One of the challenges of the beta testing process is collecting feedback from users and their service. Applications that are convenient to use have a good chance of popularity in the market, and those that are emergency have a destructive impact on the company's reputation. For this reason, the process has a key role in the aspect of project management. The inflow of a large amount of opinions is associated with, for example, dedicating by a support assistant a large amount of time reading opinions, categorizing them and creating a priority list of potential tasks for programmers to provide a better product to users as soon as possible. This is a task in which a human could replace a machine.
The main goal of this project is to provide an algorithm, which reads data, trains an AI model, tests it and predicts sentiment of input text. PyTorch is an open source machine learning framework and it is used to prepare and build the neural network.
Based on: Deep Learning Nanodegree Program | Udacity
Code sources:
- Udacity SageMaker deployment project
- Udacity Recurrent Neural Networks | Sentiment Analysis RNN
- Amazon Review Data (2018) | Code
- Python 3.6.7
- PyTorch 0.4.1
- Cuda 92 Toolkit from Nvidia
... and more.
Feel free to create conda environment from requirements.txt file.