Spurious correlation #2,124 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'that is sus' and the second variable is ON Semiconductor's stock price (ON). The chart goes from 2004 to 2023, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'that is sus' and the second variable is ON Semiconductor's stock price (ON). The chart goes from 2004 to 2023, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As Google searches for 'that is sus' increased, people were drawn to online gaming, leading to a surge in demand for electronic components. This unexpected connection boosted ON Semiconductor's stock price, proving that sometimes, even the most sus circumstances can have a shockingly positive impact. Remember, when in doubt, just blame it on the impostor syndrome!

^{Show image generation prompt} Model: dalle-3
Prompt: Create an image where a futuristic smartphone screen displays a Google search for "that is sus," with the search results showing various memes and phrases related to the popular online game, Among Us. Additionally, on the same screen, integrate a stock market app showing ON Semiconductor's stock price graph fluctuating in real-time, with the line indicating a slight increase. Ensure that the high-tech aspects of the scene are prominent, evoking a futuristic and technologically advanced aesthetic. 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: Google searches for 'that is sus' and ON Semiconductor's stock price. 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: High-tech Symbolism Vaporwave High-tech Data cyber art
ChatGPT: High-tech

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 Google searches for 'that is sus' and ON Semiconductor's stock price together. Keep the description simple.
ChatGPT: In the scene, a smartphone screen displays a Google search for "that is sus," with the search results showing various memes and phrases related to the popular online game, Among Us. On the same screen, a stock market app shows ON Semiconductor's stock price graph fluctuating in real-time, with the line showing a slight increase.

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: [ High-tech ] and depicting this scene: In the scene, a smartphone screen displays a Google search for "that is sus," with the search results showing various memes and phrases related to the popular online game, Among Us. On the same screen, a stock market app shows ON Semiconductor's stock price graph fluctuating in real-time, with the line showing a slight increase. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image where a futuristic smartphone screen displays a Google search for "that is sus," with the search results showing various memes and phrases related to the popular online game, Among Us. Additionally, on the same screen, integrate a stock market app showing ON Semiconductor's stock price graph fluctuating in real-time, with the line indicating a slight increase. Ensure that the high-tech aspects of the scene are prominent, evoking a futuristic and technologically advanced aesthetic.

*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.
^{Show prompt for explanation} 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 that is sus (Google searches for 'that is sus') caused ON Semiconductor's stock price (ON) to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

That is Sus: Uncovering the Link between Google Searches and Stock Prices

The Journal of Cybernetic Finance and Information Technology

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} 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 dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Google searches for 'that is sus' and ON Semiconductor's stock price (ON). 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. Then you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
"That is Sus": Uncovering the Link between Google Searches and Stock Prices

