This dataset presents ChatGPT usage patterns across different age groups, showing the percentage of users who have followed its advice, used it without following advice, or have never used it, based on a 2025 U.S. survey.

Context

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1842206%2Fd7e02bf38f4b08df2508d6b6e42f3066%2Fchatgpt2.png?generation=1700233710310045&alt=media" alt="">

Based on their wikipedia page

ChatGPT (Chat Generative Pre-trained Transformer) is a large language model-based chatbot developed by OpenAI and launched on November 30, 2022, that enables users to refine and steer a conversation towards a desired length, format, style, level of detail, and language. Successive prompts and replies, known as prompt engineering, are considered at each conversation stage as a context.

These reviews were extracted from Google Store App

Usage

This dataset should paint a good picture on what is the public's perception of the app over the years. Using this dataset, we can do the following

1. Extract sentiments and trends
2. Identify which version of the app had the most positive feedback, the worst.
3. Use topic modeling to identify the pain points of the application.

(AND MANY MORE!)

Note

Images generated using Bing Image Generator

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.

ChatGPT Gemini Claude Perplexity Human Evaluation Multi Aspect Review Dataset

  Introduction

Human evaluation and reviews with scalar score of AI Services responses are very usefuly in LLM Finetuning, Human Preference Alignment, Few-Shot Learning, Bad Case Shooting, etc, but extremely difficult to collect. This dataset is collected from DeepNLP AI Service User Review panel (http://www.deepnlp.org/store), which is an open review website for users to give reviews and upload… See the full description on the dataset page: https://huggingface.co/datasets/DeepNLP/ChatGPT-Gemini-Claude-Perplexity-Human-Evaluation-Multi-Aspects-Review-Dataset.

This dataset shows the types of advice users sought from ChatGPT based on a 2025 U.S. survey, including education, financial, medical, and legal topics.

UPDATE: Due to new Twitter API conditions changed by Elon Musk, now it's no longer free to use the Twitter (X) API and the pricing is 100 $/month in the hobby plan. So my automated ETL notebook stopped from updating new tweets to this dataset on May 13th 2023.

This dataset is was updated everyday with the addition of 1000 tweets/day containing any of the words "ChatGPT", "GPT3", or "GPT4", starting from the 3rd of April 2023. Everyday's tweets are uploaded 24-72h later, so the counter on tweets' likes, retweets, messages and impressions gets enough time to be relevant. Tweets are from any language selected randomly from all hours of the day. There are some basic filters applied trying to discard sensitive tweets and spam.

This dataset can be used for many different applications regarding to Data Analysis and Visualization but also NLP Sentiment Analysis techniques and more.

Consider upvoting this Dataset and the ETL scheduled Notebook providing new data everyday into it if you found them interesting, thanks! 🤗

Columns Description:

• tweet_id: Integer. unique identifier for each tweet. Older tweets have smaller IDs.

• tweet_created: Timestamp. Time of the tweet's creation.

• tweet_extracted: Timestamp. The UTC time when the ETL pipeline pulled the tweet and its metadata (likes count, retweets count, etc).

• text: String. The raw payload text from the tweet.

• lang: String. Short name for the Tweet text's language.

• user_id: Integer. Twitter's unique user id.

• user_name: String. The author's public name on Twitter.

• user_username: String. The author's Twitter account username (@example)

• user_location: String. The author's public location.

• user_description: String. The author's public profile's bio.

• user_created: Timestamp. Timestamp of user's Twitter account creation.

• user_followers_count: Integer. The number of followers of the author's account at the moment of the tweet extraction

• user_following_count: Integer. The number of followed accounts from the author's account at the moment of the Tweet extraction

• user_tweet_count: Integer. The number of Tweets that the author has published at the moment of the Tweet extraction.

• user_verified: Boolean. True if the user is verified (blue mark).

• source: The device/app used to publish the tweet (Apparently not working, all values are Nan so far).

• retweet_count: Integer. Number of retweets to the Tweet at the moment of the Tweet extraction.

