Aspect Based Sentiment Analysis of News Articles

Project Title

Aspect Based Sentiment Analysis of News Articles

Project Area of Specialization Artificial IntelligenceProject Summary

Our model will first extract news articles from certain websites secondly it will extract all the aspects and sentiments assigned to each aspect on a sentence level. Therefore given a website as input or dataset it will give aspects and sentiments assigned to them as output with percentage of accuracy. 

Project Objectives

To perform aspect based sentiment analysis on news websites articles.

Project Implementation Method

We will be using ANN and BERT model for training of our model. We are using python IDE and tensorflow. For user interface we will develop a website that will represent the aspects and sentiments assigned.

Benefits of the Project

It can be used for many purposes like;
1. Business (Market Analysis)
2. National Security (constantly observing sentiments of countries).
3.  How people are feeling about new policies by government.
4. In hotels, resturants and offices to observe the sentiments of public. 

Technical Details of Final Deliverable

We will be using our backend sentiment analysis model for analysis of dataset and a user interface in form of a website that will show all the aspects and sentiments and how accurate our data is on it.

Final Deliverable of the Project Software SystemCore Industry SecurityOther IndustriesCore Technology Artificial Intelligence(AI)Other Technologies Big DataSustainable Development Goals Industry, Innovation and Infrastructure, Peace and Justice Strong InstitutionsRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	60000
GPU	Equipment	1	60000	60000