[[ABSTRACT]]
This study explores the peculiar correlation between Google searches for the phrase "that is sus" and the stock price of ON Semiconductor (ON). Leveraging Google Trends data and LSEG Analytics (Refinitiv), we meticulously analyze the relationship between these seemingly unrelated phenomena. Surprisingly, our analysis reveals a remarkably high correlation coefficient of 0.9673955 and a significance level of p < 0.01 for the period spanning 2004 to 2023. Our findings suggest that, contrary to common intuition, internet jargon may offer valuable insights into stock price movements. This research sheds light on the intriguing interconnectedness of online vernacular and financial markets, opening the door to a new realm of "sus"-tainable investment strategies.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
The financial market is a complex and dynamic system, influenced by an intricate web of factors ranging from economic indicators to geopolitical events. Traditional financial analysis has often relied on quantitative data, such as financial statement ratios, economic indicators, and market trends, to assess the performance and movements of stock prices. However, in recent years, there has been a growing recognition of the potential impact of unconventional sources of information on market dynamics. One such unorthodox influence that has piqued the interest of researchers is the realm of internet search trends and online colloquialisms.
This study delves into the unexpected and somewhat whimsical relationship between Google searches for the phrase "that is sus" and the stock price of ON Semiconductor (ON). The term "sus," short for "suspicious," has become a ubiquitous element of internet culture, particularly within the context of online gaming and social media. Despite its seemingly casual and inconsequential nature, "that is sus" has garnered significant attention due to its correlation with stock price movements of ON Semiconductor. The notion that internet vernacular could serve as a predictive indicator for financial markets may initially appear far-fetched - or perhaps "suspect" - but our analysis challenges this notion.
Our aim in this paper is to rigorously examine the nature of the relationship between Google search trends and stock prices, while keeping our eyes peeled for any unexpected nuggets of insight along the way. The unexpected intersection of internet slang and financial markets unfolds as a compelling avenue for inquiry, one that promises to add an amusing and enlightening twist to the field of market analysis. Our exploration of this curious correlation opens up a world of possibilities for "sus"-tained investment strategies, which, dare we say, may be more than mere "sus-picions."
The next section will review the relevant literature, offering a comprehensive overview of existing research on the interplay between internet trends and stock prices, with the occasional humorous aside to keep things lively - after all, navigating this unconventional terrain calls for some levity.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The literature review section aims to provide a comprehensive overview of existing research on the interplay between internet trends and stock prices, with the occasional humorous aside to keep things lively. The pursuit of unexpected nuggets of insight within the realm of internet vernacular and financial markets calls for a balanced blend of rigor and levity. While the initial premise may seem far-fetched, it is essential to approach this investigation with an open mind and, perhaps, a pinch of salt.

Smith and Doe (2018) examined the influence of internet slang on consumer behavior, shedding light on the potential impact of colloquialisms on market dynamics. However, their study did not delve into the peculiar case of "that is sus" and its correlation with stock prices. Jones et al. (2020) conducted a comprehensive analysis of internet search trends and their implications for financial markets, emphasizing the need to consider unconventional sources of information. While their study provided valuable insights, it did not specifically explore the interrelation between online vernacular and stock price movements.

In "The Search for Meaning," the authors discuss the evolving landscape of online search behavior and its implications for various industries, teasing out the potential connections between internet trends and consumer preferences. Furthermore, "The Language of Markets" offers a compelling exploration of the unconventional factors that can influence stock price movements, prompting readers to consider the unexpected influences lurking beneath the surface of financial markets.

On a more whimsical note, "Stocks and Socks: Unraveling Unconventional Correlations" delves into the peculiar connections between seemingly unrelated entities, hinting at the potential for unconventional indicators to impact stock prices in unpredictable ways. Similarly, the fictional works "The Wizard of Wall Street" and "The Adventures of Captain Capital and the Stock-market Squad" playfully interweave elements of financial markets with fantastical narratives, providing an amusing divergence from traditional market analyses.

In their animated series "Economic Explorers," the researchers at Economy-land Productions skillfully blend educational content with vibrant characters and catchy tunes, offering a lighthearted yet insightful exploration of economic concepts. The show's episode on "Market Mysteries" playfully hints at the enigmatic nature of stock price movements and the potential for unexpected influences to come into play.

As the literature review unfolds, it becomes evident that the intersection of internet vernacular and financial markets is rife with potential for both serious inquiry and light-hearted exploration. The unexpected twists and peculiar correlations that emerge from this unconventional terrain beckon researchers to dive in and embrace the delightful unpredictability that awaits. After all, in the world of "sus"-tainable investment strategies, a touch of humor may prove to be more than a mere "sus-picion."

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Google searches for 'that is sus' and ON Semiconductor's stock price (ON). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Google Trends and LSEG Analytics (Refinitiv) . You used data from 2004 to 2023

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"That is Sus": Uncovering the Link between Google Searches and Stock Prices

[[ABSTRACT]]
This study explores the peculiar correlation between Google searches for the phrase "that is sus" and the stock price of ON Semiconductor (ON). Leveraging Google Trends data and LSEG Analytics (Refinitiv), we meticulously analyze the relationship between these seemingly unrelated phenomena. Surprisingly, our analysis reveals a remarkably high correlation coefficient of 0.9673955 and a significance level of p < 0.01 for the period spanning 2004 to 2023. Our findings suggest that, contrary to common intuition, internet jargon may offer valuable insights into stock price movements. This research sheds light on the intriguing interconnectedness of online vernacular and financial markets, opening the door to a new realm of "sus"-tainable investment strategies.

[[INTRODUCTION]]
INTRODUCTION
The financial market is a complex and dynamic system, influenced by an intricate web of factors ranging from economic indicators to geopolitical events. Traditional financial analysis has often relied on quantitative data, such as financial statement ratios, economic indicators, and market trends, to assess the performance and movements of stock prices. However, in recent years, there has been a growing recognition of the potential impact of unconventional sources of information on market dynamics. One such unorthodox influence that has piqued the interest of researchers is the realm of internet search trends and online colloquialisms.
This study delves into the unexpected and somewhat whimsical relationship between Google searches for the phrase "that is sus" and the stock price of ON Semiconductor (ON). The term "sus," short for "suspicious," has become a ubiquitous element of internet culture, particularly within the context of online gaming and social media. Despite its seemingly casual and inconsequential nature, "that is sus" has garnered significant attention due to its correlation with stock price movements of ON Semiconductor. The notion that internet vernacular could serve as a predictive indicator for financial markets may initially appear far-fetched - or perhaps "suspect" - but our analysis challenges this notion.
Our aim in this paper is to rigorously examine the nature of the relationship between Google search trends and stock prices, while keeping our eyes peeled for any unexpected nuggets of insight along the way. The unexpected intersection of internet slang and financial markets unfolds as a compelling avenue for inquiry, one that promises to add an amusing and enlightening twist to the field of market analysis. Our exploration of this curious correlation opens up a world of possibilities for "sus"-tained investment strategies, which, dare we say, may be more than mere "sus-picions."
The next section will review the relevant literature, offering a comprehensive overview of existing research on the interplay between internet trends and stock prices, with the occasional humorous aside to keep things lively - after all, navigating this unconventional terrain calls for some levity.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Data Collection:
The primary data source for this study was Google Trends, which provided information on the search interest for the phrase "that is sus" from 2004 to 2023. The time frame was selected to capture a sufficiently extensive period of online vernacular evolution, spanning the rise of Web 2.0 to the era of memes and instant messaging shorthand. After all, one cannot discount the impact of vintage "sus" on modern interpretations. In addition, LSEG Analytics (Refinitiv) supplied the historical stock price data for ON Semiconductor (ON) over the same time period. This further involved an exploration of whether the stock's performance was influenced by an undercurrent of online suspicion and doubt, or if it withstood the "sus"picions unscathed.

Correlation Analysis:
The correlation between Google search trends for "that is sus" and ON Semiconductor's stock price was calculated using a Pearson correlation coefficient, accompanied by a thorough consideration of the appropriate significance level. The choice of the Pearson correlation method was informed by both its widespread use in financial and statistical analyses and its ability to capture linear relationships - an essential consideration when examining the intricate interplay between virtual colloquialism and market movements. The robustness of the correlation coefficient was evaluated through bootstrapping techniques, as we sought to ensure that the detected relationship was not merely a fluke resulting from a select few internet enthusiasts and stock analysts wielding disproportionate influence.

Granger Causality Test:
To further probe the direction of causality between "that is sus" searches and ON Semiconductor's stock price, a Granger causality test was conducted, taking into account potential lags and the bidirectional dynamics inherent in this curious relationship. This allowed for an exploration of whether the stock was merely evoking suspicion or if the suspicion, in turn, was driving the stock's behavior. After all, suspicion is not always a one-way street.

Control Variables:
Given the multifaceted nature of stock price determinants, a suite of control variables was integrated into the regression analysis, including market indices, industry-specific factors, and miscellaneous influencers that might spuriously masquerade as "sus"pect signals. The aim here was to unpick the "sus"-pected impact of Google searches from the background noise, ensuring that we were not merely chasing shadows cast by unrelated market phenomena or the occasional internet fad.

Sensitivity Analysis:
Sensitivity analyses were performed to scrutinize the robustness of our findings under variations in time frames, methodological choices, and data sources. This exploration was undertaken with the recognition that the landscape of online jargon and stock price dynamics is as fluctuating and capricious as the market itself. We did not wish to be caught unawares by any sly attempt to surreptitiously alter our findings, as if our data were whispering "that is sus" in our ears.

Limitations:
It is pertinent to acknowledge that, despite our conscientious efforts, the inescapable limitations of our methodology and data sources may have left some grains of suspicion unturned. The dynamic nature of internet vernacular and the stock market introduces a level of unpredictability that transcends even the most astute statistical tests. However, such limitations merely serve to infuse our findings with a dash of intrigue and challenge, akin to navigating a labyrinth of virtual "sus"-picion.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Google searches for 'that is sus' and ON Semiconductor's stock price (ON). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"That is Sus": Uncovering the Link between Google Searches and Stock Prices

[[ABSTRACT]]
This study explores the peculiar correlation between Google searches for the phrase "that is sus" and the stock price of ON Semiconductor (ON). Leveraging Google Trends data and LSEG Analytics (Refinitiv), we meticulously analyze the relationship between these seemingly unrelated phenomena. Surprisingly, our analysis reveals a remarkably high correlation coefficient of 0.9673955 and a significance level of p < 0.01 for the period spanning 2004 to 2023. Our findings suggest that, contrary to common intuition, internet jargon may offer valuable insights into stock price movements. This research sheds light on the intriguing interconnectedness of online vernacular and financial markets, opening the door to a new realm of "sus"-tainable investment strategies.

[[LITERATURE REVIEW]]
The literature review section aims to provide a comprehensive overview of existing research on the interplay between internet trends and stock prices, with the occasional humorous aside to keep things lively. The pursuit of unexpected nuggets of insight within the realm of internet vernacular and financial markets calls for a balanced blend of rigor and levity. While the initial premise may seem far-fetched, it is essential to approach this investigation with an open mind and, perhaps, a pinch of salt.
Smith and Doe (2018) examined the influence of internet slang on consumer behavior, shedding light on the potential impact of colloquialisms on market dynamics. However, their study did not delve into the peculiar case of "that is sus" and its correlation with stock prices. Jones et al. (2020) conducted a comprehensive analysis of internet search trends and their implications for financial markets, emphasizing the need to consider unconventional sources of information. While their study provided valuable insights, it did not specifically explore the interrelation between online vernacular and stock price movements.
In "The Search for Meaning," the authors discuss the evolving landscape of online search behavior and its implications for various industries, teasing out the potential connections between internet trends and consumer preferences. Furthermore, "The Language of Markets" offers a compelling exploration of the unconventional factors that can influence stock price movements, prompting readers to consider the unexpected influences lurking beneath the surface of financial markets.
On a more whimsical note, "Stocks and Socks: Unraveling Unconventional Correlations" delves into the peculiar connections between seemingly unrelated entities, hinting at the potential for unconventional indicators to impact stock prices in unpredictable ways. Similarly, the fictional works "The Wizard of Wall Street" and "The Adventures of Captain Capital and the Stock-market Squad" playfully interweave elements of financial markets with fantastical narratives, providing an amusing divergence from traditional market analyses.
In their animated series "Economic Explorers," the researchers at Economy-land Productions skillfully blend educational content with vibrant characters and catchy tunes, offering a lighthearted yet insightful exploration of economic concepts. The show's episode on "Market Mysteries" playfully hints at the enigmatic nature of stock price movements and the potential for unexpected influences to come into play.
As the literature review unfolds, it becomes evident that the intersection of internet vernacular and financial markets is rife with potential for both serious inquiry and light-hearted exploration. The unexpected twists and peculiar correlations that emerge from this unconventional terrain beckon researchers to dive in and embrace the delightful unpredictability that awaits. After all, in the world of "sus"-tainable investment strategies, a touch of humor may prove to be more than a mere "sus-picion."

[[RESULTS]]
The results of our analysis revealed a remarkably high correlation coefficient of 0.9673955 between Google searches for the phrase "that is sus" and the stock price of ON Semiconductor (ON). This correlation demonstrates a strong positive relationship between the two variables. Additionally, the r-squared value of 0.9358540 indicates that approximately 93.6% of the variance in ON Semiconductor's stock price can be explained by the variation in Google searches for "that is sus."
The statistical significance of the correlation was confirmed with a p-value of less than 0.01. This suggests that the observed correlation is unlikely to be due to random chance and provides further support for the strength of the relationship between internet search trends and stock price movements.
As seen in Fig. 1, the scatterplot visually depicts the strong positive correlation between Google searches for "that is sus" and ON Semiconductor's stock price. Each data point on the plot represents the concurrent values of Google searches and stock price on specific dates throughout the analysis period.
These findings challenge conventional notions of what influences stock prices and highlight the potential impact of internet culture on financial markets. The unexpected connection between internet vernacular and stock price movements presents a fascinating area for further exploration, potentially paving the way for innovative investment strategies rooted in the lighthearted realms of online jargon.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study are consistent with prior research that has explored the unexpected interconnectedness of seemingly unrelated phenomena. While it may initially appear to be a flight of fancy to consider the influence of internet jargon on stock prices, our results underscore the "sus"-ceptibility of financial markets to unconventional influences.

Our analysis aligns with the work of Smith and Doe (2018), who highlighted the potential impact of colloquialisms on market dynamics, despite not specifically delving into the relationship between "that is sus" and stock prices. Similarly, Jones et al. (2020) emphasized the need to consider unconventional sources of information, which resonates with our exploration of internet search trends and stock price movements.

The peculiar correlations and unexpected twists identified in the literature review are encapsulated in our findings, as we uncover a remarkably high correlation coefficient and a significance level that further bolsters the seemingly "sus-picious" relationship between Google searches for "that is sus" and ON Semiconductor's stock price. The twist of fate that intertwines online vernacular with stock price movements beckons researchers and investors alike to consider the potential influence of internet culture on financial markets.

It is intriguing to note that our results challenge conventional constructs of investment analysis, prompting us to consider the unprecedented implications of internet trends on market behavior. This suggests that the quirkiness of internet jargon may hold valuable insights into market dynamics, offering a new realm of "sus"-tainable investment strategies that marries the whimsical nature of internet colloquialisms with the seriousness of financial analysis.

This study serves as a gentle reminder of the enigmatic nature of stock price movements and demonstrates the potential for unexpected influences to infiltrate the seemingly rational realm of finance. As researchers venture further into the uncharted territory of internet vernacular and its impact on financial markets, it may be prudent to keep a keen eye out for the unexpected twists and quirks that underlie these seemingly abstract connections.

In the ever-evolving landscape of financial analysis, it is essential to maintain a lighthearted openness to the unexpected and "sus"-tain an appetite for unearthing unconventional correlations that may hold unsuspected value. After all, in the world of finance, a touch of humor and an astute eye for the unexpected may be more than a mere whimsy but an indispensable tool for uncovering the hidden pulse of market movements.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Google searches for 'that is sus' and ON Semiconductor's stock price (ON). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"That is Sus": Uncovering the Link between Google Searches and Stock Prices

[[ABSTRACT]]
This study explores the peculiar correlation between Google searches for the phrase "that is sus" and the stock price of ON Semiconductor (ON). Leveraging Google Trends data and LSEG Analytics (Refinitiv), we meticulously analyze the relationship between these seemingly unrelated phenomena. Surprisingly, our analysis reveals a remarkably high correlation coefficient of 0.9673955 and a significance level of p < 0.01 for the period spanning 2004 to 2023. Our findings suggest that, contrary to common intuition, internet jargon may offer valuable insights into stock price movements. This research sheds light on the intriguing interconnectedness of online vernacular and financial markets, opening the door to a new realm of "sus"-tainable investment strategies.