• like_count: Integer. Number of Likes to the Tweet at the moment of the Tweet extraction.

• reply_count: Integer. Number of reply messages to the Tweet.

• impression_count: Integer. Number of times the Tweet has been seen at the moment of the Tweet extraction.

More info: Tweets API info definition: https://developer.twitter.com/en/docs/twitter-api/data-dictionary/object-model/tweet Users API info definition: https://developer.twitter.com/en/docs/twitter-api/data-dictionary/object-model/user

Within a year of its launch, ChatGPT has seen a surge in popularity. While many are drawn to its effectiveness and user-friendly interface, ChatGPT also introduces moral concerns, such as the temptation to present generated text as one’s own. This led us to theorize that personality traits such as Machiavellianism and sensation-seeking may be predictive of ChatGPT usage. We launched two online questionnaires with 2,000 respondents each, in September 2023 and March 2024, respectively. In Questionnaire 1, 22% of respondents were students, and 54% were full-time employees; 32% indicated they used ChatGPT at least weekly. Analysis of our ChatGPT Acceptance Scale revealed two factors, Effectiveness and Concerns, which correlated positively and negatively, respectively, with ChatGPT use frequency. A specific aspect of Machiavellianism (manipulation tactics) was found to predict ChatGPT usage. Questionnaire 2 was a replication of Questionnaire 1, with 21% students and 54% full-time employees, of which 43% indicated using ChatGPT weekly. In Questionnaire 2, more extensive personality scales were used. We found a moderate correlation between Machiavellianism and ChatGPT usage (r = .22) and with an opportunistic attitude towards undisclosed use (r = .30), relationships that largely remained intact after controlling for gender, age, education level, and the respondents’ country. We conclude that covert use of ChatGPT is associated with darker personality traits, something that requires further attention.

This dataset presents how much users trust ChatGPT across different advice categories, including career, education, financial, legal, and medical advice, based on a 2025 U.S. survey.

🧠 Awesome ChatGPT Prompts [CSV dataset]

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

  License

CC-0

This dataset shows how men and women in the U.S. reported using ChatGPT in a 2025 survey, including whether they followed its advice or chose not to use it.

This dataset summarizes how ChatGPT users rated the outcomes of the advice they received, including whether it was helpful, harmful, neutral, or uncertain, based on a 2025 U.S. survey.

IntroductionIn recent years, numerous AI tools have been employed to equip learners with diverse technical skills such as coding, data analysis, and other competencies related to computational sciences. However, the desired outcomes have not been consistently achieved. This study aims to analyze the perspectives of students and professionals from non-computational fields on the use of generative AI tools, augmented with visualization support, to tackle data analytics projects. The focus is on promoting the development of coding skills and fostering a deep understanding of the solutions generated. Consequently, our research seeks to introduce innovative approaches for incorporating visualization and generative AI tools into educational practices.MethodsThis article examines how learners perform and their perspectives when using traditional tools vs. LLM-based tools to acquire data analytics skills. To explore this, we conducted a case study with a cohort of 59 participants among students and professionals without computational thinking skills. These participants developed a data analytics project in the context of a Data Analytics short session. Our case study focused on examining the participants' performance using traditional programming tools, ChatGPT, and LIDA with GPT as an advanced generative AI tool.ResultsThe results shown the transformative potential of approaches based on integrating advanced generative AI tools like GPT with specialized frameworks such as LIDA. The higher levels of participant preference indicate the superiority of these approaches over traditional development methods. Additionally, our findings suggest that the learning curves for the different approaches vary significantly. Since learners encountered technical difficulties in developing the project and interpreting the results. Our findings suggest that the integration of LIDA with GPT can significantly enhance the learning of advanced skills, especially those related to data analytics. We aim to establish this study as a foundation for the methodical adoption of generative AI tools in educational settings, paving the way for more effective and comprehensive training in these critical areas.DiscussionIt is important to highlight that when using general-purpose generative AI tools such as ChatGPT, users must be aware of the data analytics process and take responsibility for filtering out potential errors or incompleteness in the requirements of a data analytics project. These deficiencies can be mitigated by using more advanced tools specialized in supporting data analytics tasks, such as LIDA with GPT. However, users still need advanced programming knowledge to properly configure this connection via API. There is a significant opportunity for generative AI tools to improve their performance, providing accurate, complete, and convincing results for data analytics projects, thereby increasing user confidence in adopting these technologies. We hope this work underscores the opportunities and needs for integrating advanced LLMs into educational practices, particularly in developing computational thinking skills.

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.

📌**Context**

The Healthcare Workforce Mental Health Dataset is designed to explore workplace mental health challenges in the healthcare industry, an environment known for high stress and burnout rates.

This dataset enables users to analyze key trends related to:

💠 Workplace Stressors: Examining the impact of heavy workloads, poor work environments, and emotional demands.

💠 Mental Health Outcomes: Understanding how stress and burnout influence job satisfaction, absenteeism, and turnover intention.

💠 Educational & Analytical Applications: A valuable resource for data analysts, students, and career changers looking to practice skills in data exploration and data visualization.

To help users gain deeper insights, this dataset is fully compatible with a Power BI Dashboard, available as part of a complete analytics bundle for enhanced visualization and reporting.

📌**Source**

This dataset was synthetically generated using the following methods:

💠 Python & Data Science Techniques: Probabilistic modeling to simulate realistic data distributions. Industry-informed variable relationships based on healthcare workforce studies.

💠 Guidance & Validation Using AI (ChatGPT): Assisted in refining dataset realism and logical mappings.

💠 Industry Research & Reports: Based on insights from WHO, CDC, OSHA, and academic studies on workplace stress and mental health in healthcare settings.

📌**Inspiration**

This dataset was inspired by ongoing discussions in healthcare regarding burnout, mental health, and staff retention. The goal is to bridge the gap between raw data and actionable insights by providing a structured, analyst-friendly dataset.

For those who want a ready-to-use reporting solution, a Power BI Dashboard Template is available, designed for interactive data exploration, workforce insights, and stress factor analysis.

📌**Important Note** This dataset is synthetic and intended for educational purposes only. It is not real-world employee data and should not be used for actual decision-making or policy implementation.

As ChatGPT emerges as a potential ally in healthcare decision-making, it is imperative to investigate how users leverage and perceive it. The repurposing of technology is innovative but brings risks, especially since AI’s effectiveness depends on the data it’s fed. In healthcare, ChatGPT might provide sound advice based on current medical knowledge, which could turn into misinformation if its data sources later include erroneous information. Our study assesses user perceptions of ChatGPT, particularly of those who used ChatGPT for healthcare-related queries. By examining factors such as competence, reliability, transparency, trustworthiness, security, and persuasiveness of ChatGPT, the research aimed to understand how users rely on ChatGPT for health-related decision-making. A web-based survey was distributed to U.S. adults using ChatGPT at least once a month. Bayesian Linear Regression was used to understand how much ChatGPT aids in informed decision-making. This analysis was conducted on subsets of respondents, both those who used ChatGPT for healthcare decisions and those who did not. Qualitative data from open-ended questions were analyzed using content analysis, with thematic coding to extract public opinions on urban environmental policies. Six hundred and seven individuals responded to the survey. Respondents were distributed across 306 US cities of which 20 participants were from rural cities. Of all the respondents, 44 used ChatGPT for health-related queries and decision-making. In the healthcare context, the most effective model highlights ’Competent + Trustworthy + ChatGPT for healthcare queries’, underscoring the critical importance of perceived competence and trustworthiness specifically in the realm of healthcare applications of ChatGPT. On the other hand, the non-healthcare context reveals a broader spectrum of influential factors in its best model, which includes ’Trustworthy + Secure + Benefits outweigh risks + Satisfaction + Willing to take decisions + Intent to use + Persuasive’. In conclusion our study findings suggest a clear demarcation in user expectations and requirements from AI systems based on the context of their use. We advocate for a balanced approach where technological advancement and user readiness are harmonized.

This dataset contains 14,934 instructions, contexts and responses, in several natural language categories such as classification, closed QA, generation, etc. The English original dataset was created by @databricks, who crowd-sourced the data creation via its employees. The current dataset is a translation of that dataset through ChatGPT (gpt-3.5-turbo).

Data Instances

{ "id": 14963, "instruction": "Wat zijn de duurste steden ter wereld?", "context": "", "response": "Dit is een uitgebreide lijst van de duurste steden: Singapore, Tel Aviv, New York, Hong Kong, Los Angeles, Zurich, Genève, San Francisco, Parijs en Sydney.", "category": "brainstorming" }

Data Fields

id: the ID of the item. The following 77 IDs are not included because they could not be translated (or were too long): [1502, 1812, 1868, 4179, 4541, 6347, 8851, 9321, 10588, 10835, 11257, 12082, 12319, 12471, 12701, 12988, 13066, 13074, 13076, 13181, 13253, 13279, 13313, 13346, 13369, 13446, 13475, 13528, 13546, 13548, 13549, 13558, 13566, 13600, 13603, 13657, 13668, 13733, 13765, 13775, 13801, 13831, 13906, 13922, 13923, 13957, 13967, 13976, 14028, 14031, 14045, 14050, 14082, 14083, 14089, 14110, 14155, 14162, 14181, 14187, 14200, 14221, 14222, 14281, 14473, 14475, 14476, 14587, 14590, 14667, 14685, 14764, 14780, 14808, 14836, 14891, 1 4966]

instruction: the instruction (question)

context: additional context that the AI can use to answer the question

response: the AI's expected response

category: the category of this type of question (see Dolly for more info)

Dataset Creation

Both the translations and the topics were translated with OpenAI's API for gpt-3.5-turbo. max_tokens=1024, temperature=0 as parameters.

The prompt template to translate the input is (where src_lang was English and tgt_lang Dutch):

CONVERSATION_TRANSLATION_PROMPT = """You are asked to translate a task's instruction, optional context to the task, and the response to the task, from {src_lang} to {tgt_lang}.

Here are the requirements that you should adhere to: 1. maintain the format: the task consists of a task instruction (marked instruction:), optional context to the task (marked context:) and response for the task marked with response:; 2. do not translate the identifiers instruction:, context:, and response: but instead copy them to your output; 3. make sure that text is fluent to read and does not contain grammatical errors. Use standard {tgt_lang} without regional bias; 4. translate the instruction and context text using informal, but standard, language; 5. make sure to avoid biases (such as gender bias, grammatical bias, social bias); 6. if the instruction is to correct grammar mistakes or spelling mistakes then you have to generate a similar mistake in the context in {tgt_lang}, and then also generate a corrected output version in the output in {tgt_lang}; 7. if the instruction is to translate text from one language to another, then you do not translate the text that needs to be translated in the instruction or the context, nor the translation in the response (just copy them as-is); 8. do not translate code fragments but copy them to your output. If there are English examples, variable names or definitions in code fragments, keep them in English.

Now translate the following task with the requirements set out above. Do not provide an explanation and do not add anything else.

"""

The system message was:

You are a helpful assistant that translates English to Dutch according to the requirements that are given to you.

Note that 77 items (0.5%) were not successfully translated. This can either mean that the prompt was too long for the given limit (max_tokens=1024) or that the generated translation could not be parsed into instruction, context and response fields. The missing IDs are [1502, 1812, 1868, 4179, 4541, 6347, 8851, 9321, 10588, 10835, 11257, 12082, 12319, 12471, 12701, 12988, 13066, 13074, 13076, 13181, 13253, 13279, 13313, 13346, 13369, 13446, 13475, 13528, 13546, 13548, 13549, 13558, 13566, 13600, 13603, 13657, 13668, 13733, 13765, 13775, 13801, 13831, 13906, 13922, 13923, 13957, 13967, 13976, 14028, 14031, 14045, 14050, 14082, 14083, 14089, 14110, 14155, 14162, 14181, 14187, 14200, 14221, 14222, 14281, 14473, 14475, 14476, 14587, 14590, 14667, 14685, 14764, 14780, 14808, 14836, 14891, 1 4966].

Initial Data Collection and Normalization

Initial data collection by databricks. See their repository for more information about this dataset.

Considerations for Using the Data

Note that the translations in this new dataset have not been verified by humans! Use at your own risk, both in terms of quality and biases.

Discussion of Biases

As with any machine-generated texts, users should be aware of potential biases that are included in this dataset. Although the prompt specifically includes make sure to avoid biases (such as gender bias, grammatical bias, social bias), of course the impact of such command is not known. It is likely that biases remain in the dataset so use with caution.

Other Known Limitations

The translation quality has not been verified. Use at your own risk!

Licensing Information

This repository follows the original databricks license, which is CC BY-SA 3.0 but see below for a specific restriction.

This text was generated (either in part or in full) with GPT-3 (gpt-3.5-turbo), OpenAI’s large-scale language-generation model. Upon generating draft language, the author reviewed, edited, and revised the language to their own liking and takes ultimate responsibility for the content of this publication.

If you use this dataset, you must also follow the Sharing and Usage policies.

As clearly stated in their Terms of Use, specifically 2c.iii, "[you may not] use output from the Services to develop models that compete with OpenAI". That means that you cannot use this dataset to build models that are intended to commercially compete with OpenAI. As far as I am aware, that is a specific restriction that should serve as an addendum to the current license.

This dataset is also available on the Hugging Face hub, its canonical repository.

This dataset compares how much U.S. adults trust ChatGPT relative to Google Search, including responses from a 2025 national survey measuring perceptions of AI accuracy and reliability.

This dataset reflects how Americans perceive ChatGPT's broader societal impact, based on a 2025 survey that asked whether the AI will help or harm humanity.

This dataset shows the percentage of U.S. adults who say they trust ChatGPT more than a human expert, based on a 2025 national AI trust survey.

IntroductionArtificial intelligence (AI) technology has made rapid progress for disease diagnosis and triage. In the field of ophthalmic diseases, image-based diagnosis has achieved high accuracy but still encounters limitations due to the lack of medical history. The emergence of ChatGPT enables human-computer interaction, allowing for the development of a multimodal AI system that integrates interactive text and image information.ObjectiveTo develop a multimodal AI system using ChatGPT and anterior segment images for diagnosing and triaging ophthalmic diseases. To assess the AI system's performance through a two-stage cross-sectional study, starting with silent evaluation and followed by early clinical evaluation in outpatient clinics.Methods and analysisOur study will be conducted across three distinct centers in Shanghai, Nanjing, and Suqian. The development of the smartphone-based multimodal AI system will take place in Shanghai with the goal of achieving ≥90% sensitivity and ≥95% specificity for diagnosing and triaging ophthalmic diseases. The first stage of the cross-sectional study will explore the system's performance in Shanghai's outpatient clinics. Medical histories will be collected without patient interaction, and anterior segment images will be captured using slit lamp equipment. This stage aims for ≥85% sensitivity and ≥95% specificity with a sample size of 100 patients. The second stage will take place at three locations, with Shanghai serving as the internal validation dataset, and Nanjing and Suqian as the external validation dataset. Medical history will be collected through patient interviews, and anterior segment images will be captured via smartphone devices. An expert panel will establish reference standards and assess AI accuracy for diagnosis and triage throughout all stages. A one-vs.-rest strategy will be used for data analysis, and a post-hoc power calculation will be performed to evaluate the impact of disease types on AI performance.DiscussionOur study may provide a user-friendly smartphone-based multimodal AI system for diagnosis and triage of ophthalmic diseases. This innovative system may support early detection of ocular abnormalities, facilitate establishment of a tiered healthcare system, and reduce the burdens on tertiary facilities.Trial registrationThe study was registered in ClinicalTrials.gov on June 25th, 2023 (NCT 05930444).