Download png, svg

AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: Prompt: Generate a photorealistic image depicting a bar graph showcasing the average views of MinuteEarth YouTube videos declining over time. In the background, a line graph represents Vodafone Group's stock price (VOD) following a similar downward trend. Overlay a fading world map to symbolize the diminishing interest in the world's affairs. Ensure the visual is detailed and accurately portrays the decline in views and stock price, with subtle hints of the global context. 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: Average views of MinuteEarth YouTube videos and Vodafone Group's stock price (VOD). 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: Low poly Photorealism A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s Cyber folk Cute cartoon
ChatGPT: Photorealism

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 Average views of MinuteEarth YouTube videos and Vodafone Group's stock price (VOD), in the following situation: As the average views of MinuteEarth YouTube videos dropped, so too did people's interest in the world around them. This led to a decrease in demand for telecommunications services, including Vodafone's, as viewers were no longer phoning a friend to share fascinating Earth facts. The lack of Earth-related conversations meant investors were hanging up on Vodafone, causing a dip in their stock price. Remember, when it comes to stocks and YouTube views, it's a wild, interconnected digital jungle out there!. Keep the description simple.
ChatGPT: A bar graph shows the average views of MinuteEarth YouTube videos steadily decreasing over time, while in the background, a line graph depicts Vodafone Group's stock price (VOD) following a similar downward trend. The visual also features a fading world map in the background, symbolizing the decreasing interest in the world around us.

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: [ Photorealism ] and depicting this scene: A bar graph shows the average views of MinuteEarth YouTube videos steadily decreasing over time, while in the background, a line graph depicts Vodafone Group's stock price (VOD) following a similar downward trend. The visual also features a fading world map in the background, symbolizing the decreasing interest in the world around us. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate a photorealistic image depicting a bar graph showcasing the average views of MinuteEarth YouTube videos declining over time. In the background, a line graph represents Vodafone Group's stock price (VOD) following a similar downward trend. Overlay a fading world map to symbolize the diminishing interest in the world's affairs. Ensure the visual is detailed and accurately portrays the decline in views and stock price, with subtle hints of the global context.

---

*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.

AI academic paper

Vodafun: Exploring the Link between MinuteEarth YouTube Views and Vodafone Group's Stock Price The Journal of Internet Trends and Market Analysis Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? Average views of MinuteEarth YouTube videos Vodafone Group's stock price (VOD) Neither / both
Issue:	What is the issue? The data is incorrect The chart isn't displaying properly There is a typo The source link is incorrect A calculation is wrong Something else
Additional details: Optional
Confirm you are a human:

Data details

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^Note 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^Note 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.

Try it yourself

# 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([1902610,3441890,1916100,1768780,1902370,1183210,727372,625927,914398,511353,302271,])
array_2 = np.array([47.23,71.5,34.08,32.12,24.84,32.16,19.3,19.38,17.04,15.2,10.29,])
array_1_name = "Average views of MinuteEarth YouTube videos"
array_2_name = "Vodafone Group's stock price (VOD)"

# 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

• High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.
  
  If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.
  
  Alternatively you can use a tool like Inkscape.
  
• High resolution line chart, optimized for mobile
• Alternative high resolution line chart
• Scatterplot
• Portable line chart (png)
• Portable line chart (png), optimized for mobile
• Line chart for only Average views of MinuteEarth YouTube videos
• Line chart for only Vodafone Group's stock price (VOD)
• AI-generated correlation image
• The spurious research paper: Vodafun: Exploring the Link between MinuteEarth YouTube Views and Vodafone Group's Stock Price