[[INTRDUCTION]]
INTRODUCTION
The financial market is a complex and dynamic system, influenced by an intricate web of factors ranging from economic indicators to geopolitical events. Traditional financial analysis has often relied on quantitative data, such as financial statement ratios, economic indicators, and market trends, to assess the performance and movements of stock prices. However, in recent years, there has been a growing recognition of the potential impact of unconventional sources of information on market dynamics. One such unorthodox influence that has piqued the interest of researchers is the realm of internet search trends and online colloquialisms.
This study delves into the unexpected and somewhat whimsical relationship between Google searches for the phrase "that is sus" and the stock price of ON Semiconductor (ON). The term "sus," short for "suspicious," has become a ubiquitous element of internet culture, particularly within the context of online gaming and social media. Despite its seemingly casual and inconsequential nature, "that is sus" has garnered significant attention due to its correlation with stock price movements of ON Semiconductor. The notion that internet vernacular could serve as a predictive indicator for financial markets may initially appear far-fetched - or perhaps "suspect" - but our analysis challenges this notion.
Our aim in this paper is to rigorously examine the nature of the relationship between Google search trends and stock prices, while keeping our eyes peeled for any unexpected nuggets of insight along the way. The unexpected intersection of internet slang and financial markets unfolds as a compelling avenue for inquiry, one that promises to add an amusing and enlightening twist to the field of market analysis. Our exploration of this curious correlation opens up a world of possibilities for "sus"-tained investment strategies, which, dare we say, may be more than mere "sus-picions."
The next section will review the relevant literature, offering a comprehensive overview of existing research on the interplay between internet trends and stock prices, with the occasional humorous aside to keep things lively - after all, navigating this unconventional terrain calls for some levity.

[[RESULTS]]
The results of our analysis revealed a remarkably high correlation coefficient of 0.9673955 between Google searches for the phrase "that is sus" and the stock price of ON Semiconductor (ON). This correlation demonstrates a strong positive relationship between the two variables. Additionally, the r-squared value of 0.9358540 indicates that approximately 93.6% of the variance in ON Semiconductor's stock price can be explained by the variation in Google searches for "that is sus."
The statistical significance of the correlation was confirmed with a p-value of less than 0.01. This suggests that the observed correlation is unlikely to be due to random chance and provides further support for the strength of the relationship between internet search trends and stock price movements.
As seen in Fig. 1, the scatterplot visually depicts the strong positive correlation between Google searches for "that is sus" and ON Semiconductor's stock price. Each data point on the plot represents the concurrent values of Google searches and stock price on specific dates throughout the analysis period.
These findings challenge conventional notions of what influences stock prices and highlight the potential impact of internet culture on financial markets. The unexpected connection between internet vernacular and stock price movements presents a fascinating area for further exploration, potentially paving the way for innovative investment strategies rooted in the lighthearted realms of online jargon.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the correlation between Google searches for the phrase "that is sus" and ON Semiconductor's stock price has yielded intriguing results. The remarkably high correlation coefficient, r-squared value, and statistical significance of the relationship challenge conventional wisdom regarding the influences on stock price movements. The strong positive relationship between internet search trends and stock prices opens up a new avenue of research that marries the seemingly disparate worlds of online parlance and financial markets. While some may find the idea of using internet slang as a predictive indicator for stock prices a bit "suspect," our findings suggest otherwise.

The evidence presented not only sheds light on the interconnectedness of online vernacular and financial markets but also underscores the potential for "sus"-tainable investment strategies. The whimsical nature of this correlation invites further exploration, with potential applications ranging from predicting stock price movements to crafting investment strategies peppered with a touch of internet humor. It is worth noting that the findings do not imply causation, but they do offer a rich opportunity for researchers and investors to venture into this unconventional terrain and uncover new insights.

As with any research, there are limitations to consider. The study focused on a specific period and a single company, and future investigations may benefit from examining a broader array of companies and a longer timeframe. Additionally, the nuanced dynamics of internet culture and its impact on stock prices warrant further exploration. Nevertheless, our study contributes to the evolving landscape of market analysis by unveiling an unexpected, yet compelling, relationship.

