Connect with us

General

Facebook Changes Algorithm, Promises More Personalized News Feed

Advertisement
Free ship for order included. No promo code needed, visit site to see more details and any exclusions.

Facebook’s News Feed is finally getting more personal.

The social network on Thursday announced two ranking updates based on user surveys.

One prioritizes the friends someone might want to hear from most, while the other prioritizes the links a person might consider most worthwhile.

“It’s not about the amount of time someone spends on Facebook, but rather the quality of time spent,” a company blog post said. “That means making sure people see what they want to see—whether that’s posts from family and friends or news articles and videos from Pages they follow.”

The platform has long taken its cues from signals like how often someone interacts with a given friend, how many mutual friends they share, and whether they mark someone as a “close friend.”

In a modern twist, Facebook has begun actually asking people whom they’d most like to hear from. Some folks may remember taking an online survey and listing the friends you are closest to.

“We look at the patterns that emerge from the results, some of which include being tagged in the same photos, continuously reacting and commenting on the same posts, and checking-in at the same places—and then use these patterns to inform our algorithm,” the blog said.

That doesn’t mean your News Feed will be clogged with the same seven mates’ posts. Nor does it guarantee you’ll see more friend content. According to Facebook, it simply increases the chances of viewing posts from those you have a close relationship with higher on the page.

“We also know that whomever you want to hear from right now may not be who you want to hear from in a year, or even a few months,” the firm said.

After all, human emotions are a fickle thing.

With that in mind, Facebook’s prediction models are “continuously updated” based on user interactions. You can also expect some more surveys.

Last month, the social media giant lifted the curtain on its News Feed algorithm with the new “Why am I seeing this post?” tool, which provides more details about and control over users’ experience.

Just tap the three dots in the top right corner of a post to find the feature; a drop-down menu explains how past interactions impact the ranking of content in your feed.

That includes why you’re seeing a certain post (if it’s from a friend you made, Group you joined, or Page you followed) and what has the largest influence over order of material (how often you interact with people/Groups/Pages and their videos, photos, or links; the popularity of posts shared by those you follow).

You’ll also find access to controls like See First, Unfollow, News Feed Preferences, and Privacy Shortcuts to help personalize your site.

Facebook is also using survey responses to identify rewarding links.

More on Geek.com:

SOURCE

Advertisement
Code: VZWDEAL. Enter this coupon code at checkout to get $100 discount on Samsung Galaxy Note 8. Includes free shipping. Restrictions may apply. Device payment purchase required.
Nifty and lovely! Check out our stripe cotton blouse with skinny shorts! What are you waiting for? Just shop now!

General

Polaroid Lab Turns Smartphone Snaps Into Instant Photos

Advertisement
Code: VZWDEAL. Enter this coupon code at checkout to get $100 discount on Samsung Galaxy Note 8. Includes free shipping. Restrictions may apply. Device payment purchase required.

Like live theater and paper books, printed pictures provide a sense of presence that movies, e-books, and digital images lack.

It’s that feeling—plus a hint of nostalgia—that keeps Polaroid in business.

Now, the company is launching a portable printer* that turns smartphone snaps into instant photos.

“Unlimited cloud storage can actually be your memories’ worst enemy, causing your digital photos to skyrocket in numbers and end up falling into a void of oblivion,” Polaroid CEO Oskar Smolokowski said in a statement.

[embedded content]

With a camera in every pocket, people are taking more pictures than ever. But it’s easy to lose track of special moments among a sea of online pixels.

Enter Polaroid Lab.

The idea, according to Smolokowski, is to turn precious pictures into tangible photographs, “bringing them into the world as something you can hold in your hand and store on the fridge door rather than in the cloud.”

Simply select an image from the Polaroid Originals app, place your handset on top of the machine, press a button, and voila! An instant photo (that you don’t need to shake).

Using a combination of mirrors, light, and “the unique Polaroid chemistry,” snaps are recast as instant pictures (via Polaroid)

The appliance uses a combination of mirrors, light, and “the unique Polaroid chemistry” to recast snapshots as a leave-to-develop, white-rimmed keepsake.

Starting in October, you can make pictures instead of just taking them with the $130 Polaroid Lab, compatible with iPhone 6S/iOS 11 and above, Android 7 or higher, and current Samsung, Huawei, Google Pixel, and One Plus models.

Sign up for the company newsletter “to get your hands on one first.”

*According to Polaroid, its new device is “not a printer, not a scanner, just an instant formula for timeless images.

More on Geek.com:

SOURCE

Advertisement
Click this link to get $200 discount on iPad. Includes free shipping. Restrictions may apply.
Continue Reading

General

McDonald’s Plans to Serve AI Voice Technology at Drive Thru

Advertisement
Samsung J7 V just $5 mo. New device payment purchase req'd. Plus, free shipping.

McDonald’s is slowly but surely eliminating humans workers from its fast-food equation.

Following the rollout of self-order kiosks and “personalized” menus, the burger empire plans to automate drive-thrus with its acquisition of Apprente.

The Silicon Valley startup, purchased for an undisclosed sum, was founded in 2017 to create voice-based platforms for multilingual, multi-accent, and multi-item conversational ordering.

Now, McDonald’s wants to use the system for faster, simpler, and more accurate order taking.

“Building our technology infrastructure and digital capabilities are fundamental … and enable us to meet rising expectations from our customers, while making it simpler and even more enjoyable for crew members to serve guests,” McD’s CEO Steve Easterbrook said in a statement.

It’s not entirely clear exactly how the Apprente tech will work; McDonald’s has already tested the automation solutions at select restaurants, but provided no further details.

“Apprente was born out of an opportunity to use technology to solve challenging real-world problems,” according to co-founder Itamar Arel. “And we’re thrilled to now apply this to creating personalized experiences for customers and crew.”

Arel & Co. will be founding members of a new in-house team called McD Tech Labs, expected to grow with the addition of engineers, data scientists, and other experts in the future.

While the initial focus will be to enhance McDonald’s drive thrus, the company aims to incorporate this technology into mobile ordering and kiosks.

“As we all know, technology can change by the day. And with that, so do our customers’ expectations,” a Golden Arches press release said. “We are committed to delivering the best possible experience for restaurant crew and our customers. And this is only the beginning.”

Earlier this year, McDonald’s purchased AI platform Dynamic Yield, teasing upcoming “personalized” menu options related to time of day, weather, current restaurant traffic, and trending items.

The electronic bill of fares even understands current service times, suggesting only those things that are easy to make during peak hours, in an effort to keep the drive thru running smoothly.

More on Geek.com:

SOURCE

Advertisement
Code: VZWDEAL. Enter this coupon code at checkout to get $100 discount on Samsung Galaxy Note 8. Includes free shipping. Restrictions may apply. Device payment purchase required.
Code: OAIKKNDU. Only $9.99 for Cooking Utensil Kit Beech Natural Polished Cookware Gadgets with $3 coupon code OAIKKNDU
Continue Reading

General

Machine Learning Estimates Risk of Cardiovascular Death

Advertisement
Code: VZWDEAL. Enter this coupon code at checkout to get $100 discount on Samsung Galaxy Note 8. Includes free shipping. Restrictions may apply. Device payment purchase required.

MIT researchers have developed a machine learning model that can estimate, based on the electrical activity of their heart, a patient’s risk of cardiovascular death.

The system, dubbed “RiskCardio,” was created by the Computer Science and Artificial Intelligence Laboratory (CSAIL) with the intention of better predicting health outcomes.

It focuses on folks who have survived acute coronary syndrome (ACS)—a range of conditions involving decreased flow to the heart. Just 15 minutes of a patient’s raw electrocardiogram (ECG) signal can produce a score that places people into different risk categories.

“We’re looking at the data problem of how we can incorporate very long time series into risk scores, and the clinical problem of how we can help doctors identify patients at high risk after an acute coronary event,” lead study author Divya Shanmugam said in a statement.

“The intersection of machine learning and healthcare is replete with combinations like this—a compelling computer science problem with potential real-world impact,” she added.

This isn’t the first machine-learning attempt at risk metrics; previous experiments have used external patient information like age or weight, or knowledge and expertise specific to the system.

RiskCardio, however, relies solely on patients’ raw ECG signal—with no added information.

Say someone checks into the hospital after an ACS: A physician would normally estimate risk of cardiovascular death or heart attack using medical data and lengthy tests before choosing a course of treatment.

MIT’s invention aims to improve that first step.

The team tested their model using data from a study of past patients, separating each person’s signal into a collection of adjacent heartbeats. They then assigned a label—”risky” for those who died of cardiovascular complications and “normal” for those who survived—to each set of beats.

When demonstrated on a new patient, CSAIL analysts were able to estimate whether someone would suffer from cardiovascular death within 30, 60, 90, or 365 days.

Moving forward, the team hopes to make the dataset more inclusive to account for different ages, ethnicities, and genders, and evaluate how their system accounts for ambiguous cases.

“Machine learning is particularly good at identifying patterns, which is deeply relevant to assessing patient risk,” Shanmugam said. “Risk scores are useful for communicating patient state, which is valuable for making efficient care decisions.”

More on Geek.com:

SOURCE

Advertisement
Samsung J7 V just $5 mo. New device payment purchase req'd. Plus, free shipping.
Code: MenCamo. Check our camo shorts for men! Save 29-3,59-7,89-11 with coupon “MenCamo”. We offer FREE SHIPPING WORLDWIDE! (Ends: 2018/12/31)
Continue Reading

Deals

Advertisement
A member of the Nordstrom family, HauteLook is a premier online destination offering limited-time flash sale events at insider prices up to 75% off. Every day at 8AM Pacific, we launch new events featuring the best names in women�s and men�s fashion and accessories, beauty, kids� apparel and toys, a
Shop Performance Ready Women's Styles with Free Shipping!
Get Free Shipping and Free Exchanges on All Birkenstocks!

Trending