Hi everyone,

It was wonderful to see so many people at the Welcome Drinks last Wednesday! Sadly, we won't be seeing on you Tuesday – the *Google talk has been postponed* because our speaker had to drop out (we'll be announcing a new date shortly). If you want to get your tech talk fix, there is a *Bloomberg talk* tomorrow on analysing tweets using machine learning.

At this week's *Geek Night*, we'll be playing around with esoteric programming languages and, thanks to a generous donation from Sauyon Lee, we will also have a number of cheese available for tasting.

Have a great week!

*Edward and the rest of the committee* EventsGeek Night 2 https://www.facebook.com/events/346289525782943

*19:00 Saturday 2nd Week – Undergraduate Social Area*

This week we'll be exploring the weird and wonderful world of esoteric languages. Use languages like Brainfuck https://en.wikipedia.org/wiki/Brainfuck, Befunge https://en.wikipedia.org/wiki/Befunge or Piet https://en.wikipedia.org/wiki/Esoteric_programming_language#Piet—or something of your own devising—to implement fiendishly simple programs like FizzBuzz and the Sieve of Eratosthenes.

Bring your own laptop and we'll provide the pizza 😉. Other eventsBloomberg tech talk: Finding Signals in Tweets with ML/NLP at Bloomberg – Lunch Provided

*13:00 Tuesday 2nd Week – Lecture Theatre A, Department of Computer Science*

Talk Abstract:

In the current social media era, Twitter has proven itself an indispensable source of information as we frequently see information posted or shared on Twitter become big market movers later on. Due to the mass volume, directly consuming the raw contents without any kind of refinements is undesirable, and, more importantly, the vast majority of the contents are irrelevant to what interests our clients. In this talk, we will discuss how to refine raw contents from Twitter and extract fruitful signals, e.g. Trending Topics, Company Sentiments, Social Velocity, etc from them. Furthermore, we will discuss challenges during developments of the business deliverables and how we solve them via the use of ML/NLP techniques. Finally, we will go over some applications which are built on top of these signals and used broadly by professionals in the finance domain.

Iat Chong Chan – Profile:

Iat Chong Chan is a software developer in Bloomberg Machine Learning Team. His interests mostly lie in the intersection of Computational Linguistics, Machine Learning, and High Performance Computing. He has been working on a scalable infrastructure to infer topics of social contents ingested to Bloomberg by statistical models, and also a set of tools to maintain and improve these classifiers. Iat Chong also leads the NLP guild inside Bloomberg, to advocate the use of ML/NLP techniques for new business problems. Before he joined the company, he was a MSc student in Dept. of Computer Science at University of Oxford, supervised by Prof. Stephen Pulman and Yishu Miao, and worked on building a better input method on small hand-held devices by a novel Bayesian Network with Variational Inference. ------------------------------

The Oxford University Computer Society (CompSoc) aims to organise meetings and events for our members to use and further their computing interests. See all of our upcoming events on our Facebook Page https://facebook.com/oxcompsoc/ or visit our Website https://ox.compsoc.net for more information about the society.