via Cornell University
When you search for something on the internet, do you scroll through page after page of suggestions – or pick from the first few choices?
Because most people choose from the tops of these lists, they rarely see the vast majority of the options, creating a potential for bias in everything from hiring to media exposure to e-commerce.
In a new paper, Cornell researchers introduce a tool they’ve developed to improve the fairness of online rankings without sacrificing their usefulness or relevance.
“If you could examine all your choices equally and then decide what to pick, that may be considered ideal. But since we can’t do that, rankings become a crucial interface to navigate these choices,” said computer science doctoral student Ashudeep Singh, co-first author of “Controlling Fairness and Bias in Dynamic Learning-to-Rank,” which won the Best Paper Award at the Association for Computing Machinery SIGIR Conference on Research and Development in Information Retrieval, held virtually July 25-30.
“For example, many YouTubers will post videos of the same recipe, but some of them get seen way more than others, even though they might be very similar,” Singh said. “And this happens because of the way search results are presented to us. We generally go down the ranking linearly and our attention drops off fast.”
The researchers’ method, called FairCo, gives roughly equal exposure to equally relevant choices and avoids preferential treatment for items that are already high on the list. This can correct the unfairness inherent in existing algorithms, which can exacerbate inequality and political polarization, and curtail personal choice.
“What ranking systems do is they allocate exposure. So how do we make sure that everybody receives their fair share of exposure?” said Thorsten Joachims, professor of computer science and information science, and the paper’s senior author. “What constitutes fairness is probably very different in, say, an e-commerce system and a system that ranks resumes for a job opening. We came up with computational tools that let you specify fairness criteria, as well as the algorithm that will provably enforce them.”
Online ranking systems were originally based on library science from the 1960s and ’70s, which sought to make it easier for users to find the books they wanted. But this approach can be unfair in two-sided markets, in which one entity wants to find something and another wants to be found.
“Much of machine learning work in optimizing rankings is still very much focused on maximizing utility to the users,” Joachims said. “What we’ve done over the last few years is come up with notions of how to maximize utility while still being fair to the items that are being searched.”
Algorithms that prioritize more popular items can be unfair because the higher a choice appears in the list, the more likely users are to click on and react to it. This creates a “rich get richer” phenomenon where one choice becomes increasingly popular, and other choices go unseen.
Algorithms also seek the most relevant items to searchers, but because the vast majority of people choose one of the first few items in a list, small differences in relevance can lead to huge discrepancies in exposure. For example, if 51% of the readers of a news publication prefer opinion pieces that skew conservative, and 49% prefer essays that are more liberal, all of the top stories highlighted on the home page could conceivably lean conservative, according to the paper.
“When small differences in relevance lead to one side being amplified, that often causes polarization, where some people tend to dominate the conversation and other opinions get dropped without their fair share of attention,” Joachims said. “You might want to use it in an e-commerce system to make sure that if you’re producing a product that 30% of people like, you’re getting a certain amount of exposure based on that. Or if you have a resume database, you could formulate safeguards to make sure it’s not discriminating by race or gender.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Online ranking systems
- Check out Spellbreak Chapter 2's Dominion Mode, Ranked Play, and new questson April 9, 2021 at 9:49 am
Dominion Mode is a capture and control multiplayer for teams of up to five people. What you need to know Spellbreak is a free-to-play online multiplayer Battle Royale created by Proletariat Inc that ...
- Utah still near bottom of vaccination rate rankings — and it’s not just because of the young populationon April 9, 2021 at 8:56 am
Utah continues to languish at the bottom of online trackers that rank states by their COVID-19 immunization ... CDC officials said they couldn’t remove the records from their system, said Tom Hudachko ...
- TAMIU College of Nursing ranked among Texas'most affordable nursing programson April 9, 2021 at 7:46 am
Online resource Best Value Schools has notified ... “As one of the eight nursing programs offered through The Texas A&M University System, TAMIU also happens to be home to a top-ranking program in ...
- PPG Industries (PPG) Adds SEM Products to PPG AdjustRite Systemon April 9, 2021 at 5:54 am
SEM gains direct exposure to PPG AdjustRite system users – truck fleets, repair centers, dealerships and more by posting its catalog online. PPG AdjustRite is ... It currently flaunts a Zacks Rank #1 ...
- VCSU elementary education program ranked best in the nationon April 8, 2021 at 7:21 am
Valley City State University has the top ranked elementary education program in the nation according to rankings recently released by Study.com.
Go deeper with Google Headlines on:
Online ranking systems
Go deeper with Bing News on:
Fairer search results
- A Look At The Fair Value Of Chase Corporation (NYSEMKT:CCF)on April 10, 2021 at 2:30 am
Today we will run through one way of estimating the intrinsic value of Chase Corporation (NYSEMKT:CCF) by taking the expected future cash flows and discounting them to today's value. We will take ...
- Job seekers in the driver’s seat at Navient job fairon April 9, 2021 at 3:11 am
“I saw they were having a job fair through Indeed (a job search website),” Grohol said ... Business casual work environment. The results were promising and a similar drive-through could be tried at ...
- Calculating The Fair Value Of Brookfield Infrastructure Corporation (NYSE:BIPC)on April 8, 2021 at 7:55 am
which results in the Total Equity Value, which in this case is US$3.4b. The last step is to then divide the equity value by the number of shares outstanding. Compared to the current share price of ...
- Funnel Leasing Launches H.O.M.E. to Increase Fair and Equitable Housingon April 7, 2021 at 4:48 am
Funnel, the only renter-centric property management software platform, announced the launch of H.O.M.E. (Housing Opportunities Made Equal), a 501(c)3 not-for-profit, dedicated to building responsible ...
- The Leipzig World Fair of 1784 and the Mississippi Valley: How a map may have affected the settling of Southeast Missourion April 7, 2021 at 4:42 am
On a wintry day in the early 1980s, Bob Keathley of Bernie, Mo., attended an estate sale near Lebanon, Tenn. The items being sold had been collected by a retired medical doctor who had traveled widely ...