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
- NYC elections 2021: Confused about ranked-choice voting? Here’s what you need to knowon April 29, 2021 at 11:42 am
Most voters across the five boroughs will have their first experience with ranked-choice voting in the upcoming June primaries. The new system, which passed as part of a citywide referendum in 2019, ...
- Battling public health misinformation onlineon April 28, 2021 at 9:00 pm
Social media and web-based news channels became a communication superhighway for correct and incorrect public health information during the COVID-19 pandemic. The study of this vast amount of ...
- Pa. State System moves ahead with mergers of 6 universities, including California, Clarion, Edinboroon April 28, 2021 at 8:11 am
Plans to consolidate six struggling state-owned universities into two mega schools with six campuses were approved for public comment Wednesday morning. The board of governors of the Pennsylvania ...
- Northeast earns rankings for affordability, popularity in online, trade programson April 28, 2021 at 6:54 am
Northeast Community College has recently landed on several rankings lists among other schools around Nebraska and the U.S. that offer trade education and online associate’s degrees.
- The surge of retail traders entering the stock market is straining systems for online brokerson April 27, 2021 at 12:03 pm
Website and trade execution problems are among the issues reported by retail investors in a J.D. Power satisfaction survey.
Go deeper with Google Headlines on:
Online ranking systems
Go deeper with Bing News on:
Fairer search results
- Australia’s consumer watchdog says Google and Apple need fairer app storeson April 30, 2021 at 1:25 am
Australia’s consumer watchdog, the Australian Competition and Consumer Commission (ACCC), has released a report saying Apple and Google’s dominance in the Australian app market represents an unfair ...
- Estimating The Fair Value Of Casey's General Stores, Inc. (NASDAQ:CASY)on April 29, 2021 at 10:31 pm
Does the April share price for Casey's General Stores, Inc. (NASDAQ:CASY) reflect what it's really worth? Today, we will estimate the stock's intrinsic value by estimating the company's future cash ...
- How to invest in a fairer and low carbon energy systemon April 29, 2021 at 9:00 pm
Governments throughout the world have accelerated their ambitions towards effective climate change mitigation. What is clear, in this challenge of how to tackle the complex and global issue of climate ...
- As Trump seizes on Arizona ballot audit, election officials fear partisan vote counts could be the norm in future electionson April 29, 2021 at 5:55 pm
The GOP-backed recount of Maricopa County’s ballots has been criticized for abandoning state guidelines and allowing the rules to be set by a private contractor who promoted claims that the election ...
- Pandemic Shifts Spring Career Fair to a Successful Virtual Formaton April 29, 2021 at 7:21 am
In an effort to support over 900 students with their spring 2021 Arch semester-away search, the Center for Career and Professional Development (CCPD) at Rensselaer Polytechnic Institute continues to ...