High school was not a particularly awesome time in the life of Arthur J. O'Connor. That social fairy dust that some people seem to have? He didn't have it.

"I was a wallflower. I was a nerd," O'Connor says. "I was incredibly intimidated by everybody."

Well, whatever he lacked in cool, O'Connor had in brains. He went on to work a couple of decades on Wall Street in risk management, and then enrolled in a Ph.D. business program where he wrote a paper that's gotten quite a bit of attention: "The Power of Popularity: An Empirical Study of Fan Counts and Consumer Brand Stock Prices."

"My theory was, you know, it's like in high school," he says. "Does being really popular help you win friends [or] help you enhance your performance? And it turns out that, yeah, popularity does seem to help brands."

To test this, O'Connor tracked 30 brands with the most followers on Facebook, including Abercrombie and Fitch, Adidas, Aeropostale, American Eagle Outfitters and Best Buy, among others.

O'Connor tracked the likes of those companies on Facebook for a whole year, while at the same time tracking their daily share price. What he found astonished him.

"So, 99.95 percent of the change could be explained by the change in fan counts," he says. In other words, the overwhelming majority of the change in a company's stock price correlated with the Facebook likes that day or that period.

It's not that Facebook likes caused shares to rise or fall, but the admiration a company gets on social media seems to be a good clue about stock market performance.

Naturally, people on Wall Street are interested, and many of them are already buying "sentiment feeds" and folding them into the algorithms they use to buy and sell stocks. It's kind of like a digital mood ring.

"Typically, our clients are hedge funds and institutional money managers that would look at interpreting this data in different strategies," says Rich Brown, head of financial analytics at Thomson Reuters, one of the largest providers of sentiment analysis.

Thomson Reuters' supercomputers regularly scan 4.5 million news and social media sites for information on what people are saying about a company. Tweets with words like "love" get a positive score; "disappointment" and "jerks" get negative scores.

So, computers can read the news and opinion like people do, but much faster. Does that really give anyone an edge?

"I'm not yet convinced that this is particularly the right approach," says James Liew, who teaches finance at NYU Stern Business School and has a small hedge fund. He studies sentiment analysis, but he's not using it to invest — not yet, anyway.

"A lot of the research that's coming out right now is funded by the sentiment providers," he says. "So they're looking and they're trying to sell this data ... and so the research tends to be a little bit on the biased side."

Liew says it is possible someone is getting rich off of tweets and Facebook posts, but you probably won't hear about it: When people on Wall Street are making tons of money, they don't tend to proclaim it on Twitter.

Copyright NPR 2018.