about · email me · subscribe
Spurious correlation #4,754 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is US Bottled Water Consumption per Person and the second variable is Average number of comments on SmarterEveryDay YouTube videos.  The chart goes from 2007 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the nation drank their way to hydration, the collective thirst for knowledge also grew. This led to a spike in cerebral activity, as people became H2O-bsessed with learning and sharing their thoughts. It seems the more water Americans guzzle, the more they comment, quenching their intellectual thirst and creating a ripple effect of engagement. Truly, the comment section has become a well of wisdom, all thanks to the bottle-up trend of water consumption. Could it be that the secret to sparking discussions lies in a profound connection between water and w-comments? One thing’s clear - this correlation is making waves in the world of online learning, and audiences are simply soaking it all in!

Model: dalle-3
Prompt: Create an image illustrating a scene where a diverse group of people huddles around a water cooler, each holding a bottled water and engrossed in conversations. Overhead, a screen displays a SmarterEveryDay YouTube video, with the comment section overflowing with engaging comments. As the individuals drink water, their intellectual curiosity sparks lively discussions, creating a symbiotic relationship between hydration and online engagement. The ambiance is vibrant and dynamic, capturing the fusion of physical and virtual interactions. 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: US Bottled Water Consumption per Person and Average number of comments on SmarterEveryDay YouTube videos. 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: An image that looks like it is a scene from 'Star Wars' Magic realism Minimalism Hyper-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 US Bottled Water Consumption per Person and Average number of comments on SmarterEveryDay YouTube videos, in the following situation: As the nation drank their way to hydration, the collective thirst for knowledge also grew. This led to a spike in cerebral activity, as people became H2O-bsessed with learning and sharing their thoughts. It seems the more water Americans guzzle, the more they comment, quenching their intellectual thirst and creating a ripple effect of engagement. Truly, the comment section has become a well of wisdom, all thanks to the bottle-up trend of water consumption. Could it be that the secret to sparking discussions lies in a profound connection between water and w-comments? One thing’s clear - this correlation is making waves in the world of online learning, and audiences are simply soaking it all in!. Keep the description simple.
ChatGPT: A crowd of people surrounds a water cooler, each person holding a bottled water and engaged in lively conversation. Above them, a screen displays a SmarterEveryDay YouTube video with the comment section overflowing with numerous thoughtful and engaging comments. As the people drink water, their intellectual curiosity sparks animated discussions, creating a symbiotic relationship between hydration and online engagement.

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: A crowd of people surrounds a water cooler, each person holding a bottled water and engaged in lively conversation. Above them, a screen displays a SmarterEveryDay YouTube video with the comment section overflowing with numerous thoughtful and engaging comments. As the people drink water, their intellectual curiosity sparks animated discussions, creating a symbiotic relationship between hydration and online engagement. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image illustrating a scene where a diverse group of people huddles around a water cooler, each holding a bottled water and engrossed in conversations. Overhead, a screen displays a SmarterEveryDay YouTube video, with the comment section overflowing with engaging comments. As the individuals drink water, their intellectual curiosity sparks lively discussions, creating a symbiotic relationship between hydration and online engagement. The ambiance is vibrant and dynamic, capturing the fusion of physical and virtual interactions.

*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 an increase in US Bottled Water Consumption per Person caused Average number of comments on SmarterEveryDay YouTube videos to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
H2O and Hilarity: Unearthing the Aquatic Quirk in Digital Discourse

Journal of Aquatic Linguistics

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 witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 US Bottled Water Consumption per Person and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, just make it sound clever.

Your research team used data from Statista and YouTube to assess this nagging question. You found a correlation coefficient of 0.9069810 and p < 0.01 for 2007 to 2022.

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]]
H2O and Hilarity: Unearthing the Aquatic Quirk in Digital Discourse

[[ABSTRACT]]
This paper seeks to delve into the unexplored nexus between the consumption of bottled water in the United States and the average number of comments on SmarterEveryDay YouTube videos. Through meticulous analysis of data obtained from Statista and YouTube covering the time span from 2007 to 2022, we have unearthed a surprising correlation coefficient of 0.9069810 with a p-value less than 0.01. Our findings not only shed light on the unexpected synchronization between hydration habits and online engagement but also offer tantalizing implications for the relationship between liquid refreshment and cognitive interaction in the digital sphere. In uncovering this delightful avenue of investigation, we can't help but remark on the bubbling excitement that comes with unraveling the enchanting quirkiness of human behavior.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 US Bottled Water Consumption per Person and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
H2O and Hilarity: Unearthing the Aquatic Quirk in Digital Discourse

[[ABSTRACT]]
This paper seeks to delve into the unexplored nexus between the consumption of bottled water in the United States and the average number of comments on SmarterEveryDay YouTube videos. Through meticulous analysis of data obtained from Statista and YouTube covering the time span from 2007 to 2022, we have unearthed a surprising correlation coefficient of 0.9069810 with a p-value less than 0.01. Our findings not only shed light on the unexpected synchronization between hydration habits and online engagement but also offer tantalizing implications for the relationship between liquid refreshment and cognitive interaction in the digital sphere. In uncovering this delightful avenue of investigation, we can't help but remark on the bubbling excitement that comes with unraveling the enchanting quirkiness of human behavior.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The intersection of water consumption and online engagement may seem as incongruous as fish riding bicycles, but as the adage goes, "truth is often stranger than fiction." In the digital age, where conversations flow as freely as a mountain spring and attention spans ebb and flow like the tides, understanding the link between our liquid libations and the virtual discourse that surrounds us has become an intriguing and, dare I say, refreshing topic of inquiry.

The siren song of social media has captivated researchers and analysts alike, with its lures of endless data and countless hours of scrolling through memes and cat videos in the name of "research." In this sea of digital content, the YouTube platform stands out as a veritable ocean of knowledge and amusement. Within this ocean, the SmarterEveryDay channel stands as a beacon of learning and exploration, where science and curiosity collide in a delightful display of online edutainment.

On the other hand, bottled water, with its pristine packaging and claims of "purity," has become a ubiquitous companion in the daily lives of many Americans. From busy professionals to fitness enthusiasts to those who simply prefer their H2O on-the-go, bottled water has carved out its own niche in the beverage market, buoyed by a wave of health-conscious consumers and environmental concerns.

To attempt to unravel the connection between these seemingly disparate elements – bottled water consumption and the number of comments on a YouTube channel dedicated to science – may sound like an academic exercise in frivolity. However, as we dive into the depths of this endeavor, we will reveal the buoyancy of this correlation and the undercurrent of implications it carries for our understanding of human behavior and digital interactions.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 US Bottled Water Consumption per Person and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
H2O and Hilarity: Unearthing the Aquatic Quirk in Digital Discourse

[[ABSTRACT]]
This paper seeks to delve into the unexplored nexus between the consumption of bottled water in the United States and the average number of comments on SmarterEveryDay YouTube videos. Through meticulous analysis of data obtained from Statista and YouTube covering the time span from 2007 to 2022, we have unearthed a surprising correlation coefficient of 0.9069810 with a p-value less than 0.01. Our findings not only shed light on the unexpected synchronization between hydration habits and online engagement but also offer tantalizing implications for the relationship between liquid refreshment and cognitive interaction in the digital sphere. In uncovering this delightful avenue of investigation, we can't help but remark on the bubbling excitement that comes with unraveling the enchanting quirkiness of human behavior.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of water consumption and online engagement may seem as incongruous as fish riding bicycles, but as the adage goes, "truth is often stranger than fiction." In the digital age, where conversations flow as freely as a mountain spring and attention spans ebb and flow like the tides, understanding the link between our liquid libations and the virtual discourse that surrounds us has become an intriguing and, dare I say, refreshing topic of inquiry.
The siren song of social media has captivated researchers and analysts alike, with its lures of endless data and countless hours of scrolling through memes and cat videos in the name of "research." In this sea of digital content, the YouTube platform stands out as a veritable ocean of knowledge and amusement. Within this ocean, the SmarterEveryDay channel stands as a beacon of learning and exploration, where science and curiosity collide in a delightful display of online edutainment.
On the other hand, bottled water, with its pristine packaging and claims of "purity," has become a ubiquitous companion in the daily lives of many Americans. From busy professionals to fitness enthusiasts to those who simply prefer their H2O on-the-go, bottled water has carved out its own niche in the beverage market, buoyed by a wave of health-conscious consumers and environmental concerns.
To attempt to unravel the connection between these seemingly disparate elements – bottled water consumption and the number of comments on a YouTube channel dedicated to science – may sound like an academic exercise in frivolity. However, as we dive into the depths of this endeavor, we will reveal the buoyancy of this correlation and the undercurrent of implications it carries for our understanding of human behavior and digital interactions.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The relationship between bottled water consumption and digital engagement has, until now, remained as clear as...well, bottled water. At first glance, the act of hydrating oneself with a refreshing bottle of H2O and the fervent exchange of comments on SmarterEveryDay YouTube videos seem as unrelated as an octopus at a tea party. However, as we delve into the murky waters of literature on the subject, we begin to unravel a tapestry of unexpected connections and intriguing correlations.

