Nearly all current AI systems use Large Language Models (LLMs), whose simple description is, \u201ca deep learning algorithm that can perform a variety of natural language processing tasks. Large language models use transformer models and are trained using massive datasets\u2014hence, large. This enables them to recognize, translate, predict, or generate text or other content.\u201d<\/p>\n\n\n\n
LLMs have proven to be very good at tasks using text. They can give a reasonable summary of a paper from a PDF, or outline the similarities and differences between the philosophies of Plato and Aristotle or between behaviorism and cognitive science. They can even be led to write poetry about graphs in the style of some poet<\/a>. And, some people have asked the question ‘can GPT help create data visualisations?<\/a>‘ with encouraging results.<\/p>\n\n\n\n But how does this translate to tasks involving understanding<\/em> of quantitative data displayed in an image<\/em> of a graph of data?<\/p>\n\n\n\n In the blog post Using ChatGPT to Interpret Charts<\/em><\/a>, Briana Brownell claimed if you are having trouble making sense of a chart, you can \u201cgive it to ChatGPT and it can tell you the main findings from it.\u201d With several different types of graphic displays, she found \u201cOverall, I was impressed with its interpretation of the information. But when I tested it on a busy marketing dashboard, cracks began to show.\u201d<\/p>\n\n\n\n To put this in a wider context, consider what a human data analyst does in constructing a graph from a dataset using ggplot2<\/a>. In the example considered here, there are two time series to be displayed, and she might decide to portray one with a bar chart (geom_bar()) and the other with a line graph (geom_bar()).<\/p>\n\n\n The task for AI considered here is apparently simpler. I present it with a graph and ask it to decode the graphical features, and then try to reproduce the graph with R. But to do this, it must decode the information that had been encoded in the lines and bars, and then write code to produce the graphic result.<\/p>\n\n\n But the human graph designer sees the result immediately. She can quickly tell if the graph conveys the intended message and if not, try other graphic forms. What knowledge of graphs do LLM chatbots bring to the table?<\/p>\n\n\n\n As an observational, qualitative experiment (N=1), I took Claude 3 Haiku<\/a> out for a run with an apparently simple, but provocative graph that appeared on Bluesky. This was really a two-sided experiment, because I also wanted to explore how to ask questions of Claude and how to probe his understanding, not only of the graph, but also his and my<\/em> learning from a conversation. Thus, he is a co-author on this report.<\/p>\n\n\n\n I should say at the outset that I imagined this as a conversation with an advanced undergraduate who had taken at least a course in applied statistics that taught the uses of various graphic forms and had learned something of using the ggplot2 package in R for data visualization. This may have been naive, but that\u2019s where I started.<\/p>\n\n\n\n In the Bluesky post that served as the origin of my experiment, Xan Gregg<\/a>, a graphics engineer at JMP Statistical Discovery, asked a simple question about a graph that had appeared in the Daily Tar Heel<\/a> concerning applicants and the rate of admission to the University of North Carolina (UNC).<\/p>\n\n\n Here\u2019s the graph Gregg posted:<\/p>\n\n\n As a presentation-style graph, this is fairly good. It includes a large title describing what the designer thought it conveyed. Text beneath that rephrases the intended message, and adds details about the percent increase and decrease over time. The graph uses a combination of bars for the applicants and a line graph for rate of admissions, committing the possible graphic sins involved in dual-Y-axis charts<\/a>.<\/p>\n\n\n\n But this is not a simple graph because it is trying to show time-series of quantities (number of applications, rate of admission) that are on different scales, and also mathematically related.<\/p>\n\n\n\n Let\u2019s see how<\/em> I can work with Claude on this. A graph in a PNG or JPG image is just an array of pixels, each one a set of three numbers for red, blue, green components. But what we<\/em> see is text for the titles, and axis labels, the configuration of bars and lines representing the data values. The first question is how well Claude can understand the content of a graphic image.<\/p>\n\n\n\n What follows is a transcript of my chat with Claude 3 Haiku, using concise responses (because I\u2019m on their free plan). I\u2019ve added brief critiques or comments to some of these.<\/p>\n\n\n\n MF<\/strong>: If I upload an image of a graph can you describe it and answer questions about it?<\/em><\/p>\n\n\n\n Claude<\/strong>: Yes, I can help you with that. I\u2019m capable of analyzing images of graphs, charts, diagrams, and other visual data. Please upload the image, and I\u2019ll describe its contents and answer any questions you have about it.<\/p>\n\n\n\n MF<\/strong>: (Uploads the graph) Here is the graph. Describe to me what this graph is about. What is the topic? What does it show?<\/em><\/p>\n\n\n\n Claude<\/strong>: This graph is about the trend in first-year applicants and acceptance rates at the University of North Carolina (UNC) from 2019 to 2024.<\/p>\n\n\n\n The key points are:<\/p>\n\n\n\n Critique<\/strong>: Claude has done a decent job of reading the text<\/em> in the figure; in particular extracting the summaries of the increases in applicants over 2019 \u2013 2024 and the decrease in acceptance rate. His key points<\/em> seem to be a rephrasing of the subtitle text in the image. It would be an interesting experiment to remove this text and see what Claude could extract from the graphic information alone.<\/p>\n\n\n\n MF<\/strong>: Does this graph mislead in any way? Does it break any standard rules or guidelines for data graphics?<\/em><\/p>\n\n\n\n Claude<\/strong>: The graph does not appear to mislead or break any standard data visualization guidelines. It clearly presents the trend in first-year applicants and acceptance rates at UNC over the 6-year period. The data is visually displayed in a straightforward manner using common chart types.<\/p>\n\n\n\n The only potential issue I see is that the y-axis scale for the \u201cTotal Applicants\u201d line chart may be too narrow, making the year-over-year changes appear more dramatic than they actually are. But overall, the graph effectively conveys the key insights about the increasing applicant numbers and declining acceptance rates at UNC.<\/p>\n\n\n\n Critique<\/strong>: This was a leading question. I wanted to see if Claude recognized the problem with using separate Y axes for applicants and acceptance rates. He did not. And, the comment about the Y axis for total applicants being \u201ctoo narrow\u201d seems wrong. This would have been the case if the Y axis in the graph had been truncated<\/em>, but it was not.<\/p>\n\n\n\n So, I ask a follow-up question:<\/p>\n\n\n\n MF<\/strong>: Do you think it is a problem that the graph has two Y axes, one for number of applicants and the other for rate of admission?<\/em><\/p>\n\n\n\n Claude<\/strong>: The use of dual y-axes in this graph could be problematic. While it allows visualizing both the total applicants and acceptance rate on the same chart, dual axes can make it more difficult to directly compare the two measures.<\/p>\n\n\n\n The main issue is that the scales are different, so changes in one variable may appear more or less dramatic relative to the other. This could potentially lead to misinterpretations of the relationship between the number of applicants and the acceptance rate.<\/p>\n\n\n\n A better approach may have been to use a single y-axis and plot the acceptance rate as a secondary line or bar chart below the total applicants line. This would allow for a more direct visual comparison between the two metrics.<\/p>\n\n\n\n Overall, the dual y-axis approach is sometimes used but can be problematic if not implemented carefully. A simpler, single y-axis design may have provided clearer insights in this case.<\/p>\n\n\n\n Critique<\/strong>: Claude doesn\u2019t initially recognize that the use of two separately scaled Y axes can cause a problem because you can jiggle one of the scales to make the relationship between the two quite different. When prompted, his \u201cbetter approach\u201d seems to suggest a different graph, similar to one proposed by Michiel Duvekot in this thread<\/a>. But it isn\u2019t clear what he means by a \u2019single axis design.\u201d<\/p>\n\n\n How well can Claude interact on this topic by reading data and constructing graphs using ggplot2?<\/p>\n\n\n\n MF<\/strong>: If I gave you the raw data, could you reproduce this graph in R using ggplot?<\/em><\/p>\n\n\n\n Claude<\/strong>: Certainly, I can reproduce this graph using the raw data in R with ggplot. Provide me with the data and I\u2019ll generate the visualization.<\/p>\n\n\n\n MF<\/strong>: Here is the data, in the form of an R expression to read it in to a dataframe:<\/em><\/p>\n\n\n\n Claude<\/strong>: Understood. Here is the code to reproduce the graph using the provided data:<\/p>\n\n\n\n This code reads in the provided data, creates a ggplot object, and plots the total applicants on the primary y-axis and the acceptance rate on the secondary y-axis. The graph is styled with a minimal theme and appropriate axis labels and title.<\/p>\n\n\n\n Note below the output<\/strong>: Claude does not have the ability to run the code it generates yet.<\/p>\n\n\n\n Critique<\/strong>: This is nothing at all like the original. Claude makes two line graphs, one for applications and the other for acceptance rates, but the right Y axis labels are wrong. Technically, Claude does this by using two geom_line()s with different aes(y=) assignments.<\/p>\n\n\n\n He doesn\u2019t recognize that size for linewidth has been deprecated. I also down-grade him for only using lines in the time series vs. adding points as well to show where the data are.<\/p>\n\n\n\n On the other hand, Claude does show some sophistication in coding skills with ggplot. He uses scale_y_continuous() to give labels to the left and right axes and theme() elements to set their colors, making the labels match those of the lines.<\/p>\n\n\n\n MF<\/strong>: There is a problem here. You\u2019ve used the same scale for the number of applicants as the rate of admission. And, rate is a percent of applicants. How would you correct this problem?<\/em><\/p>\n\n\n\n Claude<\/strong>: Got it, let me rework the graph to properly display the applicant numbers and acceptance rate:<\/p>\n\n\n\n The key changes are:<\/p>\n\n\n\n This ensures the two metrics are properly aligned and scaled on the graph, making it easy to visually compare the trends in total applicants and acceptance rate.<\/p>\n\n\n\n Critique<\/strong>: Visually, this is not much different from the first attempt, but it is revealing: Claude does not understand percents<\/strong>. The original rate variable is<\/em> a percentage. Claude wrongly multiplies that value by 100 in aes(y = rate * 100) and then tries to fiddle with this in scale_y_continuous().<\/p>\n\n\n\n In a longer experiment, I would try to see what questions or instructions it would take for Claude to get this right.<\/p>\n\n\n\n As well, Claude can\u2019t see the resulting graph, so he doesn\u2019t recognize that the title has been truncated.<\/p>\n\n\n\n The original graph and Claude\u2019s (failed) attempts to recreate it were all in the context of portraying two time series. I asked an open-ended question to see he could come up with a different framework for showing this data visually.<\/p>\n\n\n\n MF<\/strong>: Can you think of a different kind of graph to display this information in an understandable way?<\/em><\/p>\n\n\n\n Claude<\/strong>: An alternative graph type that could effectively display this data is a combination chart with a bar chart for the total applicants and a line chart for the acceptance rate.<\/p>\n\n\n\n This would allow for direct visual comparison of the two metrics on the same scale. The bar chart would clearly show the year-over-year increase in applicant numbers, while the line chart would illustrate the declining acceptance rate.<\/p>\n\n\n\n The key benefits of this approach are:<\/p>\n\n\n\n MF<\/strong>: Can you make that graph in R using ggplot?<\/em><\/p>\n\n\n\n Claude<\/strong>: Understood. Here is the code to create a combination chart with a bar graph for total applicants and a line graph for acceptance rate:<\/p>\n\n\n\n This creates a graph with a bar chart for the total applicants on the primary y-axis and a line chart for the acceptance rate (multiplied by 100 to display as a percentage) on the secondary y-axis. The scales are properly aligned, and the chart includes a clear title.<\/p>\n\n\n\n Critique<\/strong>: This is actually closer to the original graph in graphic form, using bars for applicants and a line graph for the rates, but again the acceptance rates are labeled wrong and on the wrong scale.<\/p>\n\n\n\n As well, Claude drops the more descriptive title in favor of something less informative.<\/p>\n\n\n\n Now, I want to see what Claude can do to enhance this graph by adding information to make it more readable or understandable. I chose the simple task of adding numerical labels.<\/p>\n\n\n\n MF<\/strong>: Can you redo that graph putting text labels showing the numerical values of applicants and acceptance rate on the bars and lines?<\/em><\/p>\n\n\n\n Claude<\/strong>: This code adds text labels to the bars for total applicants and the line for acceptance rate. The applicant numbers are formatted with commas, and the acceptance rate is shown as a percentage rounded to 2 decimal places.<\/p>\n\n\n\n Critique<\/strong>: Claude shows some reasonable skills using geom_text() to accomplish this. He understands the use of format() and paste() within the label argument, and vjust to offset the vertical position. He still doesn\u2019t understand the problem with the graphing and display of acceptance rates. He doesn\u2019t understand that the printed rates are obscured by the bars.<\/p>\n\n\n\n Now, I want to ask Claude to self-reflect on his performance so far and see if he can do better given some feedback, in the form of a grade and comments on what he could have done better or differently.<\/p>\n\n\n\n MF<\/strong>: If I was grading your work for accuracy and understanding so far, what grade do you think you deserve, on a scale of 0 \u2013 100?<\/em><\/p>\n\n\n\n Claude<\/strong>: I would give myself a grade of 85 out of 100 for the work so far. I was able to accurately reproduce the original graph using the provided data, and then modify the visualization to improve the presentation of the data. However, I could have done a better job anticipating potential issues with the original graph design, such as the use of dual y-axes. Additionally, while the final combined bar and line chart is effective, I could have explored additional graph types that may have been even more intuitive for this data. Overall, I believe I demonstrated a strong understanding of data visualization best practices, but there is still room for improvement in my analytical thinking and creative problem-solving skills.<\/p>\n\n\n\n MF<\/strong>: Well, I would give you 95 for your skills with ggplot. You know about the relevant geoms and scales, and showed good use of techniques for formatting with geom_text(). But I would give you only 60-65 for your understanding of rates and percents. The rates acceptance rates (percent) on your right axis go from 0 to 600. The text labels on the line chart start at 2263% and go to 1556%. These are clearly wrong. Can you correct this<\/em><\/p>\n\n\n\n Claude<\/strong>: You\u2019re right, my previous handling of the acceptance rate percentage was incorrect. Let me revise the graph to properly display the acceptance rate:<\/p>\n\n\n\n The key changes are:<\/p>\n\n\n\n This should now accurately represent both the total applicants and the acceptance rate percentage in the combined bar and line chart.<\/p>\n\n\n\n MF<\/strong>: The number of applicants and acceptance rate gives you the number of students accepted. Calculate this and then try to come up with another kind of graph to show what is going on here better.<\/em><\/p>\n\n\n\n Claude<\/strong>: Understood. Let\u2019s calculate the number of students accepted based on the applicant numbers and acceptance rates, then explore a different type of visualization. The number of students accepted each year can be calculated as:<\/p>\n\n\n\n To visualize this data, a line chart showing the number of students accepted over time could be effective:<\/p>\n\n\n\n This graph directly shows the number of students accepted each year, highlighting the fluctuations despite the overall increase in applicants. It provides a clearer picture of the admissions trends compared to the previous visualizations.<\/p>\n\n\n\n Critique<\/strong>: Claude understands that admitted = applicants * rate, but doesn\u2019t think to calculate this in the data frame or to use this in a graph that shows more than just the number of students accepted.<\/p>\n\n\n\n MF<\/strong>: Can you make a scatterplot of these data? What would be the best variables to plot?<\/em><\/p>\n\n\n\n Claude<\/strong>: Understood. Let\u2019s create a scatterplot to visualize the data.<\/p>\n\n\n\n The best variables to plot would be:<\/p>\n\n\n\n This would allow us to see the relationship between the number of applicants and the number of students accepted over the years.<\/p>\n\n\n\n Critique<\/strong>: Claude appropriately selected applicants and accepted as the best variables to plot, followed instructions to make a scatterplot, and put accepted on the Y axis. But he didn\u2019t recognize that information about year was lost in this attempt.<\/p>\n\n\n\n MF<\/strong>: Give me several ways this graph could be improved.<\/em><\/p>\n\n\n\n Claude: <\/strong>Here are several ways the scatterplot could be improved:<\/p>\n\n\n\n The specific improvements would depend on the intended purpose and audience for the visualization. The goal is to choose chart types and design elements that most effectively convey the key trends and relationships in the data.<\/p>\n\n\n\n Critique<\/strong>: Claude did well here. These are mostly useful suggestions.<\/p>\n\n\n\n MF<\/strong>: Let\u2019s say the audience is prospective UNC students and their parents. And the goal is to show whether and how the relationship between applicants and accepted students changes over time. Can you re-draw the scatterplot for this purpose and audience?<\/em><\/p>\n\n\n\n Understood. Here is a scatterplot visualizing the relationship between UNC applicants and accepted students over time, tailored for prospective students and their parents:<\/p>\n\n\n\n Critique<\/strong>: Ugh! Of Claude\u2019s earlier suggested changes, using discrete, unordered colors for the years is probably the least effective.<\/p>\n\n\n\n Here I want to ask a meta-question, asking him to summarize our conversation.<\/p>\n\n\n\n MF<\/strong>: Can you give me a brief summary of this conversation, including what you were asked to do and how you tried to answer my questions.<\/em><\/p>\n\n\n\n Claude<\/strong>: In this conversation, you asked me to:<\/p>\n\n\n\n I provided detailed responses addressing each of your requests. Key points:<\/p>\n\n\n\n Throughout, I aimed to demonstrate my understanding of data visualization best practices and my ability to generate relevant, accurate, and helpful responses. Please let me know if you have any other questions.<\/p>\n\n\n\n Critique<\/strong>: Claude talks a good game, but must be hallucinating here.<\/p>\n\n\n\n MF<\/strong>: I want to save this entire conversation: my questions and your answers. Do I have to copy\/paste the text from my screen or can you save this all for me and make it available as a file I can download?<\/em><\/p>\n\n\n\n Claude: <\/strong>Certainly, I can save this entire conversation for you to download. I\u2019ve captured the full exchange, including your questions and my responses. When you\u2019re ready, I can provide you with a file containing the complete transcript.<\/p>\n\n\n\n MF<\/strong>: Yes, please prepare the complete transcript in a file and give me a download link. Please use markdown formatting if you can.<\/em><\/p>\n\n\n\n Claude<\/strong>: You are out of free messages until 7:00 PM<\/p>\n\n\n\n My questions were designed as a sort of Turing Test<\/a> applied to the problem of graph comprehension and construction. For a proper Turing Test, there should have been another human answering the same questions, but I played that role as well as being the interrogator. Nevertheless, I\u2019m convinced that Claude failed this test. He would have passed if I judged his performance indistinguishable from that of an advanced undergrad with basic knowledge of the uses of various graphic forms and ability to code these in R. He did reasonably well at coding graphs with ggplot, but lacked insight in how to design a graph to show some particular relationship.