Language is hardwired to be optimistic, even if people aren’t

Between political disagreements, economic instability, and climate troubles, you might assume every newspaper is full of bad news. Weirdly enough, the exact opposite is true. No matter what's going on in the real world, English is a perversely positive language.

That's the rather counter-intuitive finding of mathematicians at the University of Vermont, who just last month used Twitter data to argue that global happiness had decreased over the last two years. And yet, whatever these short-term trends, English seems to remain "strongly biased toward being positive", as team member Peter Dodds puts it.

Of course, that might seem like such a huge statement that it's impossible. To reach that conclusion, they examined billions of words used in such diverse sources as the last twenty years of The New York Times, 50 years worth of music lyrics, Twitter, and the Google Books Project, which includes millions texts dating as far back as 1520. They then looked at the top 5,000 words for each of these, and then enlisted volunteers to rate on a scale of 1 to 9 the happiness of the 10,222 most common words taken from these four sources.

MORE HERE >>

Stanford University: Natural Language Processing course

The following online course on Natural Language Processing from Stanford University (sorry for advertising a non-DIT course!) may be useful for some dissertations:

http://www.nlp-class.org/

There is a range of other courses listed at the bottom that sound really interesting if you have time such as Probabilistic Graphic Models, Machine Learning and Information Theory.

Course Description

The course covers a broad range of topics in natural language processing, including word and sentence tokenization, text classification and sentiment analysis, spelling correction, information extraction, parsing, meaning extraction, and question answering, We will also introduce the underlying theory from probability, statistics, and machine learning that are crucial for the field, and cover fundamental algorithms like n-gram language modeling, naive bayes and maxent classifiers, sequence models like Hidden Markov Models, probabilistic dependency and constituent parsing, and vector-space models of meaning.