Smith et al. (2015) provide a foundational understanding of the bottled water market in the United States, offering insights into the patterns of consumption and the factors driving its proliferation. This work lays the groundwork for our exploration into the societal and cultural undercurrents that shape individuals' beverage choices. Doe and Jones (2018) similarly examine the environmental implications of bottled water consumption, highlighting the tension between convenience and sustainability in a world fraught with plastic waste.

Venturing into the realm of digital engagement, "Engaging Online: Strategies for Captivating Your Audience" by White (2017) offers a comprehensive overview of the dynamics of online interactions and the factors that drive user engagement. Yet, as we navigate through these scholarly seas, our narrative takes a turn toward the whimsical and unexpected.

Drawing inspiration from the source water of knowledge found in non-fiction literature, we embark on a journey through the bibliographic seas. Behold, "The Secret Life of Water" by Pollack (2019), an exploration into the mystical properties of this life-giving substance that leaves no stone unturned, no drop unexamined. Could this work hold the key to unlocking the enigmatic connection between bottled water consumption and digital discourse? Well, the truth may just flow like a river.

As we chart a course toward unconventional sources, we encounter the likes of "The Water Dancer" by Coates (2019) and "The Ocean at the End of the Lane" by Gaiman (2013), literary works that may not directly address our research questions, but certainly evoke a sense of aquatic intrigue and the depths of human experience. The overlap between these narratives and our investigation may seem as tenuous as a castaway clinging to a barrel, yet we cannot underestimate the serendipitous currents that may guide our understanding of this peculiar juxtaposition.

In our quest for connections, we also draw inspiration from the world of board games, where the game "Bananagrams" may seem as disconnected from our topic as a pineapple is from a pizza, but it serves as a reminder that unexpected pairings can result in delightful discoveries.

In the grand tradition of academic research, we find ourselves floating in uncharted waters, captivated by the inexplicable fusion of liquid sustenance and digital dialogue. As we press on in our investigation, we do so with an open heart and a sense of wonder, for in unraveling the aqua-comical quirk between consumption and commentary, we may yet discover the refreshing splash of insight and the buoyancy of the human spirit in online realms.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 US Bottled Water Consumption per Person and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Statista and YouTube . You used data from 2007 to 2022

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]]
H2O and Hilarity: Unearthing the Aquatic Quirk in Digital Discourse

[[ABSTRACT]]
This paper seeks to delve into the unexplored nexus between the consumption of bottled water in the United States and the average number of comments on SmarterEveryDay YouTube videos. Through meticulous analysis of data obtained from Statista and YouTube covering the time span from 2007 to 2022, we have unearthed a surprising correlation coefficient of 0.9069810 with a p-value less than 0.01. Our findings not only shed light on the unexpected synchronization between hydration habits and online engagement but also offer tantalizing implications for the relationship between liquid refreshment and cognitive interaction in the digital sphere. In uncovering this delightful avenue of investigation, we can't help but remark on the bubbling excitement that comes with unraveling the enchanting quirkiness of human behavior.

[[INTRODUCTION]]
The intersection of water consumption and online engagement may seem as incongruous as fish riding bicycles, but as the adage goes, "truth is often stranger than fiction." In the digital age, where conversations flow as freely as a mountain spring and attention spans ebb and flow like the tides, understanding the link between our liquid libations and the virtual discourse that surrounds us has become an intriguing and, dare I say, refreshing topic of inquiry.
The siren song of social media has captivated researchers and analysts alike, with its lures of endless data and countless hours of scrolling through memes and cat videos in the name of "research." In this sea of digital content, the YouTube platform stands out as a veritable ocean of knowledge and amusement. Within this ocean, the SmarterEveryDay channel stands as a beacon of learning and exploration, where science and curiosity collide in a delightful display of online edutainment.
On the other hand, bottled water, with its pristine packaging and claims of "purity," has become a ubiquitous companion in the daily lives of many Americans. From busy professionals to fitness enthusiasts to those who simply prefer their H2O on-the-go, bottled water has carved out its own niche in the beverage market, buoyed by a wave of health-conscious consumers and environmental concerns.
To attempt to unravel the connection between these seemingly disparate elements – bottled water consumption and the number of comments on a YouTube channel dedicated to science – may sound like an academic exercise in frivolity. However, as we dive into the depths of this endeavor, we will reveal the buoyancy of this correlation and the undercurrent of implications it carries for our understanding of human behavior and digital interactions.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To navigate the murky waters of uncovering the aquatic quirk in digital discourse, our research team embarked on a quest resembling a scientific scavenger hunt across the vast expanse of the internet. We traversed the digital seas, charting a course through the virtual ocean of data provided by Statista and the YouTube platform, all in pursuit of unraveling the enigmatic relationship between U.S. bottled water consumption per person and the average number of comments on SmarterEveryDay YouTube videos.

Our data collection journey commenced at the precipice of 2007, a time when YouTube was still in its infancy, much like a newborn sea turtle embarking on its inaugural voyage. With the agility of marine biologists studying the ebb and flow of tides, we meticulously gathered data over the years, fervently tracking the fluctuations in both bottled water consumption and the lively comments that ebbed and flowed beneath the SmarterEveryDay videos. We were particularly mindful of any data anomalies, recognizing that just as the path of a meandering river can be obstructed by unforeseen obstacles, our data may also encounter unexpected currents along the way.

The statistical analyses that followed mirrored the craftsmanship of a skilled shipwright, as we constructed complex models and charts to unveil the underlying patterns and correlations. Employing sophisticated analytical software, we calculated the correlation coefficient with precision, channeling the spirit of a seasoned captain navigating treacherous waters to reveal the astonishingly high correlation coefficient of 0.9069810, with a p-value that summoned a collective gasp from the research team when it dipped below 0.01.

Sailing through vast data oceans and wrestling with statistical krakens was not without its perils, and at times, the allure of swiftly quenching our thirst with a swig of bottled water was challenging to resist. Nevertheless, in sailing through these digital currents, we remained resolute and emerged with a treasure trove of findings that not only piqued our interest but also offered uncharted insights into the whimsical dance between hydration habits and online engagement.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 US Bottled Water Consumption per Person and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Statista and YouTube .

For the time period 2007 to 2022, you found a correlation 0.9069810, r-squared of 0.8226145, 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]]
H2O and Hilarity: Unearthing the Aquatic Quirk in Digital Discourse

[[ABSTRACT]]
This paper seeks to delve into the unexplored nexus between the consumption of bottled water in the United States and the average number of comments on SmarterEveryDay YouTube videos. Through meticulous analysis of data obtained from Statista and YouTube covering the time span from 2007 to 2022, we have unearthed a surprising correlation coefficient of 0.9069810 with a p-value less than 0.01. Our findings not only shed light on the unexpected synchronization between hydration habits and online engagement but also offer tantalizing implications for the relationship between liquid refreshment and cognitive interaction in the digital sphere. In uncovering this delightful avenue of investigation, we can't help but remark on the bubbling excitement that comes with unraveling the enchanting quirkiness of human behavior.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intersection of water consumption and online engagement may seem as incongruous as fish riding bicycles, but as the adage goes, "truth is often stranger than fiction." In the digital age, where conversations flow as freely as a mountain spring and attention spans ebb and flow like the tides, understanding the link between our liquid libations and the virtual discourse that surrounds us has become an intriguing and, dare I say, refreshing topic of inquiry.
The siren song of social media has captivated researchers and analysts alike, with its lures of endless data and countless hours of scrolling through memes and cat videos in the name of "research." In this sea of digital content, the YouTube platform stands out as a veritable ocean of knowledge and amusement. Within this ocean, the SmarterEveryDay channel stands as a beacon of learning and exploration, where science and curiosity collide in a delightful display of online edutainment.
On the other hand, bottled water, with its pristine packaging and claims of "purity," has become a ubiquitous companion in the daily lives of many Americans. From busy professionals to fitness enthusiasts to those who simply prefer their H2O on-the-go, bottled water has carved out its own niche in the beverage market, buoyed by a wave of health-conscious consumers and environmental concerns.
To attempt to unravel the connection between these seemingly disparate elements – bottled water consumption and the number of comments on a YouTube channel dedicated to science – may sound like an academic exercise in frivolity. However, as we dive into the depths of this endeavor, we will reveal the buoyancy of this correlation and the undercurrent of implications it carries for our understanding of human behavior and digital interactions.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis of the relationship between US bottled water consumption per person and the average number of comments on SmarterEveryDay YouTube videos yielded intriguing results. Across the time period from 2007 to 2022, we identified a robust correlation coefficient of 0.9069810, indicating a strong positive association between these two ostensibly unrelated variables. This correlation was accompanied by an r-squared value of 0.8226145, affirming that a substantial proportion of the variation in YouTube comments can be elucidated by fluctuations in bottled water consumption. Moreover, the p-value of less than 0.01 attests to the statistical significance of this finding, providing compelling evidence to support our exploration into the aquatic whimsy of digital dialogue.

Furthermore, the inclusion of a scatterplot (Fig. 1) visually illustrates the pronounced correlation observed between US bottled water consumption per person and the average number of comments on SmarterEveryDay YouTube videos. The scatterplot tactfully showcases the clustering of data points, painting a vivid picture of the harmonious dance between hydration habits and online engagement. It serves as a gentle reminder that even in the realm of statistical analysis, there's always room for a splash of creativity and visual appeal.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 US Bottled Water Consumption per Person and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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]]
H2O and Hilarity: Unearthing the Aquatic Quirk in Digital Discourse

[[ABSTRACT]]
This paper seeks to delve into the unexplored nexus between the consumption of bottled water in the United States and the average number of comments on SmarterEveryDay YouTube videos. Through meticulous analysis of data obtained from Statista and YouTube covering the time span from 2007 to 2022, we have unearthed a surprising correlation coefficient of 0.9069810 with a p-value less than 0.01. Our findings not only shed light on the unexpected synchronization between hydration habits and online engagement but also offer tantalizing implications for the relationship between liquid refreshment and cognitive interaction in the digital sphere. In uncovering this delightful avenue of investigation, we can't help but remark on the bubbling excitement that comes with unraveling the enchanting quirkiness of human behavior.

[[LITERATURE REVIEW]]
The relationship between bottled water consumption and digital engagement has, until now, remained as clear as...well, bottled water. At first glance, the act of hydrating oneself with a refreshing bottle of H2O and the fervent exchange of comments on SmarterEveryDay YouTube videos seem as unrelated as an octopus at a tea party. However, as we delve into the murky waters of literature on the subject, we begin to unravel a tapestry of unexpected connections and intriguing correlations.
Smith et al. (2015) provide a foundational understanding of the bottled water market in the United States, offering insights into the patterns of consumption and the factors driving its proliferation. This work lays the groundwork for our exploration into the societal and cultural undercurrents that shape individuals' beverage choices. Doe and Jones (2018) similarly examine the environmental implications of bottled water consumption, highlighting the tension between convenience and sustainability in a world fraught with plastic waste.
Venturing into the realm of digital engagement, "Engaging Online: Strategies for Captivating Your Audience" by White (2017) offers a comprehensive overview of the dynamics of online interactions and the factors that drive user engagement. Yet, as we navigate through these scholarly seas, our narrative takes a turn toward the whimsical and unexpected.
Drawing inspiration from the source water of knowledge found in non-fiction literature, we embark on a journey through the bibliographic seas. Behold, "The Secret Life of Water" by Pollack (2019), an exploration into the mystical properties of this life-giving substance that leaves no stone unturned, no drop unexamined. Could this work hold the key to unlocking the enigmatic connection between bottled water consumption and digital discourse? Well, the truth may just flow like a river.
As we chart a course toward unconventional sources, we encounter the likes of "The Water Dancer" by Coates (2019) and "The Ocean at the End of the Lane" by Gaiman (2013), literary works that may not directly address our research questions, but certainly evoke a sense of aquatic intrigue and the depths of human experience. The overlap between these narratives and our investigation may seem as tenuous as a castaway clinging to a barrel, yet we cannot underestimate the serendipitous currents that may guide our understanding of this peculiar juxtaposition.
In our quest for connections, we also draw inspiration from the world of board games, where the game "Bananagrams" may seem as disconnected from our topic as a pineapple is from a pizza, but it serves as a reminder that unexpected pairings can result in delightful discoveries.
In the grand tradition of academic research, we find ourselves floating in uncharted waters, captivated by the inexplicable fusion of liquid sustenance and digital dialogue. As we press on in our investigation, we do so with an open heart and a sense of wonder, for in unraveling the aqua-comical quirk between consumption and commentary, we may yet discover the refreshing splash of insight and the buoyancy of the human spirit in online realms.

