At last, I used transfer learning technique with using Pre-trained BERT model which gave me 95% for small sample data and 97% for large-scale data. Then, I tried CNN and RNN with different layer numbers and layer types on Keras. As neural net models, I built Torch model with Fast Text Class. Between them, I found best result 87% accuracy. Firstly, I tried statistical models as LogReg, DecisionTree, ExtraTree, RandomForest, XGBoost, LGBM Classifiers. I tried different models for sentiment analysis. My second solution is to build a recommendation system to meet customers' expectations with recommend them good books and sell more products. I build a model which can predict the review is positive or negative from text and saving our time. It takes too much time and generally does not give brief idea about product comparison. It is hard to read thousands of reviews regularly and understand which product is liked or hated by customers. Firstly, I did sentiment analysis to classify reviews as positive or negative. I found this online business problem interesting so, I tried to solve it. I worked on book reviews but the important point of this project for me is that it can be applied for different companies and different areas. So, there are many people who prefer to buy online books and give feedback about them online. In this project, I choose Kindle store reviews because it is easy to buy and read books with Kindle and Kindle app is available for every device. If the company fails to meet this expectation, it can lose money. Customers could not touch online products so they want to learn from previous customer's experiences. With the increasing demand in e-commerce, voice of customer concerns getting more important such as reviews or surveys. As a capstone project of Flatiron School, I worked on Kindle Store reviews on Amazon.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |