Sentiment Analysis for Marketing Campaigns
This project improved the efficiency of marketing campaigns by automatically evaluating user feedback that comes through different channels and automating decisions on further user engagement.
The system evaluates whether the user is interested in the proposal now or might be interested in the future, whether the user is requesting additional information and whether the user wants to move forward.
Technologies
- Deep Recurrent Neural Networks
- Word Embeddings
- Entity Recognition
- StarSpace
- PyTorch
- Numpy
- Docker
- AWS
- Sequence to Sequence Architecture
- Reinforcement Learning
- Word Lemmatization and Tokenization
- Python
- Flask
- Continuous Learning
- Kubernetes
- Jenkins