A Robot Tutor That Encourages Bored Students To Learn

Scientists have developed a new robot teacher that can detect whether children are distracted in class and accordingly respond to encourage them. Researchers at the Department of Artificial Intelligence in Madrid have developed an integrated computational architecture (Artie) for use with software applications in schools. The main goal of this work was to design a system that can detect the emotional state of primary school children interacting with educational software and make pedagogic interventions with a robot tutor that can ultimately improve the learning experience. Rather than focusing on specific emotions, the researchers first identified three cognitive states (concentrating, distracted and inactive) known to influence the course of learning. Keyboard strokes and mouse actions of children using educational software were used to predict which of these cognitive states the child is experiencing and subsequently linked to an algorithm that chooses the correct form of pedagogic intervention. These could be words and gestures of encouragement or attempts to raise interest and motivation for a specific learning objective, all of which can be delivered by a robot tutor.

A Way To Spot False FB Posts, Tweets

Scientists have developed a new method for spotting people who post false reviews or tweets from multiple social media accounts to espouse opinions. Researchers from the University of Texas have devised a statistical method that analyses multiple writing samples – a practice known as “astroturfing”. They found that it was challenging for authors to completely conceal their writing style in their text. Based on word choice, punctuation and context, the method was able to detect whether one person or multiple people were responsible for the samples. Researchers used writhing samples from online commenter’s on news websites and discovered that many people espousing their opinions online were all linked to a few singular writers with multiple accounts. Astroturfing is legal, but it is questionable ethically. The practice has been used by businesses to manipulate social media users by having one paid associate posts false reviews on sites about products for sale. Politicians have also been accused of astroturfing to create the illusion of public support for a campaign. Former US President George Bush, Hillary Clinton and Donald Trump have been accused of astroturfing.

Onion Compound May Treat Ovarian Cancer

A natural compound isolated from onions may help ovarian cancer, a new study has claimed. Researchers from Kumamoto University in Japan studied the effects of onionin A (ONA) on a preclinical model of epithelial ovarian cancer (EOC) both in vivo and in vitro. Previously, researchers found that ONA suppressed pro-tumour activation of host myeloid cells. According to WHO, EOC is the most common type ovarian cancer and has a five year survival rate of about 40%. The group’s in vitro experiments showed that EOCs which usually proliferate in the presence of pro tumour M2 macrophages, showed inhibited growth after introduction of ONA. This was thought to be due to ONA influence of STAT3, a transcription factor known to be involved in both M2 polarization and cancer cell proliferation. The team also found that ONA inhibited the pro-tumour function of myeloid-derived suppressor cells, which are associated with the suppression of the anti-tumour immune response of host lymphocytes, by using preclinical sarcoma model. ONA was also found to enhance the effects of anti-cancer drugs by strengthening their anti-proliferation capabilities.

Robots Can Almost Replace Judges

Courtrooms could soon have robots as judges, after scientists managed to develop an artificial intelligence (AI) system capable of predicting verdicts with 79% accuracy. The artificially intelligent judges were able to look at legal evidence as well as consider ethical questions to decide how a case should be resolved. The algorithm looked at data sets of 584 cases relating to torture and degrading treatment, fair trials and privacy. The computer was able to look through that information and make its own decision – which lined up with those made by Europe’s most senior judges in almost every case. The researchers said that the computer judge wasn’t likely to take the place of judges any time soon. But it could be used to help them out – prioritizing cases that are important or nee dot be heard, for instance. Researchers said they don’t see AI replacing judges or lawyers, but they’d find it useful for rapidly identifying patterns in cases that lead to certain outcomes. It could also be a valuable tool for highlighting which cases are most likely to be violations of the European Convention on Human Rights. The researchers found that during the creation of the programme the judges of European Court of Human Rights tended to look more at non-legal factors than the strictly legal arguments made in the case. In law, that puts the judges in the camp of “realists” rather than “formalists” and fits with other courts like the US Supreme Court. The developers were able to use information like that to find that the court’s decisions relied largely on the kind of language used as well as what topics were mentioned in the court texts. Previous studies have predicted outcomes based on the nature of the crime, or the policy position of each judge. This is the first time judgments have been predicted using analysis of text prepared by the court.