Niki Pavlopoulou: Abstract

Big Data has gained a considerable amount of attention lately. Many researchers and companies have put too much effort into building a number of distributed databases, search engines and frameworks to handle the memory and time constraints this data have. What is more interesting though is how to gain insight from this unstructured data (e.g. text) in an efficient way in order to present them in a structured manner, create more personalised customer products, find novel unusual patterns or findings and take actions on them. This talk focuses on the categorisation and analysis of unstructured data with the use of Natural Language Processing and Machine Learning algorithms on Apache Spark. According to our findings, Apache Spark and its Machine Learning library considerably boosts the memory and time-consuming hurdles of other frameworks and acts as an excellent analytics platform basis, where one can build one's own applications upon for the purposes of a complete and comprehensive analysis pipeline.

Organised by BCS SGAI The Specialist Group on Artificial Intelligence http://www.bcs-sgai.org