Connect with us

Technology

AI is trained to ‘predict’ academic performance based on test scores and social posts

Published

on

ai is trained to predict academic performance based on test scores and social posts

It may be difficult to predict how well a student will perform academically, but a new innovation can do so just by looking at their tweets – and with more than 93 percent accuracy.

A computer model trained on thousands of test scores and one million social media posts to distinguishing between high academic achievers and lower ones based on textual features shared in posts.

The technology, powered by artificial intelligence, determined that students who discuss scientific and cultural topics, along with writing lengthy posts and words are likely to perform well.

However, those who use an abundance of emojis, words or entire phrases written in in capital letters and vocabulary related to horoscopes, driving and military service tend to receive lower grades in school.

The team notes that by ‘predict’ they do not mean the system creates a future forecast, but rather a correlation between posts and real test scores students earned.

The use of capitalized words, emojis and exclamations were found to be negatively correlated with academic performance. On the other hand, using Latin characters, creating average post and word length, extensive vocabulary size, and entropy of users' texts were found to positively correlate with academic performance

The use of capitalized words, emojis and exclamations were found to be negatively correlated with academic performance. On the other hand, using Latin characters, creating average post and word length, extensive vocabulary size, and entropy of users' texts were found to positively correlate with academic performance

The use of capitalized words, emojis and exclamations were found to be negatively correlated with academic performance. On the other hand, using Latin characters, creating average post and word length, extensive vocabulary size, and entropy of users’ texts were found to positively correlate with academic performance

The study was conducted by a team from the National Research University Higher School of Economics, which employed a prediction model that uses mathematical textual analysis capable of rating words, phrases, topics and other content in social media posts.

Ivan Smirnov, the lead researcher, is the mastermind behind the system and experiment gathered test scores from 2,468 students who took the Program for International Students Assessment (PISA), which is a testing system used to measure pupils’ performance in math, science and reading.

Along with the exam, the dataset included more than 130,00 social media posts from the European social media site VKontakte – a Facebook alternative. 

 The results were compared with the average Unified State Exam, which is the equivalent to the SAT test in the US.

Highest scores include (orange): English words; Words related to literature ; Concepts related to reading; Terms and names related to physics; Words related to thought processes. The lower scores (green) included misspelled words, names of popular computer games, concepts related to military service, horoscope terms , and words related to driving and car accidents

Highest scores include (orange): English words; Words related to literature ; Concepts related to reading; Terms and names related to physics; Words related to thought processes. The lower scores (green) included misspelled words, names of popular computer games, concepts related to military service, horoscope terms , and words related to driving and car accidents

Highest scores include (orange): English words; Words related to literature ; Concepts related to reading; Terms and names related to physics; Words related to thought processes. The lower scores (green) included misspelled words, names of popular computer games, concepts related to military service, horoscope terms , and words related to driving and car accidents

In total, more than 1 million posts of almost 39,000 users were analyzed.

The team also gathered posts shared by students, with their consent, from the European social media site VKontakte – a Facebook alternative.

A total of 130,575 posts were used as the training sample for the prediction model, along with PISA tests.

When developing and testing the model from the PISA test, only students’ reading scores were used an indicator of academic aptitude.

Altogether, the system was trained on 1.9 billion words, with 2.5 million unique words – and the model went to work with ranking textual features in posts.

The use of capitalized words (-0.08), emojis (-0.06) and exclamations (-0.04) were found to be negatively correlated with academic performance.

On the other hand, using Latin characters, creating average post and word length, extensive vocabulary size, and entropy of users’ texts were found to positively correlate with academic performance (from 0.07 to 0.16, respectively).

Smirnov explored the resulting model by selecting 400 words with the highest and lowest scores that appear at least 5 times in the training sample. 

The team notes that by 'predict' they do not mean the system creates a future forecast, but rather a correlation between posts and real test scores students earned

The team notes that by 'predict' they do not mean the system creates a future forecast, but rather a correlation between posts and real test scores students earned

The team notes that by ‘predict’ they do not mean the system creates a future forecast, but rather a correlation between posts and real test scores students earned

The cluster with the highest scores include: English words (above, saying, yours, must); Words related to literature (Bradbury, Fahrenheit, Orwell, Huxley, Faulkner, Nabokov, Brodsky, Camus, Mann); Concepts related to reading (read, publish, book, volume); Terms and names related to physics (Universe, quantum, theory, Einstein, Newton, Hawking); Words related to thought processes (thinking, memorizing).

The second batch that indicated lower scores included misspelled words, names of popular computer games, concepts related to military service (army, oath, etc.), horoscope terms (Aries, Sagittarius), and words related to driving and car accidents (collision, traffic police, wheels, tuning).

‘Based on these rules, our model identified students with high and low academic performance using Vkontakte posts with an accuracy of up to 94%. We also tried to apply it to short texts on Twitter – successfully,’ says Smirnov. 

This post first appeared on dailymail.co.uk

Advertisement
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Technology

False widow spiders’ fangs carry harmful bacteria resistant to antibiotic treatments

Published

on

By

false widow spiders fangs carry harmful bacteria resistant to antibiotic treatments

Many fear the bite of a false black widow spider, which can lead to painful swelling, stiffness and large abscesses.

In rare cases it’s been blamed for paralysis, amputations and even death, but a new study confirms it’s not the arachnid’s bite that’s dangerous—it’s the bacteria on its fangs. 

In a new study published in Scientific Reports, researchers found spiders carry bacteria on their fangs that can infect humans.

And the germs the false black widow carries can be resistant to common antibiotics.

‘Antimicrobial resistance is an urgent and growing problem worldwide,’ said co-author Aoife Boyd, a pathologist at NUI Galway’s School of Natural Sciences. ‘[An approach connecting] human, animal and environmental health is the only way to tackle the problem.’  

Scroll down for video  

Researchers in Ireland confirmed the false widow spider carries a dozen pathogens that are harmful to humans. Though its bite is fairly harmless, its fangs can transmit antibiotic-resistant bacteria into its human victims.

Researchers in Ireland confirmed the false widow spider carries a dozen pathogens that are harmful to humans. Though its bite is fairly harmless, its fangs can transmit antibiotic-resistant bacteria into its human victims.

Researchers in Ireland confirmed the false widow spider carries a dozen pathogens that are harmful to humans. Though the arachnid’s bite is fairly harmless, its fangs can transmit antibiotic-resistant bacteria into its human victims

Previously, rare ‘skin-eating’ infections following seemingly harmless spider bites were often blamed on victims scratching their bites with dirty fingernails. 

But Boyd and his colleagues theorized the bacteria was coming from the spiders themselves.  

They swabbed some noble false widows for bacteria, and did the same to some lace-weaver and giant house spiders, also both common in the UK.

All the arachnids were rife with germs: Out  22 bacterial species found on the false widows, 12 were potentially pathogenic to humans, according to Science Alert.

She went to the GP and was given antibiotics for the infection

She went to the GP and was given antibiotics for the infection

The false widow spider migrated to the UK in the 1870s but has been spreading globally in recent years 

A false widow spider bite can become infected with bacteria, leading to large pus-filled abscesses. Some strains the false widow carries are multi-drug resistant, 'making them particularly difficult to treat with regular medicine'

A false widow spider bite can become infected with bacteria, leading to large pus-filled abscesses. Some strains the false widow carries are multi-drug resistant, 'making them particularly difficult to treat with regular medicine'

A false widow spider bite can become infected with bacteria, leading to large pus-filled abscesses. Some strains the false widow carries are multi-drug resistant, ‘making them particularly difficult to treat with regular medicine’

‘Our study demonstrates that spiders are not just venomous but are also carriers of dangerous bacteria capable of producing severe infections,’ said Neyaz Khan, an NUI Galway microbiologist,.  

Less than a dozen species of European spiders have fangs strong enough to pierce human skin.

‘But only one of them, the recent invasive noble false widow spider, is considered of medical importance,’ said co-author John Dunbar, zoologist at the Ryan Institute’s Venom System Lab.

WHAT IS A FALSE WIDOW SPIDER? 

False widow spiders, also known as noble widows, are distinctive for their shiny, black flesh, bulbous bodies, thick legs and skull-like patterns.

It’s native to the Canary Islands but migrated to the UK and Europe in the late 1800s, purportedly aboard a shipment of bananas. 

Millions of false widows have been found across the UK and the population is believed to be growing. 

The spiders have also been reported in California and Chile. 

alt

The species has a brown bulbous abdomen with cream markings that look like a skull. They have long legs and can reach about a half-inch in size.

Also known as steatoda nobilis, the spider is frequently confused for the black widow, which has deadly venom.  

 

<!—->Advertisement

False widow spiders, also known as noble false widows, are distinctive for their shiny, black flesh, bulbous bodies, thick legs and skull-like patterns. 

Typically a noble widow’s bite, which itself is fairly painless, results in just some redness and pain.

But if bacteria is passed along, an infection can occur—in rare cases, serious enough to require antibiotics or a hospital stay.

The biggest threat is some strains the false widow carries are multi-drug resistant, ‘making them particularly difficult to treat with regular medicine,’ said Kahn.

In 2016, a Hampshire woman was believed to have been bitten by a false widow and had to have part of her finger amputated.

The woman, 60, was eventually hospitalized and died of sepsis, the BBC reported.

The noble widow first arrived in the UK from the Canary Islands in the 1870s and has been a regular presence in southern England for more than 150 years.

Now it’s appearing in northern England, Ireland and even France. 

The spiders have also been reported in California and Chile. 

That massive population growth has led to a spike in serious cases, including those hard to treat with common antibiotics, according to the report.

Beyond the danger to humans, experts also worry that the false widow spreading its web across the globe poses a serious threat to wildlife.

Rainer Breitling, a biologist at the University of Manchester, fears they’ll attack ‘vulnerable native species’ in their new environments, in some cases prey much larger than the spider itself.

That, in turn, could disrupt the food chain and affect regional ecosystems.

Researchers in Germany used computer modelling to predict favorable habitats for false widow invasions, based on present patterns.

The model successfully predicted the species would migrate to Normandy.

Mediterranean islands, southern Australia, large parts of New Zealand and South Africa also seem to be likely targets for future expansion.

‘These are areas that are home to a wide range of vulnerable native species, so the potential introduction of Steatoda nobilis, which can overcome prey much larger than its own size, is quite worrying,’ said Breitling.

While the spider’s migration was originally blamed on a shipment of bananas, researchers now believe it hitches a ride on ornamental plants or tourists.

‘So more careful monitoring of plant imports could be useful to control the spread of this species and other invasive spiders,’ said Breitling.  

This post first appeared on dailymail.co.uk

Continue Reading

Technology

Elon Musk’s Boring Company hosts a ‘tunnel rave’ insides its Las Vegas Loop

Published

on

By

elon musks boring company hosts a tunnel rave insides its las vegas loop

Elon Musk’s The Boring Company celebrated the near competition of its Las Vegas Convention Center Loop’s site by hosting a ‘tunnel rave’ inside the facility.

The firm shared a first look inside with three Tesla vehicles parked at the boarding area, along with flashing lights and dance music by the late musician Avici playing in the background.

The video, shared on Twitter,  was shot inside the Loop’s hub where passengers will be transported from one end of the convention center to the other in a Model 3 electric vehicle.

The Boring Company plans to begin operations of the system in January that it says cuts the 15 minute walk from one end of the campus to the other down to just one minute.

Scroll down for video 

The Boring Company shared a first look inside with three Tesla vehicles parked at the boarding area, along with flashing lights and dance music by the late musician Avici playing in the background

The Boring Company shared a first look inside with three Tesla vehicles parked at the boarding area, along with flashing lights and dance music by the late musician Avici playing in the background

The Boring Company shared a first look inside with three Tesla vehicles parked at the boarding area, along with flashing lights and dance music by the late musician Avici playing in the background

‘During typical peak hours, driving from the Las Vegas Convention Center to Mandalay Bay, for example, can take up to 30 minutes,’ reads the firm’s website.

‘The same trip on Vegas Loop will take approximately 3 minutes.’

The Boring Company claims the Tesla vehicles will reach top speeds of 155 miles per hour, making the trip more of a sprint than a sluggish shuttle ride.

In May, the company completed its excavation of one of two tunnels making up the convention center loop.

Musk shared renders (pictured) earlier this year of what the area will look like once it is complete. Above the tunnels is a display showing passengers when and where their vehicles will depart and, for color, a sprawling wall ad for Las Vegas tourism sporting the city's 'What happens in Vegas, only happens here' slogan

Musk shared renders (pictured) earlier this year of what the area will look like once it is complete. Above the tunnels is a display showing passengers when and where their vehicles will depart and, for color, a sprawling wall ad for Las Vegas tourism sporting the city's 'What happens in Vegas, only happens here' slogan

Musk shared renders (pictured) earlier this year of what the area will look like once it is complete. Above the tunnels is a display showing passengers when and where their vehicles will depart and, for color, a sprawling wall ad for Las Vegas tourism sporting the city’s ‘What happens in Vegas, only happens here’ slogan

The Vegas loop will first included the Las Vegas Convention Center, but the firm plans to expand it to run along the Strip, McCarran International Airport, Allegiant Stadium, downtown Las Vegas and eventually to Los Angeles.

The system was first announced in May 2019, but like most of Musk’s projects the loop hit a three-month delay.

However, the process appears to be moving along, as The Boring Company is currently receiving approval for a number of agreements and is putting the final touches on the 0.8-mile-long tunnels and passenger stations.

And in the spirit of things, the firm decided to through a part in the passenger loading area – complete with strobe lights and dance music.

Musk shared renders earlier this year of what the area will look like once it is complete.

The video, shared on Twitter , was shot inside the Loop’s hub where passengers will be transported from one end of the convention center to the other in a Model 3 electric vehicle

The video, shared on Twitter , was shot inside the Loop’s hub where passengers will be transported from one end of the convention center to the other in a Model 3 electric vehicle

The video, shared on Twitter , was shot inside the Loop’s hub where passengers will be transported from one end of the convention center to the other in a Model 3 electric vehicle

Above the tunnels is a display showing passengers when and where their vehicles will depart and, for color, a sprawling wall ad for Las Vegas tourism sporting the city’s ‘What happens in Vegas, only happens here’ slogan.

The cars will use onboard self-driving software to navigate the tunnels in addition to ‘tracking wheel’ which guide the vehicle along its specific lane.

The renders are, of course, only tentative his point and could change drastically between now and when the station is actually built.

They do, however, show the progression of Musk’s Las Vegas loop, which he said in a corresponding tweet is ‘coming soon.’

This post first appeared on dailymail.co.uk

Continue Reading

Technology

Robocallers pose as Apple and Amazon support in new scam

Published

on

By

robocallers pose as apple and amazon support in new scam

The Federal Trade Commission (FTC) is warning consumers of a new robocall scheme where scammers are posing as Apple and Amazon support.

Robocallers are using recorded messages that tell the person that something is wrong with their account like a suspicious purchase, lost package or their iCloud was breached.

The message prompts them to press ‘one’ to speak with customer service in order to discuss the problem – and this is where the scamming begins.

A fake representative is then connected and will attempt to extract a consumer’s personal information, like their credit card number or account passwords.

Scroll down for video 

Robocallers are using recorded messages tell the person, along with using their name, that something is wrong with their account like a suspicious purchase, lost package or their iCloud was breached

Robocallers are using recorded messages tell the person, along with using their name, that something is wrong with their account like a suspicious purchase, lost package or their iCloud was breached

Robocallers are using recorded messages tell the person, along with using their name, that something is wrong with their account like a suspicious purchase, lost package or their iCloud was breached 

‘If you get an unexpected call or message about a problem with any of your accounts, hang up,’ the FTC said. ‘Do not press 1 to speak with customer support, do not call a phone number they gave you, do not give out your personal information.’

The FTC found two parts of this scam – a caller acting as an employee of Amazon or Apple.

For the Amazon scheme, unsuspecting victims will be told there’s something wrong with your account. It could be a suspicious purchase, a lost package, or an order they can’t fulfill.

‘An unauthorized purchase of an iPhone XR 64 GB for $749 is being ordered from your Amazon account,’ the recording states.

The message prompts the individual to press 'one' to speak with customer service in order to discuss the problem – and this is where the scamming begins. A robocaller is then connected and will attempt to extract a consumer's personal information, like their credit card number or account passwords

The message prompts the individual to press 'one' to speak with customer service in order to discuss the problem – and this is where the scamming begins. A robocaller is then connected and will attempt to extract a consumer's personal information, like their credit card number or account passwords

The message prompts the individual to press ‘one’ to speak with customer service in order to discuss the problem – and this is where the scamming begins. A robocaller is then connected and will attempt to extract a consumer’s personal information, like their credit card number or account passwords 

‘To cancel your order or to connect with one of our customer support representatives please press one or simply stay on the line.’

In the scam disguised as Apple, the robocaller says: ‘Suspicious activity in your iCloud account, your iCloud account has been breached.’

‘Before you use any Apple device, please contact Apple support adviser.’

And again, prompts the person to press on to connect to the scammer.

Robocalls have become a major issue in the US.

Some 58 billion scam calls were made in 2019, an increase over 11 billion from the previous year.

However, in 2020 the number of calls took a dramatic dive to 30 billion across the nation.

In 2019, Americans, on average were hit with 15 robocalls per person in April, but exactly one year later that number decreased to 8.7 calls per person.

The decrease may stem from anti-robocall measures put into place December 2019.

In addition to fining convicted spammers from $1,500 to up to $10,000, the bill, signed by President Donald Trump, gives authorities more enforcement powers and looks to accelerate measures the industry is already taking to identify robocalls.

White House press secretary Stephanie Grisham said: ‘American families deserve control over their communications, and this legislation will update our laws and regulations to stiffen penalties, increase transparency, and enhance government collaboration to stop unwanted solicitation.’ 

This post first appeared on dailymail.co.uk

Continue Reading

Trending

Copyright © 2020 DiazHub.