Natural language processing and machine learning can be applied to student feedback to help university administrators and teachers address problematic areas in teaching and learning. The proposed system analyzes student comments from both course surveys and online sources to identify sentiment polarity, the emotions expressed, and satisfaction versus dissatisfaction. A comparison with direct-assessment results demonstrates the system's reliability.

Online health communities are a valuable source of information for patients and physicians. However, such user-generated resources are often plagued by inaccuracies and misinformation. In this work we propose a method for automatically establishing the credibility of user-generated medical statements and the trustworthiness of their authors by exploiting linguistic cues and distant supervision from expert sources. To this end we introduce a probabilistic graphical model that jointly learns user trustworthiness, statement credibility, and language objectivity. We apply this methodology to the task of extracting rare or unknown side-effects of medical drugs --- this being one of the problems where large scale non-expert data has the potential to complement expert medical knowledge. We show that our method can reliably extract side-effects and filter out false statements, while identifying trustworthy users that are likely to contribute valuable medical information.

As that "mention" gets pulled into the system, an AI called Natural Language Processing reads the post text and determines its "Sentiment." Sentiment is used to determine if the post is positive, neutral, or negative, (and in some advanced cases, the emotion like "anger" "sadness" or "joy"). Doing this manually for every post that comes in isn't feasible (we see tens of thousands of posts on any given week). AI does this automatically for us, and it can "learn" to improve its NLP Sentiment analysis as more posts pass through it, and as manual adjustments for errors are made. And speaking of Christian's post, he used the "#nofilter" hashtag which can be assigned a "proud" tag since its basically saying "my picture was so good, I didn't need to edit it."

Text Analytics Poll Shows Le Pen Positioned to "Trump" Macron To Americans following the French Presidential Election taking place in less than a week, it might appear as though recent history is repeating itself. And in many ways, it is. The post Text Analytics Reveals Potential French Election Upset appeared first on OdinText.

Use our LinkedIn Login to download this post to PDF or save it to MyLibrary! Everyone has been hearing about AI, some have been hearing about NLP - and everyone has an opinion, belief, or thought about AI. However, that opinion, belief, or thought about AI (and/or NLP) is fully dependent upon the voices of whom everyone has chosen to listen. We are at a stage in our rate of change of technology where we have to let go of how we learned things in the past -- and step into a new stage of keeping ourselves always available to learn, no matter what we believe and/or think. We cannot, more than ever before, solve our problems with the same thinking we used to create them (said Albert Einstein nearly 100 years ago!).

Less than six months ago, Mark Zuckerberg dismissed the idea that the social publishing platform he founded was being used to manipulate voters as "pretty crazy." But in a new report, Facebook now says it has data that "does not contradict" a key U.S. intelligence report that describes "information warfare" ordered by Russian President Vladimir Putin and carried out on Facebook and across the web. "Russia's goals were to undermine public faith in the U.S. democratic process, denigrate Secretary Clinton, and harm her electability and potential presidency," officials wrote in a declassified version of the U.S. Director of National Intelligence report in January. Guided by the Russian government's "clear preference" for Donald Trump, the DNI report said, Moscow followed a strategy "that blends covert intelligence operations--such as cyber activity--with overt efforts by Russian Government agencies, state-funded media, third-party intermediaries, and paid social media users or'trolls.'" Scholars have long theorized about the possibility of people manipulating public opinion on Facebook--Facebook itself carried out a mood experiment on its users--but U.S. intelligence officials call Moscow's latest meddling "unprecedented."

On average approximately 40 to 50 percent of tasks in a call center are good candidates for automation. These are tasks that a call center agent or manager can trigger – updating your address, for example. The dialog between the AI and the customer is controlled by how the AI application is programmed and closely measured with human oversight. AI does not run without tight controls in place. The analytics include sentiment analysis that tells management which AI-conducted customer interactions were positive or negative.

Facebook must obtain the permission of German users of WhatsApp before processing their personal data, a German court confirmed on Tuesday. Last August, Facebook subsidiary WhatsApp changed its privacy policy to allow the transfer of its users' personal information to Facebook for processing. That angered the Hamburg Commissioner for Data Protection and Freedom of Information, which in September ordered the companies to stop the transfer until they had obtained users' consent, and to delete any data they had already transferred. Facebook challenged the order in Hamburg's administrative court, and on Tuesday the court handed down its ruling. The court upheld the Commissioner's requirement to obtain consent, but threw out the order to delete the data on procedural grounds.

Charts are an excellent way to convey patterns and trends in data, but they do not facilitate further modeling of the data or close inspection of individual data points. We present a fully automated system for extracting the numerical values of data points from images of scatter plots. We use deep learning techniques to identify the key components of the chart, and optical character recognition together with robust regression to map from pixels to the coordinate system of the chart. We focus on scatter plots with linear scales, which already have several interesting challenges. Previous work has done fully automatic extraction for other types of charts, but to our knowledge this is the first approach that is fully automatic for scatter plots. Our method performs well, achieving successful data extraction on 89% of the plots in our test set.