Analysing unstructured data using gensim
by Gautam Jeyaraman (speaking)
Objective
Learn the basics of text analysis using gensim. This includes building semantic models like lda, lsi and what to do with this extracted data.
Description
Text analytics is a growing field in computer science and extracting insights from unstructured data has always been a hard hill to climb. In this session, we will see some of the basic methods with which we can extract basic semantics like topic models and word vectors from our own data using gensim. Also, we will see what to do with this extracted data and how to go forward from this.
Speaker bio
I am Gautam Jeyaraman and I work in a startup. We specialize in text analysis and extracting insights from huge corpora containing unstructured data. Basically, I have worked in getting meaningful data out of large text dumps all the time. Processing text data has always been a big task and people don't have a clue on what vectorizing their document means and where to proceed after they vectorize their documents. I can easily make both these points understandable and make sense on unstructured text analytics.