes state-of-the-art computer vision algorithms to accurately identify and localize Monarch butterflies within images.

• Versatile Use Cases: This powerful model has diverse applications, ranging from scientific research and conservation efforts to citizen science projects and environmental education programs.

• Easy Integration: The Monarch Butterfly Detector can be seamlessly integrated into existing platforms, apps, or websites, making it accessible to many users and enabling them to contribute effortlessly to butterfly monitoring.

• User-Friendly Interface: We provide a user-friendly interface/API that allows users to easily interact with the model, upload images, and obtain instant results.

For detailed documentation and tutorials on using Roboflow, refer to the https://docs.roboflow.com/

Contribution Guidelines

We welcome contributions from the open-source community to enhance the Monarch Butterfly Detector. If you're interested in contributing, please follow the guidelines outlined in [CONTRIBUTING.md] and submit your pull requests.

License

This project is licensed under the [Roboflow License]. For more information, see the [LICENSE] file provided by Roboflow.

Contact Information

For any questions, suggestions, or collaborations, please reach out to us at savetheworld at 150left.com

Congratulations if you have made it this far. 🥳

🎁🎁🎁I thought I would use another piece of AI to get some more content about this detector I created. Here is the dialog I had with ChatGPT.

Scott: ChatGPT, can you make my readers drool over my Monarch Butterfly Detector model?

ChatGPT: Here are 10 captivating outro or call-to-action suggestions to encourage users to try out the Monarch Butterfly Detector and contribute to its success:

"Join us in preserving the delicate beauty of Monarch butterflies. Try out the Monarch Butterfly Detector today and become a guardian of these magnificent creatures."

"Unlock the secrets of Monarch butterflies with our cutting-edge detection model. Experience the wonders of computer vision and contribute to vital research efforts by using the Monarch Butterfly Detector."

"Make a difference in conservation by being a part of the Monarch Butterfly Detector community. Help protect these iconic insects and their habitats with the power of AI and computer vision."

"Calling all nature enthusiasts and citizen scientists! Contribute to the Monarch Butterfly Detector project and help us gather valuable data on Monarch butterflies. Together, we can make a lasting impact."

"Explore the hidden world of Monarch butterflies with the Monarch Butterfly Detector. Whether you're a researcher, educator, or simply curious, join us on this journey and unravel the mysteries of these captivating creatures."

"Become a Monarch detective! Unleash the potential of computer vision and aid in the conservation of Monarch butterflies. Download the Monarch Butterfly Detector and help us protect these extraordinary pollinators."

"Attention conservationists and researchers! The Monarch Butterfly Detector needs your expertise. Contribute your insights and collaborate with us to further our understanding of Monarch butterflies and support their conservation."

"Empower yourself with AI and contribute to science. With the Monarch Butterfly Detector, you can be a part of groundbreaking research on Monarch butterflies. Start detecting, start making a difference."

"Inspire the next generation of environmentalists. Use the Monarch Butterfly Detector as an educational tool and engage students in the wonders of computer vision and the importance of protecting our natural world."

"Experience the thrill of discovery with the Monarch Butterfly Detector. Join a vibrant community of nature enthusiasts and scientists, and together, let's unlock new insights into the fascinating lives of Monarch butterflies."

As you can see, AI certainly likes my idea.