I aim to cover the following aspects under the talk: 1. Using nltk with python (Overview of modules and data) 2. Basics of natural language processing (tokenisation, stemming, wordnet, pos tagging) 3. Sentiment Analysis (overview of classification methods, binary versus fuzzy classification) 4. Directions of sentiment analysis 5. Applications in discerning human emotions.
The workshop would aim to provide a general overview of the concepts that are used in conducting a Sentiment Analysis on textual data.
The beginning 5 minutes of the talk would deal with how nltk is used in python, what corpus it provides, the stemmers inbuilt, sentence tokenisation and pickled models. I would then move to using this nltk toolkit for sentence tokenisation and pos tagging and how NER (Named-Entity Recognition can be useful for Aspect based sentiment analysis) which would take around 10 minutes.
I would then proceed to discuss about the classification methods like bag-of-words, random forests etc. and where and when they should be used. In here, I would also explain the bias induced in dataset regarding the industry it is dealing with. I would also touch briefly on binary classification (positive, negative) or probability value vector in case of multi-label classification. This would take 10 minutes.
I would then discuss about the various directions in which sentiment analysis is used, namely, stance detection, aspect based sentiment analysis etc. I would go over the various ares that sentiment analysis can be used (product reviews, social media posts) and how that information about sentiment can be used. And then I would conclude by discussing about the projects that I have worked upon, that is, giving AI the benefit of recognising and empathising with emotions and how it would be helpful.
We are looking for sponsors!
If you can help make PyCon SG a success, please message us at email@example.com