[[RESULTS]]
The statistical analysis of the relationship between US bottled water consumption per person and the average number of comments on SmarterEveryDay YouTube videos yielded intriguing results. Across the time period from 2007 to 2022, we identified a robust correlation coefficient of 0.9069810, indicating a strong positive association between these two ostensibly unrelated variables. This correlation was accompanied by an r-squared value of 0.8226145, affirming that a substantial proportion of the variation in YouTube comments can be elucidated by fluctuations in bottled water consumption. Moreover, the p-value of less than 0.01 attests to the statistical significance of this finding, providing compelling evidence to support our exploration into the aquatic whimsy of digital dialogue.
Furthermore, the inclusion of a scatterplot (Fig. 1) visually illustrates the pronounced correlation observed between US bottled water consumption per person and the average number of comments on SmarterEveryDay YouTube videos. The scatterplot tactfully showcases the clustering of data points, painting a vivid picture of the harmonious dance between hydration habits and online engagement. It serves as a gentle reminder that even in the realm of statistical analysis, there's always room for a splash of creativity and visual appeal.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study have brought to light a truly unexpected and slightly absurd relationship between two seemingly disparate phenomena: US bottled water consumption per person and the average number of comments on SmarterEveryDay YouTube videos. Our results have not only supported the prior research but also expanded upon it, illustrating the remarkable synchronicity between liquid consumption and digital discourse.

First and foremost, our analysis corroborates the work of Smith et al. (2015) by demonstrating a substantial positive correlation between bottled water consumption and online engagement. While the relationship may appear as outlandish as a fish riding a bicycle, our findings lend empirical support to Smith et al.'s groundwork in understanding the societal factors influencing beverage choices. It seems that the act of staying hydrated may also lead to a heightened propensity for engaging in online conversations, suggesting that the flow of H2O may indeed fuel the flow of digital dialogue.

Similarly, the unexpected parallels with the bibliographic seas we explored during our literature review cannot be discounted. While some may scoff at the idea of drawing inspiration from "The Secret Life of Water" by Pollack (2019) in our investigation, our results suggest that perhaps there is a mystical connection between the properties of water and the dynamics of digital engagement.

Not to be overlooked are the board game of "Bananagrams" and the literary works of Coates (2019) and Gaiman (2013). While these sources may have superficially appeared as tangential to our research questions, our findings imply that there may be hidden depths to these supposedly frivolous connections. The unexpected pairings have indeed resulted in a delightful and illuminating discovery, leaving us reminiscent of the old adage that sometimes truth is stranger than fiction.

The scatterplot presented in our results (Fig. 1) not only serves as a visual representation of our correlation but also highlights the need to inject creativity and visual appeal into statistical analysis. After all, who says a scatterplot can't also serve as a canvas for artistic expression? In our exploration of this uncharted territory, we have found that there is always room for a touch of whimsy in the staid world of research.

In conclusion, our findings have unearthed a delightfully quirky alliance between liquid refreshment and digital discourse, a serendipitous connection that invites further investigation into the whimsical nuances of human behavior. As we wade through the waters of academia, we do so with a buoyant spirit and an openness to the unexpected, for it is in the most unlikely places that we may find the refreshing splash of insight.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 US Bottled Water Consumption per Person and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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]]
H2O and Hilarity: Unearthing the Aquatic Quirk in Digital Discourse

[[ABSTRACT]]
This paper seeks to delve into the unexplored nexus between the consumption of bottled water in the United States and the average number of comments on SmarterEveryDay YouTube videos. Through meticulous analysis of data obtained from Statista and YouTube covering the time span from 2007 to 2022, we have unearthed a surprising correlation coefficient of 0.9069810 with a p-value less than 0.01. Our findings not only shed light on the unexpected synchronization between hydration habits and online engagement but also offer tantalizing implications for the relationship between liquid refreshment and cognitive interaction in the digital sphere. In uncovering this delightful avenue of investigation, we can't help but remark on the bubbling excitement that comes with unraveling the enchanting quirkiness of human behavior.

[[INTRDUCTION]]
The intersection of water consumption and online engagement may seem as incongruous as fish riding bicycles, but as the adage goes, "truth is often stranger than fiction." In the digital age, where conversations flow as freely as a mountain spring and attention spans ebb and flow like the tides, understanding the link between our liquid libations and the virtual discourse that surrounds us has become an intriguing and, dare I say, refreshing topic of inquiry.
The siren song of social media has captivated researchers and analysts alike, with its lures of endless data and countless hours of scrolling through memes and cat videos in the name of "research." In this sea of digital content, the YouTube platform stands out as a veritable ocean of knowledge and amusement. Within this ocean, the SmarterEveryDay channel stands as a beacon of learning and exploration, where science and curiosity collide in a delightful display of online edutainment.
On the other hand, bottled water, with its pristine packaging and claims of "purity," has become a ubiquitous companion in the daily lives of many Americans. From busy professionals to fitness enthusiasts to those who simply prefer their H2O on-the-go, bottled water has carved out its own niche in the beverage market, buoyed by a wave of health-conscious consumers and environmental concerns.
To attempt to unravel the connection between these seemingly disparate elements – bottled water consumption and the number of comments on a YouTube channel dedicated to science – may sound like an academic exercise in frivolity. However, as we dive into the depths of this endeavor, we will reveal the buoyancy of this correlation and the undercurrent of implications it carries for our understanding of human behavior and digital interactions.

[[RESULTS]]
The statistical analysis of the relationship between US bottled water consumption per person and the average number of comments on SmarterEveryDay YouTube videos yielded intriguing results. Across the time period from 2007 to 2022, we identified a robust correlation coefficient of 0.9069810, indicating a strong positive association between these two ostensibly unrelated variables. This correlation was accompanied by an r-squared value of 0.8226145, affirming that a substantial proportion of the variation in YouTube comments can be elucidated by fluctuations in bottled water consumption. Moreover, the p-value of less than 0.01 attests to the statistical significance of this finding, providing compelling evidence to support our exploration into the aquatic whimsy of digital dialogue.
Furthermore, the inclusion of a scatterplot (Fig. 1) visually illustrates the pronounced correlation observed between US bottled water consumption per person and the average number of comments on SmarterEveryDay YouTube videos. The scatterplot tactfully showcases the clustering of data points, painting a vivid picture of the harmonious dance between hydration habits and online engagement. It serves as a gentle reminder that even in the realm of statistical analysis, there's always room for a splash of creativity and visual appeal.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the peculiar relationship between US bottled water consumption per person and the average number of comments on SmarterEveryDay YouTube videos has yielded noteworthy insights. The remarkably strong positive correlation coefficient of 0.9069810, coupled with the visually captivating scatterplot, emphasizes the unexpected synchronicity between hydration habits and digital discourse. We can't help but marvel at the fluidity of this association, highlighting the ripple effect of liquid refreshment on virtual interactions.

As we wrap up our analysis, it's clear that this correlation, like a well-constructed H2O molecule, holds its structure across the expansive temporal landscape from 2007 to 2022. The robust r-squared value underlines the substantial explanatory power of bottled water consumption over the ebb and flow of comments on SmarterEveryDay's YouTube content. This dynamic interplay imparts a buoyant optimism as we navigate the depths of human behavior and online engagement, showcasing the fascinating interplay between the aqueous and the amusing.

In traversing this uncharted terrain, we've uncovered a tale as old as time, or at least as old as the internet – the unlikely dance of aqua and antics, fluidity and fun. This novel avenue of inquiry underscores the refreshing, dare we say, sparkling nature of statistical exploration, reminding us that, in the vast ocean of data, unexpected correlations can emerge like hidden treasures waiting to be discovered.

As we hoist our academic anchors, it is with a sense of whimsy and wonder that we assert the sufficiency of this inquiry. Like a bottle of perfectly chilled water on a scorching day, the relationship between US bottled water consumption and SmarterEveryDay YouTube comments appears to have quenched our thirst for knowledge in this domain. Further research in this area seems as unnecessary as a lifeguard at a synchronized swimming competition. With that said, we firmly conclude that the aquatic quirk in digital discourse has been thoroughly plumbed, leaving us all a bit more buoyant and bemused in the process.


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 H2O and Hilarity: Unearthing the Aquatic Quirk in Digital Discourse. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Aquatic Linguistics


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 H2O and Hilarity: Unearthing the Aquatic Quirk in Digital Discourse. Respond only with the name of a fictional organization.

ChatGPT:

Humor in Hydrology Society


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 H2O and Hilarity: Unearthing the Aquatic Quirk in Digital Discourse with an abstract of This paper seeks to delve into the unexplored nexus between the consumption of bottled water in the United States and the average number of comments on SmarterEveryDay YouTube videos. Through meticulous analysis of data obtained from Statista and YouTube covering the time span from 2007 to 2022, we have unearthed a surprising correlation coefficient of 0.9069810 with a p-value less than 0.01. Our findings not only shed light on the unexpected synchronization between hydration habits and online engagement but also offer tantalizing implications for the relationship between liquid refreshment and cognitive interaction in the digital sphere. In uncovering this delightful avenue of investigation, we can't help but remark on the bubbling excitement that comes with unraveling the enchanting quirkiness of human behavior.

ChatGPT:

bottled water consumption, United States, YouTube comments, correlation coefficient, Statista data, digital discourse, liquid refreshment, online engagement, cognitive interaction, hydration habits

*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

US Bottled Water Consumption per Person
Source: Statista
See what else correlates with US Bottled Water Consumption per Person

Average number of comments on SmarterEveryDay YouTube videos
Detailed data title: Average number of comments on SmarterEveryDay YouTube videos.
Source: SmarterEveryDay on YouTube
See what else correlates with Average number of comments on SmarterEveryDay YouTube videos

Correlation r = 0.9069810 (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 = 0.8226145 (Coefficient of determination)
This means 82.3% of the change in the one variable (i.e., Average number of comments on SmarterEveryDay YouTube videos) is predictable based on the change in the other (i.e., US Bottled Water Consumption per Person) over the 16 years from 2007 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.3E-6. 0.0000012596968446356639000000
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 0.91 in 0.00013% of random cases. Said differently, if you correlated 793,842 random variables You don't actually need 793 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 15 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 15 because we have two variables measured over a period of 16 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.

[ 0.75, 0.97 ] 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.
2007200820092010201120122013201420152016201720182019202020212022
US Bottled Water Consumption per Person (Gallons)2928.527.628.329.230.83234.136.5394242.34445.24746.5
Average number of comments on SmarterEveryDay YouTube videos (Average Comments)128.182241.7569274.938593.0181532.182997.093635.575163.575374.064361.055659.878626.7310755.39945.564831.92




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([29,28.5,27.6,28.3,29.2,30.8,32,34.1,36.5,39,42,42.3,44,45.2,47,46.5,])
array_2 = np.array([128.182,241.75,69,274.938,593.018,1532.18,2997.09,3635.57,5163.57,5374.06,4361.05,5659.87,8626.73,10755.3,9945.56,4831.92,])
array_1_name = "US Bottled Water Consumption per Person"
array_2_name = "Average number of comments on SmarterEveryDay YouTube videos"

# 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?

You're the correlation whisperer we needed!


Correlation ID: 4754 · Black Variable ID: 32 · Red Variable ID: 25492
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0