SwarBhaav - Transforming Calls into Actionable Feedback

Table of Contents

• Introduction
• Features
• Demo
• Tech Stack
• Installation
• Usage

Introduction

The Sentiment Analysis of Incoming Calls on Helpdesk project is a comprehensive solution tailored for analyzing the sentiment of incoming calls in helpdesks, call centers, and customer services. With the ever-increasing volume of customer interactions in these domains, understanding customer sentiments expressed during phone conversations is crucial for improving customer service delivery.

Features

• Dual Dashboards: The project offers separate dashboards for rookies and managers, each with distinct access controls.

• Chat Analysis: Analyze chat conversations to provide summaries, sentiment scores, and key positive and negative words. Users can specify date ranges for analysis.

• Swar or Audio Sentiment Analysis: Utilize the Librosa model to classify Swar recordings into one of seven different emotions, enhancing the depth of sentiment analysis.

• Reporting: Generate comprehensive reports and store the results in a MongoDB database for users to review whenever necessary, facilitating data-driven decision-making.

Demo

For a live demo of the project, visit Demo Link.

Tech Stack

• Frontend:

  • Next.js: React framework for building user interfaces.
  • Tailwind CSS: Utility-first CSS framework.

• Backend:

  • Node.js: JavaScript runtime for server-side development.
  • FastAPI: Modern, fast (high-performance) web framework for building APIs.

• Sentiment Analysis:

  • Librosa: Python library for audio and music analysis.
  • Transformers: State-of-the-art natural language processing models.

• Data Sources:

  • Swar Dataset
  • WhatsApp Chats

Installation

1. Clone the repository:

   git clone https://github.com/Archit1706/SwarBhaav.git

2. Install dependencies for both the frontend and backend:

   # Navigate to the frontend directory
   cd frontend
   npm install
   
   # Navigate to the backend directory
   cd ../backend
   pip install -r requirements.txt

3. Configuration:

   • Set up environment variables and configuration files as needed for your development and production environments.

4. Start the development server:

   # In the frontend directory
   npm run dev
   
   # In the backend directory
   uvicorn main:app --reload

Usage

• Access the application by visiting the appropriate URL in your browser.
• Log in with your credentials to access the dashboard.
• Explore the chat analysis, Swar sentiment analysis, and reporting features based on your user role.