Download png, svg

AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: [ Concept art ] Generate an image showcasing a graduation ceremony for Communication and Journalism students. The scene should depict graduates receiving their Bachelor's degrees and being handed microphones and diplomas. As the graduates begin their careers, they are seen producing captivating news articles and dynamic radio segments. Show them engaging with complex mathematical concepts and weaving calculus and linear algebra into their work. Additionally, depict an increase in the number of likes on 3Blue1Brown's YouTube videos, symbolizing a growing appreciation for math content. Capture the positive impact of effective communication skills on the appreciation and engagement with math education. Keep the visual simple, with emphasis on the graduates' actions and their influence on the audience. 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: Bachelor's degrees awarded in Communication, journalism, and related programs and Total likes of 3Blue1Brown 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: A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s Vaporwave 3D Pixar Style Concept art Cyber folk
ChatGPT: Concept art

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 Bachelor's degrees awarded in Communication, journalism, and related programs and Total likes of 3Blue1Brown YouTube videos, in the following situation: As the number of Communication and Journalism graduates rose, so did the nation's collective ability to effectively convey complex mathematical concepts. These skilled individuals subtly wove the beauty of calculus and linear algebra into their news articles and radio segments, unknowingly cultivating a growing appreciation for 3Blue1Brown's content. With each perfectly crafted sentence and impeccably timed broadcast, they were unknowingly nudging more and more people towards hitting that 'like' button on those mind-boggling math videos. It's almost as if the derivative of their communication skills with respect to 3Blue1Brown's content was always positive! Could the solution to engaging math education be as simple as hiring more journalism graduates? It's a story that adds up, no matter how you angle it.. Keep the description simple.
ChatGPT: A graduation ceremony for Communication and Journalism students is taking place. As each graduate receives their Bachelor's degree, they are handed a microphone and a diploma. Over the next few days, these graduates begin their careers, producing captivating news articles and dynamic radio segments. Throughout the country, people start to engage more with complex mathematical concepts, thanks to the elegant and skillful weaving of calculus and linear algebra into the graduates' work. Meanwhile, the number of likes on 3Blue1Brown's YouTube videos steadily increases, as more and more individuals appreciate the mesmerizing math content being presented. The scene symbolizes the positive impact that effective communication skills have on the appreciation and engagement with math education.

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: [ Concept art ] and depicting this scene: A graduation ceremony for Communication and Journalism students is taking place. As each graduate receives their Bachelor's degree, they are handed a microphone and a diploma. Over the next few days, these graduates begin their careers, producing captivating news articles and dynamic radio segments. Throughout the country, people start to engage more with complex mathematical concepts, thanks to the elegant and skillful weaving of calculus and linear algebra into the graduates' work. Meanwhile, the number of likes on 3Blue1Brown's YouTube videos steadily increases, as more and more individuals appreciate the mesmerizing math content being presented. The scene symbolizes the positive impact that effective communication skills have on the appreciation and engagement with math education. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ Concept art ] Generate an image showcasing a graduation ceremony for Communication and Journalism students. The scene should depict graduates receiving their Bachelor's degrees and being handed microphones and diplomas. As the graduates begin their careers, they are seen producing captivating news articles and dynamic radio segments. Show them engaging with complex mathematical concepts and weaving calculus and linear algebra into their work. Additionally, depict an increase in the number of likes on 3Blue1Brown's YouTube videos, symbolizing a growing appreciation for math content. Capture the positive impact of effective communication skills on the appreciation and engagement with math education. Keep the visual simple, with emphasis on the graduates' actions and their influence on the audience.

---

*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

Penned to Pixels: Unveiling the Ink-credible Link between Journalism Graduates and 3Blue1Brown YouTube Likes The Journal of Media Metamorphosis Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? Bachelor's degrees awarded in journalism Total likes of 3Blue1Brown YouTube videos 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.
4. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
5. 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. ^Note 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

# 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([90658,92551,93794,92289,92528,91763,90775,])
array_2 = np.array([211875,1197830,2845730,1170490,1450330,1117650,374341,])
array_1_name = "Bachelor's degrees awarded in journalism"
array_2_name = "Total likes of 3Blue1Brown 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

• 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 Bachelor's degrees awarded in journalism
• Line chart for only Total likes of 3Blue1Brown YouTube videos
• AI-generated correlation image
• The spurious research paper: Penned to Pixels: Unveiling the Ink-credible Link between Journalism Graduates and 3Blue1Brown YouTube Likes