SoylentNews is people
SoylentNews
from the department-of-unwanted-hyperfocus dept.
Researchers at the Cornell and the Technische Univerität Berlin and Cornell have studied the problem that more popular items get priority in search results, creating a positive feedback loop that unfairly deprecates other, equally valuable items.
Rankings are the primary interface through which many online platforms match users to items (e.g. news, products, music, video). In these two-sided markets, not only the users draw utility from the rankings, but the rankings also determine the utility (e.g. exposure, revenue) for the item providers (e.g. publishers, sellers, artists, studios). It has already been noted that myopically optimizing utility to the users – as done by virtually all learning-to-rank algorithms – can be unfair to the item providers. We, therefore, present a learning-to-rank approach for explicitly enforcing merit-based fairness guarantees to groups of items (e.g. articles by the same publisher, tracks by the same artist). In particular, we propose a learning algorithm that ensures notions of amortized group fairness, while simultaneously learning the ranking function from implicit feedback data. The algorithm takes the form of a controller that integrates unbiased estimators for both fairness and utility, dynamically adapting both as more data becomes available. In addition to its rigorous theoretical foundation and convergence guarantees, we find empirically that the algorithm is highly practical and robust.
Journal Reference:
Marco Morik, Ashudeep Singh, Jessica Hong, and Thorsten Joachims. 2020. Controlling Fairness and Bias in Dynamic Learning-to-Rank. In Proceedings
of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '20), July 25–30, 2020, Virtual Event, China.
ACM, NewYork, NY, USA. DOI: https://doi.org/10.1145/3397271.3401100
Maybe this, if deployed widely, can help reduce the tendencies for discourse to develop isolated silos.
(Score: 2) by The Mighty Buzzard on Monday August 24 2020, @05:04PM (5 children)
No, a search engine should give you the most popular results for the query you give it. It's on you if you ask for the wrong thing. Popular means it's going to be the correct result for the most people, which is what a search engine should be aiming for.
My rights don't end where your fear begins.
(Score: 3, Insightful) by Lester on Monday August 24 2020, @06:28PM (2 children)
No. A search engine should give you the results that you would select if you could read all the results. The first approach is to suppose that those picked by people were the best. But this approach has turn into an endogàmic system.
(Score: 0) by Anonymous Coward on Tuesday August 25 2020, @02:04AM
This, a search engine should aspire to scanning every website out there as frequently as possible and giving you as close to what you ask for as possible. If what you ask for isn't what you want, then the search engine should allow you some method of changing your request to get what you want.
One of the reasons why I use duckduckgo is that they try to give me what I ask for rather than what they think I want. The result is that it's less likely that I'm going to wind up in a bubble having my expectations changed in a self-reinforcing cycle.
(Score: 2) by The Mighty Buzzard on Tuesday August 25 2020, @03:04PM
No, to do that a search engine would need to know way more about you than any site has any business knowing about you. The most popular result for a given search input is what should be returned.
My rights don't end where your fear begins.
(Score: 0) by Anonymous Coward on Tuesday August 25 2020, @08:48PM (1 child)
By your definition, when you ask a search engine "what is 2 + 2", the search engine should return you "5" if the majority of people find that to be the right answer.
Be careful what you wish for...
(Score: 2) by The Mighty Buzzard on Wednesday August 26 2020, @02:08PM
And? Search engines should not be catering to what a few people who think they know better than everyone else want. Only fascists think like that.
My rights don't end where your fear begins.