Tommy / Getty Images
Over the course of the pandemic, social media investigators, epidemiologists, and health nerds alike have begun to notice an interesting trend in the review section for Yankee candles at Amazon.
Whenever there has been an influx of negative reviews indicating a lack of smell, there has usually been a rise in COVID cases to keep up.
A new wave of bad reviews for Yankee candles pic.twitter.com/1mlandB78I
Toothpaste (drewtoothpaste) December 21, 2021
Loss of the sense of smell is one of the most well-known symptoms of infection. After noticing this trend, people began to wonder: Could the reviews themselves be a reliable indicator of an increase in the virus?
This theory has been put under a microscope, taking on new prominence amid concerns that there will be no official data to track infections across the United States as another winter approaches.
How the review became a warning sign
Nick Beauchamp, associate professor of political science at Northeastern University, first complained about Yankee Kandel’s theory late last year.
He decided that it wouldn’t be too hard to tell if there was actually a link. Having focused on previous projects that attempted to predict COVID cases using social media data, he sought to create a model to test it.
“I just thought, OK, that’s easy to do. Maybe I’ll just try to scrap some Amazon reviews and see the actual trends, rather than just cutting and pasting some reviews that point to a lack of smell,” he said.
John Grimm/LightRocket via Getty Images
To his surprise, the relationship was clear; COVID cases followed a very similar pattern of repeat reviews.
Here’s a chart of the “no smell” complaints of the three best Yankee candles on Amazon. pic.twitter.com/EFUsGil5k4
– Nick Beauchamp (@nick_beauchamp) December 22, 2021
As Beauchamp’s initial tweets about the results circulated in December 2021, he was quick to add more data to find a definitive answer. By mid-January, he had written a paper and submitted it to a journal, and by June of this year it had been published.
“It’s a very small paper, but it’s a paper that I think has caught a lot of people’s interest, especially because it’s trying to do something more cautious, which a lot of people have noticed in terms of quality on Twitter,” he said.
In the end, the results from the paper showed that the COVID cases were predictive of reviews, which means that if there is a recorded increase in COVID cases, there is likely to be an increase in negative reviews. But can it work in reverse?
“The other thing I was trying to find was, ‘Can we predict COVID cases using reviews?'” “And what we found is that, at least until December 2021, not really. Using past COVID cases to predict future COVID cases is very good, and you can’t do anything better with reviews.”
But then something happened. After adding more data to his model in June of this year, he found that the relationship between revisions and COVID rates has shifted again: revisions are now predictive of COVID rates.
In other words, the rise in negative reviews may actually be a warning sign older than the official COVID data.
“This is either due to a lack of COVID measurement, or worse COVID measurements, or maybe something else has changed. I suppose the reviews themselves haven’t changed much,” Beauchamp said.
One of the interesting reactions Beauchamp noticed was the tweets and the study itself evolved into its own metadata sets, gaining popularity again when users noticed a spike in COVID cases.
Some researchers refer to these trends as “digital navigation paths,” because online activity, such as searching, interacting with old Twitter threads, or in this case, leaving a review, can give unique insight into a person’s real-life circumstances.
As for Beauchamp, he maintains a healthy level of skepticism toward the study, even with all of his controls.
Why some think the official statements are a ‘big mess’
These days, the quality of COVID tracking has become a concern for Beauchamp and other experts working with public health data, especially since President Joe Biden has declared the pandemic “over.”
“Traditional data sources are getting worse,” Beauchamp said. “The CDC is kind of cutting back on their measurements. Everyone measures themselves less frequently. They report these things to government agencies less frequently.”
He also noted the decline in wastewater measurements, and said the frequent interest in Yankee Candle reviews was an example of how many people remain invested in tracking COVID numbers.
“Those of us who still care and worry about the pandemic, and don’t think it’s over, are looking for other sources of data that can be used to track new waves and that kind of thing,” he added. .
Abrar Karan, a physician and infectious disease researcher at Stanford University, said that the evolving nature of the virus has made it difficult to determine the most effective way to collect and analyze COVID data, especially three years after the outbreak of the epidemic.
“Looking back at the beginning of the pandemic, every case we’ve documented has been very significant,” Karan said. “And we’ve been trying to figure out what to do with that data.”
Over time, new issues emerged, such as cases of re-infection and how to document them. Karan also cited reduced testing and decentralization as other obstacles. Many people stop testing frequently, if they stop testing at all, and those who choose to get tested at home often do not report their results to public health departments.
Justin Sullivan / Getty Images
But at this point in the pandemic, Karan said tracing some key sources, even if they are less robust than in previous years, has proven to be an effective strategy, given the breadth of data available from past years.
He said that observing trends in reported cases was the clearest way, as long as there was no recent shift in the amount of tests available.
“The most important question I get asked, as a clinician or epidemiologist, is, ‘What are the risks of doing Activity X for infection with SARS-CoV-2? And honestly, you can really pretty much at this point answer that based on [trend] activity, and less of what is happening around you, because data is a big mess.”
Karan also noted that wastewater data can be very useful, even if it is not very accurate in measuring the number of cases.
Ultimately, Karan said a combination of data sources can help experts and laypeople make the best decisions for themselves regarding their own COVID safety.
“People are constantly weighing these risks and benefits based on limited data, but the data nonetheless. So you can triangulate a lot of things, like all the things we just talked about to get a sense of where we are with the new variables,” he said.
And when it comes to including Yankee candle data in the mix?
“These kinds of things are used in public health more for research,” he said. “But at this point in COVID, I don’t think candlestick reviews are going to change our public health strategy.”
Alternatively, it can be an indication that there is more untouched data online that can be of benefit to the greater good. And if there is, Beauchamp is the best.
“It’s better if we join together in some kind of movement here, if we can,” he said. “So I’m glad to be a small part of that.”
#suspect #COVID #boom #coming #follow #digital #breadcrumbs