Back
Artificial Intelligence

Sentiment Analysis

Copy link

Sentiment analysis (or opinion mining) is a natural language processing (NLP) technique used to determine whether data is positive, negative or neutral. Sentiment analysis is often performed on textual data to help businesses monitor brand and product sentiment in customer feedback, and understand customer needs.

Stacks:

Linux/Windows

Python

NLP

Neural Networks

Dataset: The dataset consists of a large number of targeted domain sentences with their labels to train the model.

Hardware (Resources) (Storage & Compute Power & Time)

For training, we need 64 GB ram with the latest processors and GPU.

For just inference, we can run it on any minimum requirements with GPU.

Workflow (Processing)

1. Collect the data set from the targeted domain and then labelled it.

2. Train the model.

3. Test the model and its accuracy.

4. Integrate with the API or any targeted application.

End To End (Development & Integration in a System)

Following steps are included in the deployment of a Sentiment Engine:

API Development

Environment Setup

Engine Installation and Configuration

Model Deployment

Server and Route Setup

Testing

Deployment (Server / API)

Linux/Windows with Python Flask API.

Output (Screenshots) Applications (General Real World Use)

1. Social media monitoring

2. Customer support ticket analysis

3. Brand monitoring and reputation management

4. Listen to voice of the customer (VoC)

5. Listen to voice of the employee

6. Product analysis

7. Market research and competitive research

Use Case (Our Specific)

We use it to analyze the sentences spoken in any video after getting its transcription.

Task

Artificial Intelligence

  • Strategy

    Neural Network, Sentiment Analysis, Deep Learning

Leave a Reply

Your email address will not be published. Required fields are marked *