Georgia Tech: Open Source Machine Learning Tool Could Help Choose Cancer Drugs. “The selection of a first-line chemotherapy drug to treat many types of cancer is often a clear-cut decision governed by standard-of-care protocols, but what drug should be used next if the first one fails? That’s where Georgia Institute of Technology researchers believe their new open source decision support tool could come in. Using machine learning to analyze RNA expression tied to information about patient outcomes with specific drugs, the open source tool could help clinicians chose the chemotherapy drug most likely to attack the disease in individual patients.”
Georgia Tech: New Visualization Tool Helps Non-Experts Understand Neural Networks. “‘Visual analytics helps people make sense of complex systems that use large data and discover insights by effectively visualizing them and let people interact with them,’ said Minsuk (Brian) Kahng, a Ph.D. student in the School of Computational Science and Engineering (CSE). Kahng has recently been working alongside Associate Professor Polo Chau to build visualization tools for deep learning models, with an emphasis on public accessibility. Two examples of his work are ActiVis, a visualization system for industry-scale deep neural network models that is deployed at Facebook, and the newly released GAN Lab, which is now available to the public online.”
Georgia Tech: IC Researchers Highlight Design Implications as Venezuelans Turn to Facebook for Barter, Exchange. “Consider a scenario in which economic turmoil and hyperinflation have made it nearly impossible to purchase many of life’s basic necessities. There are food and medicine shortages, and scammers purchase what is available in bulk in an effort to manage the flow and pricing of supplies at the expense of other citizens. How, then, might honest citizens go about navigating the challenging circumstances to procure the items they need to survive? It’s a familiar environment to Venezuelan citizens who, since an economic crisis gripped the country in 2014, have faced such barriers in their daily lives. Out of necessity, many have turned to online solidarity economies like Facebook groups that are dedicated to a fairer system of barter and exchange.” I had never heard the term “solidarity economy” before. Haverford College enlightened me.
Inside Higher Ed: Big Brother: College Edition. “When Matthew Wolfsen, a student activist at Georgia Tech, asked the university for all its records on him, he got back two binders of documents. Some of it was expected — his high school transcript, for instance. He also found that administrators kept tabs on his political affiliation and a trip he took to Washington in July. ‘Continuing to monitor this student’s social media accounts,’ Steven Norris, a social media manager for Georgia Tech, said in one email reviewed by Inside Higher Ed. The email contained details about a Facebook group Wolfsen had joined and a screenshot from his Facebook account about a meeting of the University System of Georgia’s Board of Regents Wolfsen planned to attend. The materials were sent to several leaders of the institution’s communications team.”
Georgia Tech: One in Five Materials Chemistry Papers May be Wrong, Study Suggests. “Can companies rely on the results of one or two scientific studies to design a new industrial process or launch a new product? In at least one area of materials chemistry, the answer may be yes — but only 80 percent of the time.”
Georgia Tech: New Georgia Tech Research May Help Combat Abusive Online Comments. “Researchers at the Georgia Institute of Technology’s School of Interactive Computing have come up with a novel computational approach that could provide a more cost- and resource-effective way for internet communities to moderate abusive content. They call it the Bag of Communities (BoC), a technique that leverages large-scale, preexisting data from other internet communities to train an algorithm to identify abusive behavior within a separate target community.”
WebWire: Social Media Could Take Only a Fraction of Users’ Time With New Georgia Tech Method. “Implemented in a web browser, the visualization tool, called SentenTree (short for Sentence Tree), has been used to take almost a quarter of a million tweets shared in a 15-minute window of time during the 2014 World Cup and filter the conversation. The resulting single 100-word social post revealed that Brazil scored a goal in its own net, putting them down 0-1 in their match against Croatia. In the example post, ‘World Cup’ and ‘own goal’ are larger than other words, signaling that they appear more frequently. In the middle of and connecting these two phrases are ‘2014,’ ‘bad,’ and ‘Brazil,’ which together give an idea of the larger social conversation. If users want more context, SentenTree allows them to hover over any word and drill down to see more details, including the number of times the phrases appear along with the original tweets.”