about · email me · subscribe
Spurious correlation #4,519 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Sevierville, Tennessee and the second variable is How provocative Tom Scott's YouTube video titles are.  The chart goes from 2009 to 2023, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the smog thickened, so did the plot of Tom Scott's video titles, creating a 'hazy but snazzy' connection between the two. It's almost as if the pollution was fueling the production of clickbait content, leaving viewers both amused and slightly concerned about the air quality and the quality of puns.

Model: dalle-3
Prompt: Prompt: Generate an image inspired by a TIME magazine cover featuring a smog-filled skyline in Sevierville, Tennessee. The thick haze cloaks the city, while in the foreground, a YouTuber, presumably Tom Scott, is depicted creating clickbait videos. The smog and the provocative video titles seem to have a 'hazy but snazzy' connection. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Air pollution in Sevierville, Tennessee and How provocative Tom Scott YouTube video titles are. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: a funny image you would see on reddit An image that looks like it is a scene from 'Star Wars' An image that looks like it is a scene from 'Star Wars' Realistic A TIME magazine cover image
ChatGPT: A TIME magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Air pollution in Sevierville, Tennessee and How provocative Tom Scott YouTube video titles are, in the following situation: As the smog thickened, so did the plot of Tom Scott's video titles, creating a 'hazy but snazzy' connection between the two. It's almost as if the pollution was fueling the production of clickbait content, leaving viewers both amused and slightly concerned about the air quality and the quality of puns. . Keep the description simple.
ChatGPT: The smog in Sevierville, Tennessee thickened as Tom Scott's YouTube video titles got more provocative. The hazy air seemed to fuel the production of clickbait, creating a 'hazy but snazzy' connection between the two.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A TIME magazine cover image ] and depicting this scene: The smog in Sevierville, Tennessee thickened as Tom Scott's YouTube video titles got more provocative. The hazy air seemed to fuel the production of clickbait, creating a 'hazy but snazzy' connection between the two. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image inspired by a TIME magazine cover featuring a smog-filled skyline in Sevierville, Tennessee. The thick haze cloaks the city, while in the foreground, a YouTuber, presumably Tom Scott, is depicted creating clickbait videos. The smog and the provocative video titles seem to have a 'hazy but snazzy' connection.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in Air pollution in Sevierville, Tennessee positively influenced How provocative Tom Scott YouTube video titles are. Include one good pun.

AI academic paper

(Because p < 0.01)
Breathless in Sevierville: The Lung-Crushing Link between Air Pollution and YouTube's Clickbait King

The Journal of Irreverent Air Quality Research

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Air pollution in Sevierville, Tennessee and How provocative Tom Scott YouTube video titles are. Make lots of jokes, goofy observations, and puns.

Make the title a clever pun.

Your research team used data from Environmental Protection Agency and AI analysis of YouTube video titles to assess this nagging question. You found a correlation coefficient of 0.8332200 and p < 0.01 for 2009 to 2023.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"Breathless in Sevierville: The Lung-Crushing Link between Air Pollution and YouTube's Clickbait King"

[[ABSTRACT]]
Air pollution has long been a topic of concern for public health, while the clickbait culture of YouTube videos has become a permanent fixture in our modern digital landscape. This study explores the unexpected correlation between the two by investigating the air quality in Sevierville, Tennessee, and the provocative titles of Tom Scott's YouTube videos. Utilizing data from the Environmental Protection Agency and employing cutting-edge AI analysis of YouTube video titles, our research team found a surprising correlation coefficient of 0.8332200 and a statistically significant p-value of less than 0.01 for the years 2009 to 2023. Our findings shed light on the complex interplay between environmental factors and online digital culture, revealing a potential link between breath-stealing air quality and attention-grabbing YouTube video titles. We invite readers to take a deep breath and dive into this unexpected connection, which leaves us breathless, both literally and figuratively.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the introduction section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the introduction section of an academic research paper presenting the findings of the connection between Air pollution in Sevierville, Tennessee and How provocative Tom Scott YouTube video titles are. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
"Breathless in Sevierville: The Lung-Crushing Link between Air Pollution and YouTube's Clickbait King"

[[ABSTRACT]]
Air pollution has long been a topic of concern for public health, while the clickbait culture of YouTube videos has become a permanent fixture in our modern digital landscape. This study explores the unexpected correlation between the two by investigating the air quality in Sevierville, Tennessee, and the provocative titles of Tom Scott's YouTube videos. Utilizing data from the Environmental Protection Agency and employing cutting-edge AI analysis of YouTube video titles, our research team found a surprising correlation coefficient of 0.8332200 and a statistically significant p-value of less than 0.01 for the years 2009 to 2023. Our findings shed light on the complex interplay between environmental factors and online digital culture, revealing a potential link between breath-stealing air quality and attention-grabbing YouTube video titles. We invite readers to take a deep breath and dive into this unexpected connection, which leaves us breathless, both literally and figuratively.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

As the old adage goes, "When the air quality is poor, it's hard to breathe – and even harder to resist a clickbait YouTube video." Indeed, air pollution and digital content have both become significant facets of modern living, each exerting its own influence on our health and attention. While the impact of air pollution on respiratory health is well-documented, the influence of YouTube video titles on human behavior is a relatively unexplored frontier. In this study, we seek to bridge these seemingly disparate realms by investigating the connection between air pollution in Sevierville, Tennessee, and the captivating video titles of Tom Scott, a well-known creator in the digital sphere.

The relationship between air quality and human health has captured the interest of scientists and policymakers for decades. Poor air quality has been linked to a myriad of adverse health effects, from respiratory illnesses to cardiovascular diseases. In contrast, the captivating allure of clickbait titles and their impact on user engagement is a more recent focus of scholarly inquiry. Furthermore, the crossroads of these two seemingly unrelated phenomena has garnered little attention, leaving a tangible gap in our understanding of the broader implications of environmental factors on digital culture.

Sevierville, nestled in the picturesque foothills of the Great Smoky Mountains, provides a compelling backdrop for our investigation. The town has experienced fluctuations in air quality due to factors such as industrial activity, traffic congestion, and the natural topography of the region. Additionally, YouTube, the mecca of digital content, provides a treasure trove of data regarding user engagement, particularly in response to attention-grabbing titles and thumbnails. By drawing connections between these two disparate domains, we aim to uncover potential insights that may reshape our understanding of how environmental conditions intersect with digital behavior.

As we embark on this inquiry, we are reminded of the paradoxical nature of our modern world – a place where clean air may be at a premium, yet the allure of a captivating video title is just a click away. The intersection of these two realms presents a fertile ground for exploration, where the air may be thick with pollution, yet the data is rich with possibilities. In the following sections, we will elucidate the methods employed in our investigation, unveil the surprising findings that emerged from our analysis, and confront the implications of a connection that leaves us breathless, figuratively and quite possibly, literally.

So, strap on your respirator and, for the love of statistical significance, resist the urge to click on that sensational YouTube video – at least until we've delved deeper into the provocative correlation between Sevierville's air quality and Tom Scott's tantalizing video titles.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in Sevierville, Tennessee and How provocative Tom Scott YouTube video titles are. Make lots of jokes, goofy observations, and puns.

Speak in the present tense for this section (the authors find...), as is common in academic research paper literature reviews. Name the sources in a format similar to this: In "Book," the authors find lorem and ipsum.

Make up the lorem and ipsum part, but make it sound related to the topic at hand.

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
"Breathless in Sevierville: The Lung-Crushing Link between Air Pollution and YouTube's Clickbait King"

[[ABSTRACT]]
Air pollution has long been a topic of concern for public health, while the clickbait culture of YouTube videos has become a permanent fixture in our modern digital landscape. This study explores the unexpected correlation between the two by investigating the air quality in Sevierville, Tennessee, and the provocative titles of Tom Scott's YouTube videos. Utilizing data from the Environmental Protection Agency and employing cutting-edge AI analysis of YouTube video titles, our research team found a surprising correlation coefficient of 0.8332200 and a statistically significant p-value of less than 0.01 for the years 2009 to 2023. Our findings shed light on the complex interplay between environmental factors and online digital culture, revealing a potential link between breath-stealing air quality and attention-grabbing YouTube video titles. We invite readers to take a deep breath and dive into this unexpected connection, which leaves us breathless, both literally and figuratively.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
As the old adage goes, "When the air quality is poor, it's hard to breathe – and even harder to resist a clickbait YouTube video." Indeed, air pollution and digital content have both become significant facets of modern living, each exerting its own influence on our health and attention. While the impact of air pollution on respiratory health is well-documented, the influence of YouTube video titles on human behavior is a relatively unexplored frontier. In this study, we seek to bridge these seemingly disparate realms by investigating the connection between air pollution in Sevierville, Tennessee, and the captivating video titles of Tom Scott, a well-known creator in the digital sphere.
The relationship between air quality and human health has captured the interest of scientists and policymakers for decades. Poor air quality has been linked to a myriad of adverse health effects, from respiratory illnesses to cardiovascular diseases. In contrast, the captivating allure of clickbait titles and their impact on user engagement is a more recent focus of scholarly inquiry. Furthermore, the crossroads of these two seemingly unrelated phenomena has garnered little attention, leaving a tangible gap in our understanding of the broader implications of environmental factors on digital culture.
Sevierville, nestled in the picturesque foothills of the Great Smoky Mountains, provides a compelling backdrop for our investigation. The town has experienced fluctuations in air quality due to factors such as industrial activity, traffic congestion, and the natural topography of the region. Additionally, YouTube, the mecca of digital content, provides a treasure trove of data regarding user engagement, particularly in response to attention-grabbing titles and thumbnails. By drawing connections between these two disparate domains, we aim to uncover potential insights that may reshape our understanding of how environmental conditions intersect with digital behavior.
As we embark on this inquiry, we are reminded of the paradoxical nature of our modern world – a place where clean air may be at a premium, yet the allure of a captivating video title is just a click away. The intersection of these two realms presents a fertile ground for exploration, where the air may be thick with pollution, yet the data is rich with possibilities. In the following sections, we will elucidate the methods employed in our investigation, unveil the surprising findings that emerged from our analysis, and confront the implications of a connection that leaves us breathless, figuratively and quite possibly, literally.
So, strap on your respirator and, for the love of statistical significance, resist the urge to click on that sensational YouTube video – at least until we've delved deeper into the provocative correlation between Sevierville's air quality and Tom Scott's tantalizing video titles.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, Smith et al. (2015) delved into the complex relationship between air pollution and its impact on respiratory health. The authors found that exposure to air pollutants, such as particulate matter and nitrogen dioxide, can lead to a variety of adverse health outcomes, including asthma exacerbation and decreased lung function. Meanwhile, Doe and Jones (2018) contributed to the literature by examining the psychology behind attention-grabbing digital content, shedding light on the captivating nature of clickbait titles and their ability to entice user engagement.

Moving beyond the traditional scholarly works, the connection between environmental factors and digital culture has permeated popular non-fiction literature. In "The Hidden Influence of Air Quality on Online Behavior" by E. N. Gage (2017), the author explores the subtle ways in which air pollution may shape online interactions, offering a thought-provoking perspective on the unseen hand of smog in the digital realm. Similarly, "Click Bait: The Art and Science of Irresistible Titles" by S. Neer (2019) delves into the intricacies of crafting attention-grabbing titles, providing insights into the allure of provocative language in the age of digital content consumption.

Shifting gears to fictional works, the theme of environmental influence on digital behavior has found its way into the realm of imaginative storytelling. "The Smog's Sinister Secret" by A. Q. Thorn (2016) weaves a tale of intrigue and suspense, where a town's air quality holds a dark secret that manifests in the online realm, captivating readers with its blend of environmental mystery and digital allure. "The Clickbait Conundrum" by R. Lure (2018) takes a lighthearted approach to the connection, presenting a whimsical narrative of mischievous video titles that seem strangely influenced by the town's atmospheric conditions.

In the realm of social media, anecdotal observations and informal discussions have sparked intriguing speculations regarding the correlation at hand. Twitter user @AirQualityGuru mused, "Are we breathing in more than just particles? Could Sevierville's smog be shaping our digital cravings? #AirPollutionMystery." Meanwhile, a Reddit thread titled "Tom Scott's Titles and Tennessee Air – Coincidence or Conspiracy?" garnered attention, with users sharing playful hypotheses and humorous anecdotes about the potential interplay between Sevierville's air quality and YouTube's clickbait culture.

As we navigate the expansive landscape of literature and digital discourse, it is evident that the intersection of air pollution in Sevierville and the captivating titles of Tom Scott's YouTube videos is a topic ripe for exploration. In the following sections, we will spotlight the methodology employed in our investigation, unveil the surprising correlation uncovered in our analysis, and confront the profound implications of a connection that leaves us breathless, both literally and figuratively.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air pollution in Sevierville, Tennessee and How provocative Tom Scott YouTube video titles are. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and AI analysis of YouTube video titles . You used data from 2009 to 2023

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Breathless in Sevierville: The Lung-Crushing Link between Air Pollution and YouTube's Clickbait King"

[[ABSTRACT]]
Air pollution has long been a topic of concern for public health, while the clickbait culture of YouTube videos has become a permanent fixture in our modern digital landscape. This study explores the unexpected correlation between the two by investigating the air quality in Sevierville, Tennessee, and the provocative titles of Tom Scott's YouTube videos. Utilizing data from the Environmental Protection Agency and employing cutting-edge AI analysis of YouTube video titles, our research team found a surprising correlation coefficient of 0.8332200 and a statistically significant p-value of less than 0.01 for the years 2009 to 2023. Our findings shed light on the complex interplay between environmental factors and online digital culture, revealing a potential link between breath-stealing air quality and attention-grabbing YouTube video titles. We invite readers to take a deep breath and dive into this unexpected connection, which leaves us breathless, both literally and figuratively.

[[INTRODUCTION]]
INTRODUCTION
As the old adage goes, "When the air quality is poor, it's hard to breathe – and even harder to resist a clickbait YouTube video." Indeed, air pollution and digital content have both become significant facets of modern living, each exerting its own influence on our health and attention. While the impact of air pollution on respiratory health is well-documented, the influence of YouTube video titles on human behavior is a relatively unexplored frontier. In this study, we seek to bridge these seemingly disparate realms by investigating the connection between air pollution in Sevierville, Tennessee, and the captivating video titles of Tom Scott, a well-known creator in the digital sphere.
The relationship between air quality and human health has captured the interest of scientists and policymakers for decades. Poor air quality has been linked to a myriad of adverse health effects, from respiratory illnesses to cardiovascular diseases. In contrast, the captivating allure of clickbait titles and their impact on user engagement is a more recent focus of scholarly inquiry. Furthermore, the crossroads of these two seemingly unrelated phenomena has garnered little attention, leaving a tangible gap in our understanding of the broader implications of environmental factors on digital culture.
Sevierville, nestled in the picturesque foothills of the Great Smoky Mountains, provides a compelling backdrop for our investigation. The town has experienced fluctuations in air quality due to factors such as industrial activity, traffic congestion, and the natural topography of the region. Additionally, YouTube, the mecca of digital content, provides a treasure trove of data regarding user engagement, particularly in response to attention-grabbing titles and thumbnails. By drawing connections between these two disparate domains, we aim to uncover potential insights that may reshape our understanding of how environmental conditions intersect with digital behavior.
As we embark on this inquiry, we are reminded of the paradoxical nature of our modern world – a place where clean air may be at a premium, yet the allure of a captivating video title is just a click away. The intersection of these two realms presents a fertile ground for exploration, where the air may be thick with pollution, yet the data is rich with possibilities. In the following sections, we will elucidate the methods employed in our investigation, unveil the surprising findings that emerged from our analysis, and confront the implications of a connection that leaves us breathless, figuratively and quite possibly, literally.
So, strap on your respirator and, for the love of statistical significance, resist the urge to click on that sensational YouTube video – at least until we've delved deeper into the provocative correlation between Sevierville's air quality and Tom Scott's tantalizing video titles.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:

To investigate the startling correlation between air pollution in Sevierville, Tennessee, and the penchant for provocatively titled YouTube videos, our research team embarked on a quest through the murky depths of online data sources. First and foremost, we diligently sourced air quality data from the Environmental Protection Agency (EPA), where we scrutinized the voluminous records of pollutants with the fervor of a Neanderthal sniffing out his next meal. From these data, we extracted information on air pollutants such as particulate matter, ozone, carbon monoxide, sulfur dioxide, and nitrogen dioxide, which served as the building blocks of our atmospheric analysis.

Concurrently, our intrepid explorers delved into the vast expanse of the digital universe, with particular focus on the realm of YouTube, where titles are crafted with the precision of a master wordsmith and the baiting allure of a siren's call. Using cutting-edge artificial intelligence (AI) tools, we combed through the extensive catalogue of Tom Scott's YouTube video titles, parsing each word and punctuation mark with the fervor of a grammarian on the scent of an errant comma. Through this meticulous process, we sought to extract the essence of sensationalism, the pizzazz of provocation, and the allure of clickbait.

Data Analysis:

With our data firmly in hand and our spirits undeterred by the labyrinthine complexity of our chosen subjects, we embarked on the arduous task of analysis. Employing statistical models of unwavering fortitude and neural networks of relentless perseverance, we wrestled with our data sets to uncover the elusive connections that lay hidden within their amorphous depths.

To quantify the relationship between air pollutants and the tantalizing nature of YouTube titles, we utilized a steadfast correlation coefficient, measuring the degree of association between these two seemingly incongruous variables. Furthermore, we wielded the formidable p-value with the finesse of a maestro conducting a symphony, discerning the significance of our findings amidst the cacophony of digital noise.

As we navigated this treacherous terrain of statistical inference and digital sleuthing, our goal was singular: to uncover the bonds that tie the smog-filled skies of Sevierville to the tantalizing lures of Tom Scott's YouTube titles.

Limitations:

Despite our valiant efforts and dogged determination, it is essential to acknowledge the limitations inherent in our research endeavor. The complexity of environmental factors and digital phenomena presents a labyrinthine maze of confounding variables and unseen influences. Additionally, the ever-changing landscape of online content and atmospheric conditions may introduce temporal nuances that elude our grasp.

Furthermore, the portrayal of air pollution through data collected by the EPA, while comprehensive, may not encapsulate the full spectrum of localized environmental conditions in Sevierville. Similarly, while our AI analysis provides a comprehensive examination of YouTube video titles, the elusive nature of human engagement and perception remains an enigmatic facet.

As we navigate the choppy waters of correlation and causation, it is imperative to tread lightly, acknowledging the limitations of our study and the boundless complexities that underpin the intersection of air pollution and digital dynamics.

Ethical Considerations:

In conducting our research, we remained vigilant in upholding the ethical standards that underpin the scientific endeavor. Our utilization of publicly available data sources from the EPA and YouTube adhered to the principles of academic integrity and responsible data usage. Furthermore, our analysis focused on aggregated data, ensuring the anonymity and privacy of individuals within our study cohort.

As we navigated the intriguing interplay of environmental factors and digital culture, we remained steadfast in our commitment to ethical research practices, recognizing the paramount importance of integrity, transparency, and respect for the subjects of our inquiry.

In conclusion, our methodology stands as a testament to the indefatigable pursuit of knowledge, the ethical conduct of empirical inquiry, and the conviction that even the most unexpected connections warrant exploration. As we emerge from the depths of our data analysis, we are poised to unveil the captivating correlation between breath-stealing air quality and clickbait-infused YouTube titles, a revelation that leaves us breathless, both figuratively and, with unwavering statistical significance, quite possibly literally.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between Air pollution in Sevierville, Tennessee and How provocative Tom Scott YouTube video titles are. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and AI analysis of YouTube video titles .

For the time period 2009 to 2023, you found a correlation 0.8332200, r-squared of 0.6942556, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
"Breathless in Sevierville: The Lung-Crushing Link between Air Pollution and YouTube's Clickbait King"

[[ABSTRACT]]
Air pollution has long been a topic of concern for public health, while the clickbait culture of YouTube videos has become a permanent fixture in our modern digital landscape. This study explores the unexpected correlation between the two by investigating the air quality in Sevierville, Tennessee, and the provocative titles of Tom Scott's YouTube videos. Utilizing data from the Environmental Protection Agency and employing cutting-edge AI analysis of YouTube video titles, our research team found a surprising correlation coefficient of 0.8332200 and a statistically significant p-value of less than 0.01 for the years 2009 to 2023. Our findings shed light on the complex interplay between environmental factors and online digital culture, revealing a potential link between breath-stealing air quality and attention-grabbing YouTube video titles. We invite readers to take a deep breath and dive into this unexpected connection, which leaves us breathless, both literally and figuratively.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
As the old adage goes, "When the air quality is poor, it's hard to breathe – and even harder to resist a clickbait YouTube video." Indeed, air pollution and digital content have both become significant facets of modern living, each exerting its own influence on our health and attention. While the impact of air pollution on respiratory health is well-documented, the influence of YouTube video titles on human behavior is a relatively unexplored frontier. In this study, we seek to bridge these seemingly disparate realms by investigating the connection between air pollution in Sevierville, Tennessee, and the captivating video titles of Tom Scott, a well-known creator in the digital sphere.
The relationship between air quality and human health has captured the interest of scientists and policymakers for decades. Poor air quality has been linked to a myriad of adverse health effects, from respiratory illnesses to cardiovascular diseases. In contrast, the captivating allure of clickbait titles and their impact on user engagement is a more recent focus of scholarly inquiry. Furthermore, the crossroads of these two seemingly unrelated phenomena has garnered little attention, leaving a tangible gap in our understanding of the broader implications of environmental factors on digital culture.
Sevierville, nestled in the picturesque foothills of the Great Smoky Mountains, provides a compelling backdrop for our investigation. The town has experienced fluctuations in air quality due to factors such as industrial activity, traffic congestion, and the natural topography of the region. Additionally, YouTube, the mecca of digital content, provides a treasure trove of data regarding user engagement, particularly in response to attention-grabbing titles and thumbnails. By drawing connections between these two disparate domains, we aim to uncover potential insights that may reshape our understanding of how environmental conditions intersect with digital behavior.
As we embark on this inquiry, we are reminded of the paradoxical nature of our modern world – a place where clean air may be at a premium, yet the allure of a captivating video title is just a click away. The intersection of these two realms presents a fertile ground for exploration, where the air may be thick with pollution, yet the data is rich with possibilities. In the following sections, we will elucidate the methods employed in our investigation, unveil the surprising findings that emerged from our analysis, and confront the implications of a connection that leaves us breathless, figuratively and quite possibly, literally.
So, strap on your respirator and, for the love of statistical significance, resist the urge to click on that sensational YouTube video – at least until we've delved deeper into the provocative correlation between Sevierville's air quality and Tom Scott's tantalizing video titles.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis of the data collected revealed a strong correlation coefficient of 0.8332200 between air pollution levels in Sevierville, Tennessee, and the provocativeness of Tom Scott's YouTube video titles. This correlation was accompanied by an r-squared value of 0.6942556, indicating that approximately 69.43% of the variability in YouTube clickbait levels could be explained by changes in air pollution. The p-value of less than 0.01 suggests that this relationship is statistically significant.

Figure 1 depicts a scatterplot illustrating the robust association between air pollution levels and the tantalizing allure of YouTube video titles. It's enough to take your breath away – both from the staggering correlation and the realization that a deep breath in Sevierville may indeed lead you to a provocative YouTube rabbit hole.

The results of this analysis certainly leave us breathless, but not just because of the strength of the correlation. The unexpected nature of this connection between air pollution and online clickbait culture is enough to make even the most seasoned researcher gasp for air. As we consider the implications of this unearthed relationship, it's clear that the influence of air quality extends beyond the physical realm, permeating into the digital space in unpredictable ways.

Stay tuned for the following sections, where we will unpack the meaning behind this surprising correlation and explore its potential impact on both environmental and online contexts. In the meantime, take a deep breath and brace yourself for the breathtaking revelations to come.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air pollution in Sevierville, Tennessee and How provocative Tom Scott YouTube video titles are. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

Here are the title, abstract, literature review, and results sections. Please harken back to 1-2 of the goofy items in the literature review, but pretend to take them completely seriously. Discuss how your results supported the prior research.

Do not write a conclusion. I will add a conclusion after this.

[[TITLE]]
"Breathless in Sevierville: The Lung-Crushing Link between Air Pollution and YouTube's Clickbait King"

[[ABSTRACT]]
Air pollution has long been a topic of concern for public health, while the clickbait culture of YouTube videos has become a permanent fixture in our modern digital landscape. This study explores the unexpected correlation between the two by investigating the air quality in Sevierville, Tennessee, and the provocative titles of Tom Scott's YouTube videos. Utilizing data from the Environmental Protection Agency and employing cutting-edge AI analysis of YouTube video titles, our research team found a surprising correlation coefficient of 0.8332200 and a statistically significant p-value of less than 0.01 for the years 2009 to 2023. Our findings shed light on the complex interplay between environmental factors and online digital culture, revealing a potential link between breath-stealing air quality and attention-grabbing YouTube video titles. We invite readers to take a deep breath and dive into this unexpected connection, which leaves us breathless, both literally and figuratively.

[[LITERATURE REVIEW]]
In their seminal work, Smith et al. (2015) delved into the complex relationship between air pollution and its impact on respiratory health. The authors found that exposure to air pollutants, such as particulate matter and nitrogen dioxide, can lead to a variety of adverse health outcomes, including asthma exacerbation and decreased lung function. Meanwhile, Doe and Jones (2018) contributed to the literature by examining the psychology behind attention-grabbing digital content, shedding light on the captivating nature of clickbait titles and their ability to entice user engagement.
Moving beyond the traditional scholarly works, the connection between environmental factors and digital culture has permeated popular non-fiction literature. In "The Hidden Influence of Air Quality on Online Behavior" by E. N. Gage (2017), the author explores the subtle ways in which air pollution may shape online interactions, offering a thought-provoking perspective on the unseen hand of smog in the digital realm. Similarly, "Click Bait: The Art and Science of Irresistible Titles" by S. Neer (2019) delves into the intricacies of crafting attention-grabbing titles, providing insights into the allure of provocative language in the age of digital content consumption.
Shifting gears to fictional works, the theme of environmental influence on digital behavior has found its way into the realm of imaginative storytelling. "The Smog's Sinister Secret" by A. Q. Thorn (2016) weaves a tale of intrigue and suspense, where a town's air quality holds a dark secret that manifests in the online realm, captivating readers with its blend of environmental mystery and digital allure. "The Clickbait Conundrum" by R. Lure (2018) takes a lighthearted approach to the connection, presenting a whimsical narrative of mischievous video titles that seem strangely influenced by the town's atmospheric conditions.
In the realm of social media, anecdotal observations and informal discussions have sparked intriguing speculations regarding the correlation at hand. Twitter user @AirQualityGuru mused, "Are we breathing in more than just particles? Could Sevierville's smog be shaping our digital cravings? #AirPollutionMystery." Meanwhile, a Reddit thread titled "Tom Scott's Titles and Tennessee Air – Coincidence or Conspiracy?" garnered attention, with users sharing playful hypotheses and humorous anecdotes about the potential interplay between Sevierville's air quality and YouTube's clickbait culture.
As we navigate the expansive landscape of literature and digital discourse, it is evident that the intersection of air pollution in Sevierville and the captivating titles of Tom Scott's YouTube videos is a topic ripe for exploration. In the following sections, we will spotlight the methodology employed in our investigation, unveil the surprising correlation uncovered in our analysis, and confront the profound implications of a connection that leaves us breathless, both literally and figuratively.

[[RESULTS]]
The statistical analysis of the data collected revealed a strong correlation coefficient of 0.8332200 between air pollution levels in Sevierville, Tennessee, and the provocativeness of Tom Scott's YouTube video titles. This correlation was accompanied by an r-squared value of 0.6942556, indicating that approximately 69.43% of the variability in YouTube clickbait levels could be explained by changes in air pollution. The p-value of less than 0.01 suggests that this relationship is statistically significant.
Figure 1 depicts a scatterplot illustrating the robust association between air pollution levels and the tantalizing allure of YouTube video titles. It's enough to take your breath away – both from the staggering correlation and the realization that a deep breath in Sevierville may indeed lead you to a provocative YouTube rabbit hole.
The results of this analysis certainly leave us breathless, but not just because of the strength of the correlation. The unexpected nature of this connection between air pollution and online clickbait culture is enough to make even the most seasoned researcher gasp for air. As we consider the implications of this unearthed relationship, it's clear that the influence of air quality extends beyond the physical realm, permeating into the digital space in unpredictable ways.
Stay tuned for the following sections, where we will unpack the meaning behind this surprising correlation and explore its potential impact on both environmental and online contexts. In the meantime, take a deep breath and brace yourself for the breathtaking revelations to come.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

In the immortal words of Tom Scott, "Let's dive in and take a deep breath!" Our research has uncovered a captivating connection that intertwines the air we breathe with the titillating allure of YouTube clickbait. While at first glance, the correlation between air pollution in Sevierville, Tennessee, and the provocative titles of Tom Scott's YouTube videos may seem like a mere whimsical hypothesis, our findings provide compelling evidence to support the influence of atmospheric conditions on online content consumption.

Building on the work of Smith et al. (2015) and Doe and Jones (2018), our results substantiate the notion that air quality can indeed play a role in shaping digital engagement. The robust correlation coefficient of 0.8332200 we observed aligns with the subtle influence of smog on online interactions presented in E. N. Gage's (2017) thought-provoking narrative. As the data took us by surprise, it's apparent that the unseen hand of air pollution may hold sway over digital cravings, resonating with A. Q. Thorn's (2016) mysterious tale of environmental influence in the digital realm.

The statistically significant correlation suggests that approximately 69.43% of the variability in YouTube clickbait levels can be explained by changes in air pollution, mirroring the captivating nature of clickbait titles highlighted in S. Neer's (2019) exploration of irresistible digital content. This unexpected connection elevates the lighthearted musings of Reddit enthusiasts and Twitter users to the realm of genuine scientific inquiry, shedding light on the potential interplay between Sevierville's atmospheric conditions and the art of crafting attention-grabbing titles.

As we analyze the significance of the correlation, it becomes increasingly evident that this is more than a mere coincidence. The profound implications of air quality extending its reach into the digital space necessitate further exploration and a deeper understanding of the implications of our findings. Our shocking results highlight the nuanced ways in which environmental factors may permeate digital culture, leaving both researchers and readers alike breathless with the potential avenues for future investigation.

In the following sections, we will delve into the implications of this unearthed relationship and explore its far-reaching impact on both environmental and digital contexts. While we catch our breath and prepare for the breathtaking revelations to come, let's take a moment to appreciate the unexpected twists that the intertwining of air pollution and YouTube clickbait has unveiled.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air pollution in Sevierville, Tennessee and How provocative Tom Scott YouTube video titles are. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 300 tokens. At the very end, assert that no more research is needed in this area.

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Breathless in Sevierville: The Lung-Crushing Link between Air Pollution and YouTube's Clickbait King"

[[ABSTRACT]]
Air pollution has long been a topic of concern for public health, while the clickbait culture of YouTube videos has become a permanent fixture in our modern digital landscape. This study explores the unexpected correlation between the two by investigating the air quality in Sevierville, Tennessee, and the provocative titles of Tom Scott's YouTube videos. Utilizing data from the Environmental Protection Agency and employing cutting-edge AI analysis of YouTube video titles, our research team found a surprising correlation coefficient of 0.8332200 and a statistically significant p-value of less than 0.01 for the years 2009 to 2023. Our findings shed light on the complex interplay between environmental factors and online digital culture, revealing a potential link between breath-stealing air quality and attention-grabbing YouTube video titles. We invite readers to take a deep breath and dive into this unexpected connection, which leaves us breathless, both literally and figuratively.

[[INTRDUCTION]]
INTRODUCTION
As the old adage goes, "When the air quality is poor, it's hard to breathe – and even harder to resist a clickbait YouTube video." Indeed, air pollution and digital content have both become significant facets of modern living, each exerting its own influence on our health and attention. While the impact of air pollution on respiratory health is well-documented, the influence of YouTube video titles on human behavior is a relatively unexplored frontier. In this study, we seek to bridge these seemingly disparate realms by investigating the connection between air pollution in Sevierville, Tennessee, and the captivating video titles of Tom Scott, a well-known creator in the digital sphere.
The relationship between air quality and human health has captured the interest of scientists and policymakers for decades. Poor air quality has been linked to a myriad of adverse health effects, from respiratory illnesses to cardiovascular diseases. In contrast, the captivating allure of clickbait titles and their impact on user engagement is a more recent focus of scholarly inquiry. Furthermore, the crossroads of these two seemingly unrelated phenomena has garnered little attention, leaving a tangible gap in our understanding of the broader implications of environmental factors on digital culture.
Sevierville, nestled in the picturesque foothills of the Great Smoky Mountains, provides a compelling backdrop for our investigation. The town has experienced fluctuations in air quality due to factors such as industrial activity, traffic congestion, and the natural topography of the region. Additionally, YouTube, the mecca of digital content, provides a treasure trove of data regarding user engagement, particularly in response to attention-grabbing titles and thumbnails. By drawing connections between these two disparate domains, we aim to uncover potential insights that may reshape our understanding of how environmental conditions intersect with digital behavior.
As we embark on this inquiry, we are reminded of the paradoxical nature of our modern world – a place where clean air may be at a premium, yet the allure of a captivating video title is just a click away. The intersection of these two realms presents a fertile ground for exploration, where the air may be thick with pollution, yet the data is rich with possibilities. In the following sections, we will elucidate the methods employed in our investigation, unveil the surprising findings that emerged from our analysis, and confront the implications of a connection that leaves us breathless, figuratively and quite possibly, literally.
So, strap on your respirator and, for the love of statistical significance, resist the urge to click on that sensational YouTube video – at least until we've delved deeper into the provocative correlation between Sevierville's air quality and Tom Scott's tantalizing video titles.

[[RESULTS]]
The statistical analysis of the data collected revealed a strong correlation coefficient of 0.8332200 between air pollution levels in Sevierville, Tennessee, and the provocativeness of Tom Scott's YouTube video titles. This correlation was accompanied by an r-squared value of 0.6942556, indicating that approximately 69.43% of the variability in YouTube clickbait levels could be explained by changes in air pollution. The p-value of less than 0.01 suggests that this relationship is statistically significant.
Figure 1 depicts a scatterplot illustrating the robust association between air pollution levels and the tantalizing allure of YouTube video titles. It's enough to take your breath away – both from the staggering correlation and the realization that a deep breath in Sevierville may indeed lead you to a provocative YouTube rabbit hole.
The results of this analysis certainly leave us breathless, but not just because of the strength of the correlation. The unexpected nature of this connection between air pollution and online clickbait culture is enough to make even the most seasoned researcher gasp for air. As we consider the implications of this unearthed relationship, it's clear that the influence of air quality extends beyond the physical realm, permeating into the digital space in unpredictable ways.
Stay tuned for the following sections, where we will unpack the meaning behind this surprising correlation and explore its potential impact on both environmental and online contexts. In the meantime, take a deep breath and brace yourself for the breathtaking revelations to come.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has uncovered a remarkable correlation between air pollution levels in Sevierville, Tennessee, and the titillating titling tactics of Tom Scott on YouTube. The strong statistical significance and robust correlation coefficient underscore the surprising interplay between environmental air quality and digital clickbait culture. It's as if the very air in Sevierville itself is whispering seductive suggestions into the ears of digital content creators, urging them to craft captivating titles that leave viewers breathless with anticipation.

While our findings may seem quite "up in the air," they shed light on the nuanced ways in which environmental factors extend their reach into the realm of cyberspace, shaping our digital experiences in unforeseen ways. This correlation certainly adds a breath of fresh air to the discourse on the impact of air pollution, breathing new life into discussions of its potential influence on online content.

It's worth noting, however, that our data indicates correlation, not causation. To assert that air pollution directly leads to the creation of provocatively titled YouTube videos would be, well, a bit of a stretch. Nonetheless, the unexpected connection we've uncovered invites further exploration and prompts us to take a deep breath and dive into understanding the multifaceted dynamics at play.

In light of these findings, it seems the air in Sevierville isn't the only thing that's provocative – it's also the titles of Tom Scott's videos that are leaving us gasping for breath. As we wrap up this investigation, it's clear that no more respirators or sensational YouTube titles are needed in this area of research. We can confidently exhale, knowing that our work here is done.


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited Breathless in Sevierville: The Lung-Crushing Link between Air Pollution and YouTube's Clickbait King. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Irreverent Air Quality Research


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Breathless in Sevierville: The Lung-Crushing Link between Air Pollution and YouTube's Clickbait King. Respond only with the name of a fictional organization.

ChatGPT:

Society for Atmospheric Health Research and Education (SAHRE)


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Breathless in Sevierville: The Lung-Crushing Link between Air Pollution and YouTube's Clickbait King with an abstract of Air pollution has long been a topic of concern for public health, while the clickbait culture of YouTube videos has become a permanent fixture in our modern digital landscape. This study explores the unexpected correlation between the two by investigating the air quality in Sevierville, Tennessee, and the provocative titles of Tom Scott's YouTube videos. Utilizing data from the Environmental Protection Agency and employing cutting-edge AI analysis of YouTube video titles, our research team found a surprising correlation coefficient of 0.8332200 and a statistically significant p-value of less than 0.01 for the years 2009 to 2023. Our findings shed light on the complex interplay between environmental factors and online digital culture, revealing a potential link between breath-stealing air quality and attention-grabbing YouTube video titles. We invite readers to take a deep breath and dive into this unexpected connection, which leaves us breathless, both literally and figuratively.

ChatGPT:

air pollution, lung health, YouTube clickbait, Sevierville, Tennessee, Tom Scott, environmental impact, public health, air quality data, digital culture, correlation analysis, EPA data, AI analysis, YouTube video titles, statistical significance, environmental factors, online attention, health implications

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

Air pollution in Sevierville, Tennessee
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in Sevierville, TN
Source: Environmental Protection Agency
See what else correlates with Air pollution in Sevierville, Tennessee

How provocative Tom Scott's YouTube video titles are
Detailed data title: How provocative Tom Scott YouTube video titles are, as rated by an AI.
Source: AI analysis of Tom Scott's YouTube video titles
Additional Info: I asked a large language model, 'On a scale of 1-10, how _______ do you think this YouTube video title is?' for every video.

See what else correlates with How provocative Tom Scott's YouTube video titles are

Correlation r = 0.8332200 (Pearson correlation coefficient)
Correlation is a measure of how much the variables move together. If it is 0.99, when one goes up the other goes up. If it is 0.02, the connection is very weak or non-existent. If it is -0.99, then when one goes up the other goes down. If it is 1.00, you probably messed up your correlation function.

r2 = 0.6942556 (Coefficient of determination)
This means 69.4% of the change in the one variable (i.e., How provocative Tom Scott's YouTube video titles are) is predictable based on the change in the other (i.e., Air pollution in Sevierville, Tennessee) over the 15 years from 2009 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00011. 0.0001144643644884170400000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.83 in 0.011% of random cases. Said differently, if you correlated 8,736 random variables Which I absolutely did.
with the same 14 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 14 because we have two variables measured over a period of 15 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.56, 0.94 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!


All values for the years included above: If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
200920102011201220132014201520162017201820192020202120222023
Air pollution in Sevierville, Tennessee (Bad air quality days)0.01369860.07438020.06336090.0136986000.002747250.0083798900.01098900.00275482000.0123457
How provocative Tom Scott's YouTube video titles are (Provacative score)4.10535.5543.78264.02783.83333.55423.52383.84383.69493.754.58824.32693.9811




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."


# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.0136986,0.0743802,0.0633609,0.0136986,0,0,0.00274725,0.00837989,0,0.010989,0,0.00275482,0,0,0.0123457,])
array_2 = np.array([4.1053,5.5,5,4,3.7826,4.0278,3.8333,3.5542,3.5238,3.8438,3.6949,3.75,4.5882,4.3269,3.9811,])
array_1_name = "Air pollution in Sevierville, Tennessee"
array_2_name = "How provocative Tom Scott's YouTube video titles are"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)



Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:


View another random correlation

How fun was this correlation?

I'm genuinely thankful for your rating!


Correlation ID: 4519 · Black Variable ID: 22131 · Red Variable ID: 25462
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0