In light of these findings, we assert that further research in this area is superfluous. We have unearthed a treasure trove of 'sus'-piciously delightful insights, and it is time to let this particular financial meme rest in peace.

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 That is Sus: Uncovering the Link between Google Searches and Stock Prices. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Cybernetic Finance and Information Technology

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 That is Sus: Uncovering the Link between Google Searches and Stock Prices. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Algorithmic Market Analysis and Behavioral Economics

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 That is Sus: Uncovering the Link between Google Searches and Stock Prices with an abstract of This study explores the peculiar correlation between Google searches for the phrase "that is sus" and the stock price of ON Semiconductor (ON). Leveraging Google Trends data and LSEG Analytics (Refinitiv), we meticulously analyze the relationship between these seemingly unrelated phenomena. Surprisingly, our analysis reveals a remarkably high correlation coefficient of 0.9673955 and a significance level of p < 0.01 for the period spanning 2004 to 2023. Our findings suggest that, contrary to common intuition, internet jargon may offer valuable insights into stock price movements. This research sheds light on the intriguing interconnectedness of online vernacular and financial markets, opening the door to a new realm of "sus"-tainable investment strategies.

ChatGPT:

Google searches, "that is sus" Google Trends, stock price, ON Semiconductor, LSEG Analytics, Refinitiv, correlation between Google searches and stock prices, internet jargon, financial markets, investment strategies, sustainability, stock price movements

*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

Google searches for 'that is sus'
Detailed data title: Relative volume of Google searches for 'that is sus' (Worldwide, without quotes)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'that is sus'

ON Semiconductor's stock price (ON)
Detailed data title: Opening price of ON Semiconductor (ON) on the first trading day of the year
Source: LSEG Analytics (Refinitiv)
Additional Info: ^{See full details} Via Microsoft Excel Stockhistory function

See what else correlates with ON Semiconductor's stock price (ON)

Correlation r = 0.9673955 (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 = 0.9358540 (Coefficient of determination)
This means 93.6% of the change in the one variable (i.e., ON Semiconductor's stock price (ON)) is predictable based on the change in the other (i.e., Google searches for 'that is sus') over the 20 years from 2004 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.5E-12.^Show 0.0000000000035133273934172680
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note 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 0.97 in 3.5E-10% of random cases. Said differently, if you correlated 284,630,462,243 random variables^Note You don't actually need 284 billion 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 19 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 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.

[ 0.92, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} 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: ^Note 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.

	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022	2023
Google searches for 'that is sus' (Rel. search volume)	3.83333	7.08333	8.66667	3.83333	1.33333	6.41667	5.58333	6.91667	10.25	10.0833	8.66667	8.66667	11.0833	12.5	15.4167	14.4167	40.8333	58.1667	81.6667	79.6
ON Semiconductor's stock price (ON) (Stock price)	6.57	4.6	5.54	7.57	8.99	3.43	8.86	10.05	7.83	7.25	8	10.18	9.65	12.75	21.03	16.14	24.75	33.05	68.53	63.95

Why this works

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.
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.
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

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{Show the steps to do this.} 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([3.83333,7.08333,8.66667,3.83333,1.33333,6.41667,5.58333,6.91667,10.25,10.0833,8.66667,8.66667,11.0833,12.5,15.4167,14.4167,40.8333,58.1667,81.6667,79.6,])
array_2 = np.array([6.57,4.6,5.54,7.57,8.99,3.43,8.86,10.05,7.83,7.25,8,10.18,9.65,12.75,21.03,16.14,24.75,33.05,68.53,63.95,])
array_1_name = "Google searches for 'that is sus'"
array_2_name = "ON Semiconductor's stock price (ON)"

# 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. ^Note 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:

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 Google searches for 'that is sus'
Line chart for only ON Semiconductor's stock price (ON)
AI-generated correlation image
The spurious research paper: That is Sus: Uncovering the Link between Google Searches and Stock Prices

View another random correlation

How fun was this correlation?

Your correlation rating is out of this world!

Correlation ID: 2124 · Black Variable ID: 1367 · Red Variable ID: 1771


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: