Posted in social, technology

Digital doctor: the computer will see you now

Just as people display their emotions through body language and behaviour, your emotional state can now be detected using your Instagram account.

Researchers at the University of Vermont and Harvard University have shown that machine learning algorithms can successfully detect depression from Instagram photos. Currently, the computerised method has a success rate of 70%, a vast improvement on the 42% achieved by general practice doctors diagnosing in-person.

The computerised method has a success rate of 70%

In order to collect the data, the scientists recruited 166 volunteers from Amazon’s Mechanical Turk, half of whom had reported having clinical depression in the last three years. Using well-established psychology research, their Instagram feeds were analysed for signs of depression, including brightness, colour and shading preferences. Pixel analysis of the dataset showed that depressed individuals tended to post bluer, darker and greyer photos than their healthier colleagues. From Instagram’s pre-set filters, it was found that the black-and-white ‘Inkwell’ was the most popular among depressed people. On the other hand, healthy individuals seemed to favour warmer filters such as ‘Valencia’.

Along with colours, the amount of faces shown in photos could also be used to indicate depression. Although depressed people were more likely to post a photo including a face, their photos had, on average, fewer people within the shot. “Fewer faces may be an oblique indicator that depressed users interact in smaller settings,” says Chris Danforth, a professor at the University of Vermont. This is corroborated by previous research linking depression to less social interaction. Or, it indicate that depressed people take more ‘selfies’. However, according to Danforth, this ‘sad-selfie’ hypothesis remains untested.

“So much is encoded in our digital footprint,”

“So much is encoded in our digital footprint,” Danforth explains. “Clever artificial intelligence will be able to find signals, especially for mental illnesses.” It is certainly true that this new technique has potential, especially in terms of early onset diagnoses, avoiding false diagnoses and reducing the cost of mental health screening. However, it is still in its early stages. “This study is not yet a diagnostic test, not by a long shot,” says Danforth. “But it is a proof of concept of a new way to help people.”

Tabitha Watson

Image Credit: []

Posted in biology, physics, technology

Humans vs Neanderthals – the mammoth competition that ended in extinction

After thousands of years, the reason for the Neanderthal’s extinction has finally come to light. Using isotopic analysis, it was found that both ancient humans and the Neanderthals were in direct competition for their main food source – woolly mammoths.

The first anatomically modern humans are thought to have colonised Europe around 43,000 years ago, forcing the Neanderthals into extinction approximately 3,000 years later. So, why did Homo sapiens succeed where the Neanderthals could not? There are many hypotheses, but by far the most common is that the diet of anatomically modern humans was more varied and flexible, allowing them to consume fish. However, a new study by the Senckenberg Research Institute and the Natural History Museum has blown this out of the water.

The hypothesis that early humans had a more varied diet has been fuelled by the observation that they had a higher abundance of 15N in their bone collagen when compared with Neanderthals. This difference was chalked up to the addition of freshwater fish to the diet, a conclusion that has been refuted by  Prof. Dr. Hervé Bocherens and his colleagues at the University of Tübingen.

There are two main explanations for the presence of 15N in ancient human remains – a high concentration of 15N in the natural environment, especially concentrated in the meat of large herbivores whose meat makes up the majority of the diet, or a significant dietary contribution from a single prey with higher 15N abundance than prey usually found at archaeological sites (e.g. fish or mammoth meat).

Until recently, it has not been possible to distinguish between the dietary impact of freshwater fish and mammoth as both are known to have high 15N abundance and comparable levels of the 13C isotope. Due to the overlapping isotope abundances, accurate estimation from collagen alone was not possible. However, due to recent advances in stable nitrogen isotope analysis on individual amino acids, it is possible to identify the exact origin of the proteins consumed by the ancient humans.

In the study, the remains of three anatomically modern humans were examined. Found in the Belogorsk region of south Crimea, the remains were examined for phenylalanine (as a baseline) and glutamic acid (as an indicator of trophic position). Alongside the humans, the fossils of variety of prey animals found during the excavation were also investigated. Using the percentage ratio of the 13C to 15N isotopes present in the proteins of both the ancient humans and their prey, the scientists could establish the main components of their diet. Using this data, it was found that mammoth meat made up around 40-50% of the Homo sapiens’ diet. Isotopic studies of western European Neanderthals have also pointed to a significant consumption of mammoth meat, placing them in direct competition with the ancient humans.

This fierce interspecies competition for resources placed the Neanderthals under extreme stress. Without unrivalled access to their main food source – woolly mammoths – they were unable to forage enough food to survive. Whether due to superior hunting ability, increased brain size or other factors, Homo sapiens emerged on top. Without competition, humans thrived and have persisted until today. However, this is not the case for the poor woolly mammoths.

Tabitha Watson

Image Credit: []

Posted in general, science, technology

Not feeling your selfie?

In a rather Black Mirror turn of events, researchers at the University of Waterloo have developed an app that will tell you how to take ‘the perfect selfie’.

To help you capture your best angle, the app uses an algorithm to direct the way you position the camera.

In order to decide on the ‘best’ angle, the researchers used 3D digital scans of a collection of computer generated people. Then, after taking hundreds of virtual selfies – each with different composition and lighting, an online crowdsourcing service was used to get thousands of people to rate the selfies as either ‘good’ or ‘bad’. These voting patterns were then mathematically modelled in order to develop the algorithm.

To check that the app worked as it should, the researchers had real people take selfies with and without the computerised aid. Based on the subsequent online ratings, a 26% improvement was seen in selfies taken with the app compared to a normal phone camera.

‘We can expand the potential to include variable aspects such as hairstyle, types of smile or even the outfit you wear,’ says Dan Vogel, one of the scientists involved in the development of the app.

Tabitha Watson

To see the app in action, click here.

Image credit: []