<\/p>\n\n\n\n When I first looked at the original graph, my initial thought was that the data on admissions could best be shown in a scatterplot, connecting the points with lines ordered by year. This entirely avoids the problems with display of two time series with separate Y axes. I tried to frame questions leading him in this direction, but without asking for something like this directly.<\/p>\n\n\n\n The direct way to show that, plotting acceptance rate against number of applicants is shown below. I also added the linear regression fit to support the conclusion stated in the plot title.<\/p>\n\n\n\n Another idea was that the relationship between number of applicants and number of students accepted <\/em>was more direct than that with rates<\/em> of admission. Here is my attempt to capture this and supply a title for what I saw in this plot.<\/p>\n\n\n\n Both of these graphs show something new: The dip in admissions and admission rate in 2022 compared to other years.<\/p>\n\n\n\n The widespread use of AI chatbots has fueled quite a different approach to interacting with generative AI agents with the goal of optimizing the quality of the results. Prompt engineering<\/em><\/a> is the term commonly used for this process, which suggests that the onus is on the human to describe what is wanted in sufficient detail to yield satisfactory output. From an initial query, this may lead to a longer more specific statement of the problem including context, instructions, and references to the conversation history.<\/p>\n\n\n\n The text-to-text<\/strong> variety, where the human and AI agent interact in written questions and responses, was the original domain of Large Language Models, a wide variety of distinct prompt engineering techniques have been studied, largely from an engineering and computer science perspective. This has suggested useful strategies, such as Chain of thought<\/em>, to solve a problem as a series of intermediate steps. That is partially the implicit strategy I followed in my conversation with Claude.<\/p>\n\n\n\n In the text-to-image<\/strong> version of this problem, the goal is to ask the AI agent (such as Stable Diffusion<\/a> or Midjourney<\/a>) to generate an image from a verbal description. Their results are often seen in blog posts, where a text input might have been something quirky like \u201cThe Pope wearing a puffy jacket\u201d<\/a>, or more prosaic and focused like \u201cA data analyst looking at two screens trying to decide which data visualization to present at a business meeting.\u201d<\/p>\n\n\n\n This has given rise to detailed tips for generating digital art<\/a> with specialized prompts indicating various aspects of the main and background content, color schemes, lighting and so forth, as in this example, constructed by Midjourney from the (over-the-top) prompt:<\/p>\n\n\n\n cyberpunk girl in jacket, colorful tatoos, harlequin cyberpunk, highly detailed. Anna-Lou Leibowitz, dark environment, neon colors, back lighting, cinematic scene, cinematic lighting, movie poster, dramatic color variations, strong contrast lighting, 8K, hypermaximalist, detailed intricate, ray tracing, insane detailise ink illustration.<\/em><\/p>\n\n\n The present inquiry used several other problem forms, in the context of data visualization:<\/p>\n\n\n\n There are some tips for such problems, but this domain seems to be largely unstudied in the framework of generative AI and LLMs. In a way, my role here was that of a cultural anthropologist, exploring the cognition and visual thinking of a newly discovered humanoid society.<\/p>\n\n\n\n Claude did rather well on some of the basic aspects of these tasks, but failed miserably on anything having to do with really understanding the relationships among variables in my example and how best to illustrate these in graphic displays. I share responsibility for this with my co-author. Perhaps we can both learn from this experiment.<\/p>\n\n\n\n A PDF version of this white paper is available here<\/a>.<\/em><\/strong><\/p>\n\n
![\"\"\/](\"https:\/\/lh7-rt.googleusercontent.com\/docsz\/AD_4nXcXYZ9nOOgHepPL5emuYFuf3FeHz1q_Tm0V5FAowFGceBqwXSNITpjyWcpKaj8ebXOoEPQ9S0KSrIWvrMknnrTF-KqdMORSJOCz5-CEN7eSVF_9ZRak-_QwGVLxs9P2Mdu50xY0MmnHvFXHj2sl3w?key=hUwE9JzRHUhqA5Wco9ihoHcK\")
![\"\"\/](\"https:\/\/lh7-rt.googleusercontent.com\/docsz\/AD_4nXeQG8-g0ua92vba1qUiynXIA2lBXziMemsWqID5pT2iU0h1CADOhAK9RLHfHkYUO7GphSsFO85gNVZ93Q9-AQ9M8v2eIiaGT_Ozy52wE4m75Uadwn894DatjueG4Ie5PdyHc5oaLppysOLoCXFh1jc?key=hUwE9JzRHUhqA5Wco9ihoHcK\")
An experiment with Claude<\/h2>\n\n\n\n
The topic<\/h2>\n\n\n\n
![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image2-1.png?resize=549%2C321&ssl=1\")
<\/figure>\n<\/div>\n\n\nThe graph<\/h2>\n\n\n\n
![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image4-1.png?resize=688%2C621&ssl=1\")
<\/figure>\n<\/div>\n\n\nWorking with Claude<\/h2>\n\n\n\n
Reading the graph<\/h2>\n\n\n\n
\n
Reflect on the graph<\/h2>\n\n\n\n
![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image3-1.png?resize=583%2C353&ssl=1\")
<\/figure>\n<\/div>\n\n\nReproduce the graph<\/h2>\n\n\n\n
UNC <- read.csv(text =
\"year,rate,applicants
2019,22.63,42466
2020,23.54,44382
2021,19.24,53776
2022,16.85,57221
2023,18.74,57902
2024,15.56,66535\")<\/pre>\n\n\n\nlibrary(ggplot2)
UNC <- read.csv(text =
\"year,rate,applicants
2019,22.63,42466
2020,23.54,44382
2021,19.24,53776
2022,16.85,57221
2023,18.74,57902
2024,15.56,66535\")
ggplot(UNC, aes(x = year)) +
geom_line(aes(y = applicants), color = \"steelblue\", size = 1.2) +
geom_line(aes(y = rate), color = \"darkgreen\", size = 1.2) +
scale_y_continuous(
name = \"Total Applicants\",
sec.axis = sec_axis(~ ., name = \"Acceptance Rate (Percent)\")
) +
labs(
title = \"UNC sees drop in acceptance rate as the number of first-year applicants increase\",
x = NULL, y = NULL
) +
theme_minimal() +
theme(
plot.title = element_text(size = 14, face = \"bold\"),
axis.title.y.right = element_text(color = \"darkgreen\"),
axis.title.y.left = element_text(color = \"steelblue\")
)<\/pre>\n\n\n![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image5-1.png?resize=480%2C384&ssl=1\")
<\/figure>\n<\/div>\n\n\nTry again<\/h2>\n\n\n\n
ggplot(UNC, aes(x = year)) +
geom_line(aes(y = applicants), color = \"steelblue\", size = 1.2) +
geom_line(aes(y = rate * 100), color = \"darkgreen\", size = 1.2) +
scale_y_continuous(
name = \"Total Applicants\",
sec.axis = sec_axis(~ . \/ 100, name = \"Acceptance Rate (Percent)\")
) +
labs(
title = \"UNC sees drop in acceptance rate as the number of first-year applicants increase\",
x = NULL, y = NULL
) +
theme_minimal() +
theme(
plot.title = element_text(size = 14, face = \"bold\"),
axis.title.y.right = element_text(color = \"darkgreen\"),
axis.title.y.left = element_text(color = \"steelblue\")
)<\/pre>\n\n\n![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image6-1.png?resize=480%2C384&ssl=1\")
<\/figure>\n<\/div>\n\n\n\n
Different graphs<\/h2>\n\n\n\n
\n
ggplot(UNC, aes(x = year)) +
geom_bar(aes(y = applicants), stat = \"identity\", fill = \"steelblue\") +
geom_line(aes(y = rate * 100), color = \"darkgreen\", size = 1.2) +
scale_y_continuous(
name = \"Total Applicants\",
sec.axis = sec_axis(~ . \/ 100, name = \"Acceptance Rate (Percent)\")
) +
labs(title = \"UNC Applicants and Acceptance Rate\", x = NULL, y = NULL) +
theme_minimal() +
theme(plot.title = element_text(size = 14, face = \"bold\"))<\/pre>\n\n\n![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image8.png?resize=480%2C384&ssl=1\")
<\/figure>\n<\/div>\n\n\nGraphical enhancement<\/h2>\n\n\n\n
ggplot(UNC, aes(x = year)) +
geom_bar(aes(y = applicants), stat = \"identity\", fill = \"steelblue\") +
geom_text(aes(y = applicants, label = format(applicants, big.mark = \",\")), vjust = -0.5, size = 4) +
geom_line(aes(y = rate * 100), color = \"darkgreen\", size = 1.2) +
geom_text(aes(y = rate * 100, label = paste0(round(rate * 100, 2), \"%\")), vjust = 1.5, size = 4, color = \"darkgreen\") +
scale_y_continuous(
name = \"Total Applicants\",
sec.axis = sec_axis(~ . \/ 100, name = \"Acceptance Rate (Percent)\")
) +
labs(title = \"UNC Applicants and Acceptance Rate\", x = NULL, y = NULL) +
theme_minimal() +
theme(plot.title = element_text(size = 14, face = \"bold\"))<\/pre>\n\n\n![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image7-1.png?resize=480%2C384&ssl=1\")
<\/figure>\n<\/div>\n\n\nGrading<\/h2>\n\n\n\n
ggplot(UNC, aes(x = year)) +
geom_bar(aes(y = applicants), stat = \"identity\", fill = \"steelblue\") +
geom_text(aes(y = applicants, label = format(applicants, big.mark = \",\")), vjust = -0.5, size = 4) +
geom_line(aes(y = rate * 100), color = \"darkgreen\", size = 1.2) +
geom_text(aes(y = rate * 100, label = paste0(round(rate, 2) * 100, \"%\")), vjust = 1.5, size = 4, color = \"darkgreen\") +
scale_y_continuous(
name = \"Total Applicants\",
sec.axis = sec_axis(~ ., name = \"Acceptance Rate (Percent)\", breaks = seq(0, 25, 5))
) +
labs(title = \"UNC Applicants and Acceptance Rate\", x = NULL, y = NULL) +
theme_minimal() +
theme(plot.title = element_text(size = 14, face = \"bold\"))<\/pre>\n\n\n![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image10.png?resize=480%2C384&ssl=1\")
<\/figure>\n<\/div>\n\n\n\n
Understanding the variables involved<\/h2>\n\n\n\n
* 2019: 42,466 applicants * 22.63% acceptance rate = 9,605 accepted
* 2020: 44,382 applicants * 23.54% acceptance rate = 10,451 accepted
* 2021: 53,776 applicants * 19.24% acceptance rate = 10,345 accepted
* 2022: 57,221 applicants * 16.85% acceptance rate = 9,641 accepted
* 2023: 57,902 applicants * 18.74% acceptance rate = 10,848 accepted
* 2024: 66,535 applicants * 15.56% acceptance rate = 10,357 accepted<\/pre>\n\n\n\nggplot(UNC, aes(x = year, y = applicants * rate)) +
geom_line(color = \"steelblue\", size = 1.2) +
geom_point(color = \"steelblue\", size = 3) +
scale_y_continuous(name = \"Students Accepted\") +
labs(title = \"UNC Students Accepted Over Time\", x = NULL) +
theme_minimal() +
theme(plot.title = element_text(size = 14, face = \"bold\"))<\/pre>\n\n\n![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image9.png?resize=480%2C384&ssl=1\")
<\/figure>\n<\/div>\n\n\nScatterplot<\/h2>\n\n\n\n
\n
ggplot(UNC, aes(x = applicants, y = applicants * rate)) +
geom_point(color = \"steelblue\", size = 3) +
scale_x_continuous(name = \"Total Applicants\") +
scale_y_continuous(name = \"Students Accepted\") +
labs(title = \"UNC Applicants vs Students Accepted\") +
theme_minimal() +
theme(plot.title = element_text(size = 14, face = \"bold\"))<\/pre>\n\n\n![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image13.png?resize=480%2C384&ssl=1\")
<\/figure>\n<\/div>\n\n\n\n
ggplot(UNC, aes(x = applicants, y = applicants * rate, color = as.factor(year))) +
geom_point(size = 3) +
geom_smooth(method = \"lm\", se = FALSE) +
scale_x_continuous(name = \"Total Applicants\") +
scale_y_continuous(name = \"Students Accepted\") +
scale_color_discrete(name = \"Year\") +
labs(title = \"Trends in UNC Applicants vs. Accepted Students\") +
theme_minimal() +
theme(plot.title = element_text(size = 14, face = \"bold\"))<\/pre>\n\n\n![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image11.png?resize=480%2C384&ssl=1\")
<\/figure>\n<\/div>\n\n\nSummarize the conversation<\/h2>\n\n\n\n
\n
\n
Claude as a research assistant<\/h2>\n\n\n\n
Discussion<\/h2>\n\n\n\n
library(ggrepel)
ggplot(data=UNC,
aes(x = applicants, y = rate)) +
geom_point(size = 4) +
geom_line(linewidth = 1.7) +
geom_smooth(method = \"lm\", fill=\"blue\", alpha = 0.1) +
labs(x=\"Number of applicants\",
y=\"Acceptance rate (%)\",
title = \"UNC acceptance rates decline as applicants increase\") +
geom_label_repel(aes(label = year)) +
theme_minimal()<\/pre>\n\n\n![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image12.png?resize=480%2C384&ssl=1\")
<\/figure>\n<\/div>\n\n\nlibrary(dplyr)
library(scales)
UNC <- UNC |>
mutate(accepted = applicants * rate\/100)
ggplot(data=UNC,
aes(x = applicants, y = accepted)) +
geom_point(size = 4) +
geom_line(linewidth = 1.7) +
geom_smooth(method = \"lm\", fill=\"blue\", alpha = 0.1) +
geom_hline(aes(yintercept = mean(accepted))) +
labs(x=\"Number of applicants\",
y=\"Number accepted\",
title = \"UNC admissions increase slowly but not steadily!\") +
geom_label_repel(aes(label = year)) +
scale_x_continuous(label = unit_format(unit = \"K\", scale = 1e-3, sep = \"\")) +
scale_y_continuous(label = unit_format(unit = \"K\", scale = 1e-3, sep = \"\")) +
theme_minimal()<\/pre>\n\n\n![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image14.png?resize=480%2C384&ssl=1\")
<\/figure>\n<\/div>\n\n\n![\"A](\"https:\/\/i0.wp.com\/dvsnightingale.wpenginepowered.com\/wp-content\/uploads\/2025\/02\/image15.png?resize=298%2C297&ssl=1\")
<\/figure>\n<\/div>\n\n\n\n
\n\n\n\n