Customer Profile

World Vision is an international Christian humanitarian organisation dedicated to working with children and families to overcome extreme poverty and injustice. They work to promote human transformation, seek justice for the oppressed and demonstrate the love of God for all peoples. World Vision serves all people regardless of religion, race, ethnicity or gender. Today, World Vision is helping more than 100 million people through its various development, humanitarian and emergency relief programs. With more than 45,000 staff in 100 countries, it is one of the largest relief organisations in the world.

The Challenge

Being the largest relief organisations in the world, World Vision wanted to develop a system that can perform sentiment analysis based on the data/tweets collected from various social media channels.

With the help of automated real-time data collection and tools that enforce data integrity and uniformity, World Vision was looking to monitor the microblogs where people post real-time messages about their opinions on a variety of topics, discuss current issues, complain, and express positive sentiment for products they use in daily life. Using sentiment analytics, the World Vision staff could analyse the practices and tactics that were producing the best results and where they need to adopt better-performing programs.

The Solution

BlazeClan conducted an exhaustive study to understand the requirements mentioned by the World Vision team, to develop a sentiment analysis engine driven by tunable NLP that takes tweets/posts as its data source. The end user tweets were identified and classified into different categories as Positive, Negative and Neutral. The blazeclan team then assisted in creating the visualisation using appropriate tools to deduce the analysis of these posts and hosted this engine on Amazon Web Services as infrastructure.

The solution included –

Core Functionalities:

  • Tunable Sentiment Analysis Engine will be developed
  • Natural Langue Recognition Engine
  • The measures/inputs of the sentiment analysis
  • Influencers Identification
  • Python Anaconda Distribution 3.X shall be utilised in the proposed engagement

Machine Learning Algorithm:

  • Supervised Learning Algorithm
  • Sentiment Categorizations:
  • Positive
  • Negative
  • Neutral

Visualisations created utilizing third-party tools:

  • Quick Sight
  • Google Visualization
  • Python Native
  • Bokeh
  • Provisioning AWS infrastructure services
  • EC2
  • Kinesis
  • Lambda
  • BOTO Library
  • S3
  • RDS – SQL Lite

Once the workflow was understood, BlazeClan adhered to the Big Data Solution approach that is

designed to help the company define a:

  • Big Data Analytics Process,
  • Adopt Right Tools,
  • Build a Cloud-Based Analytics engine and
  • Empower businesses with actionable and operational business analytics.

This 5 step solution approach included:

1. Data Discovery: Data structure, data sources, data volume were identified.

2. Analytics Discovery: The architecture was designed by understanding data correlation, frequency and algorithm.

3. Tool and Technology Discovery: The tools and technologies required for the implementation.

4. Infrastructure Discovery: Helped in identifying the right resources for the architecture in a cost-optimized way.

5. Implementation Phase: A continuous delivery approach was taken during the implementation Phase, with a lean structure of continuous learning based iterations. This approach assured low upfront investments and adoptive actionable analytics.

The Benefits

1. Sentiment Analysis: Business stakeholders were able to achieve very high accuracy in identifying a sentimental trend from the programs executed by them

2. Real-Time Visualization: This helped the company in real time insights by trend, topic and handle

3. Scalability: They achieved the ability to scale the application as and when required by leveraging auto-scaling and load balancing features of AWS.

Tech Stack

BlazeClan availed a number of AWS services to execute this project successfully.

  • Amazon EC2 was used for computing capacity management for their application deployment. It helped in reducing the time required to spin up new server instances to minutes, allowing them to quickly scale capacity, both up and down, as per their requirement.
  • Amazon RDS service was used to set up, operate and scale relational database and was mainly used for Postgres deployments.
  • Amazon S3 was used to store and retrieve any amount of data from anywhere and everywhere.
  • Amazon DynamoDB was used for all applications that required consistent, single-digit millisecond latency at any scale.

Prank sombody with the fake Windows 10 upgrade screen which never ends. Open the site in a web browser and go full screen with the F11 key.

Service Tags: