Knowing what people are talking about and understanding their concerns is very valuable to Businesses. Gathering such information is the objective of this Project. To be precise it is doing more of what is working and less of what is not working. Reteriving the topics people are talking about and analyzing the sentiment can be defined as goals for this project. It is really hard to achieve these goals if we have to manually read through large volumes of data. We need automated algorithms to achieve these goals for us. We will be exploring supervised and unsupervied machine learning techniques in this project. We will do Sentiment analysis on the dataset and categorize the documents as positive or negative and also understand the topics for the dataset. We can build a recommendation with sentiment model and topic model.
Dataset: Amazon reviews of shoes,clothing and jewellery. source:http://jmcauley.ucsd.edu/data/amazon/
sentiment_model.ipynb topic_mode.ipynb