On the 18th of May, the Virtusa Auditorium saw a bunch of techies gathered for the evening. This was none other than for the Colombo Big Data Meetup. In its latest edition, the meetup was all about Real Time Analytics – Stream Processing & Text Analysis with Machine Learning. Here’s what you need to know.
The first session for the evening was by Mahesh Madushanka, Associate Technical Lead at CAKE LABS. His focus was mainly on real time analytics and stream processing. He started off by briefing the audience on what real time analytics is. According to Madushanka, with analytics its all about discovery, interpretation and communication of meaningful patterns in data. He further went on to explain what stream processing is and the differences between batch processing versus real time processing.
Next, Madushanka moved on to stream processing technologies. He talked specifically on Apache Storm. For those of you not in the know, Apache Storm is a free and open source distributed real time computation system. Its simple and can pretty much be used with any programming language. Madushanka also touched on how Apache Storm can be used as an ETL (Extract, Transform, Load) tool. Towards the latter part of the session, the audience was briefed on CAKE ETL Framework, along with the limitations and challanges of implementing such stream processing techniques.
As Madushanka concluded his session , we then moved on to Haritha Thilakarathne from Tech One Global. Haritha started off by saying how text is boring and that tech people are good with numbers. Then again, whatever you do, text something you would have to deal with often. Haritha talked about analytics, how conventional business intelligence tools are all about numbers. But what happens when numbers are no longer enough? This is where text analytics comes into the picture. He went on to talk about the different text mining applications in the form of business, academic, social media, software, security and chatbots.
The final session then proceeded to focus on the more technical side of text analytics. This is where the discussion focused on the major tasks of text analytics and concepts such as Bag of Words, Sentiment Analysis, etc. In case you’re confused, Bag of Words refer to a representation model that is used to simplify content, while Sentiment Analysis is a machine learning classification.
Towards the final half of the second session, Haritha touched on chatbots and other specifics such as Microsoft’s LUIS (Language Understanding Intelligence Service). He concluded by showing an image of what appeared to be of an office secretary, only to discover that’s actually a robot that acts as a secretary. The ultimate implementation of text analytics.
So there you have it, the jist of what happened at the latest Colombo Big Data Meetup. We should expect the next Big Data meetup in a few months’ time. Until next time.
Have more to add to Colombo Big Data Meetup: Real Time Analytics And Machine Learning? Let us know in the comments below.
Subscribe to our mailing list and get interesting stuff and updates to your email inbox.
thank you for subscribing 🙂
awww something went wrong 🙁
We respect your privacy and take protecting it seriously