Sentiment Analysis System for Roman Urdu

Most of the work conducted on Sentiment Analysis has been for major languages such as English, German and Chinese. Very little work is done on Roman Urdu (Urdu words in English script: "Aap kaise ho?"), Roman Urdu is a resource-poor language. The development of a Roman Urdu Sentiment Analy

Project Title

Project Area of Specialization

Artificial Intelligence

Project Summary

Most of the work conducted on Sentiment Analysis has been for major languages such as English, German and Chinese. Very little work is done on Roman Urdu (Urdu words in English script: "Aap kaise ho?"), Roman Urdu is a resource-poor language. The development of a Roman Urdu Sentiment Analyzer is necessary for two major reasons:

•Urdu is the third most-spoken language globally, with more than 830 million native speakers.

•It is increasingly being used because people prefer to communicate on the web using the Latin script i.e., RU uses the 26-letter English alphabet (instead of typing in their language using a language-specific keyboard). Its diversity and enormity of its user base motivate work on Sentiment Analysis.

Project Objectives

The objectives of this project are:

1. To develop the largest ever Roman Urdu dictionary.

2. To give mean sentiment score to RU dictionary.

3. To develop a model that will analyze the Roman Urdu data.

4. Develop Flask-based web GUI framework for the system.

Project Implementation Method

1. A lexical Dictionary for Roman Urdu (RU) is under development so that it may assist in getting the sentiment for a sentence (work still in progress to enrich the resource).

2. A system has been built that can accept the user input in Roman Urdu and return the sentiment of the given sentence.

3. Concurrently, a prototype Flask framework-based web app is developed (more work on it is in progress).

Benefits of the Project

The main benefit of this project is that it will help different companies, especially clothing companies and the government to know about the sentiment of the people. As we know we have developed sentiment analysis systems for the English language but we don't have any robust Roman Urdu Sentiment Analysis system.

Technical Details of Final Deliverable

The Final Deliverable is a web application using Flask which will be deployed on the Heroku server. The application will capable of finding the sentiment of sentences as well as a large number of data as well. the application is developed using python and the interface is developed using flask