AI News Hub an AI-driven news aggregator that curates real-

time, summarised news

AY24TECSA09

A Third Year Mini Project Report Submitted in partial fulfillment of the

requirements of the degree of

BACHELOR OF ENGINEERING
IN

COMPUTER ENGINEERING
BY

Anurag Arote (03)

Rohit Mahashetty(39)

Abhay Maurya (41)

Ravikant Mishra (42)

Supervisor
Mrs. Uma Goradiya(Assistant professor)

DEPARTMENT OF COMPUTER ENGINEERING

SHREE L.R. TIWARI COLLEGE OF ENGINEERING
SHREE L.R. TIWARI EDUCATIONAL CAMPUS, MIRA ROAD (East),

THANE -401 107, MAHARASHTRA.

University of Mumbai

(AY 2024-25)

1
 Declaration by the Candidate
I/We declare that this written submission represents my ideas in my own words and
where others' ideas or words have been included, I/We have adequately cited and
referenced the original sources. I/We also declare that I/We have adhered to all principles
of academic honesty and integrity and have not misrepresented or fabricated or falsified
any idea/data/fact/source in my submission. I/We understand that any violation of the
above will be cause for disciplinary action by the Institute and can also evoke penal
action from the sources which have thus not been properly cited or from whom proper
permission has not been taken when needed.

Date: _____ October, 2024

Anurag Arote
Roll No.: 03 Exam. Seat No.:

Rohit Mahashetty
Roll No.: 39 Exam. Seat No.:

Abhay Maurya

Roll No.: 41 Exam. Seat No.:

Ravikant Mishra
Roll No.: 42 Exam. Seat No.:

2
 DEPARTMENT OF COMPUTER ENGINEERING
CSM601 Mini Project – 2B

Sixth Semester, 2024-2025 (Even Semester)

CERTIFICATE
This is to certify that the Mini Project entitled “AI News
Hub an AI-driven news
aggregator that curates real-time, summarised news
” is a bonafide work of

Anurag Arote (03)

Rohit Mahashetty (39)

Abhay Maurya (41)

Ravikant Mishra (42)

submitted to the University of Mumbai in partial fulfilment of the requirement of course

name “ Mini Project – 2B” having course code CSM601 for the award of the degree
of “Bachelor of Engineering” in “Computer Engineering” .
Signature of Supervisor/Guide Signature of Project Coordinator
Name: Mrs. Uma Goradiya Name: Dr. Bhushankumar Nemade
Date: _______________ Date: _______________

Signature of the H.O.D. Signature of the Principal

Name: Dr. Bhushankumar Nemade Name: Dr. Deven Shah
Date: _____________ Date: _______________

3
 DEPARTMENT OF COMPUTER ENGINEERING
CSM601 Mini Project – 2B

Sixth Semester, 2024-2025 (Even Semester)

Major Project Report Approval

This Mini-project report entitled “ AI News

Hub an AI-driven news
aggregator that curates real-time, summarised news” by
Anurag Arote (03)

Rohit Mahashetty (39)

Abhay Maurya (41)

Ravikant Mishra (42)

is belonging to the course name “ Mini Project – 2B” having course code CSM601
submitted as a Term work and approved for the degree of Batchelor of Engineering in
Computer Engineering.
Examiners
1. Name: ________________________(Internal)

Signature: _____________________

2. Name: ________________________(External)

Signature: _____________________

Date:
Place:

4
 Acknowledgement

I would like to express my deepest gratitude to everyone who has contributed to the
successful completion of this project. First and foremost, I extend my heartfelt thanks to my
supervisor, Mrs. Uma Goradiya, for their unwavering guidance, valuable insights, and
consistent support throughout the development of this Designing and Implementing a
Scientific Career Counseling Software..I am also immensely grateful to SHREE. L. R.
TIWARI COLLEGE OF ENGINEERING, Mumbai University, for providing the necessary
resources and a conducive environment for this research. Special thanks to the faculty
members and my peers for their constructive feedback, which helped me refine my ideas and
improve the overall system.

Lastly, I am thankful to my Supervisors and friends for their encouragement and

understanding during the course of this project. Without their support, this work would not
have been possible.

Thank you all for making this journey a successful one.

Anurag Arote
Roll No.: 03 Exam. Seat No.:

Rohit Mahashetty
Roll No.: 39 Exam. Seat No.:

Abhay Maurya

Roll No.: 41 Exam. Seat No.:

Ravikant Mishra
Roll No.: 42 Exam. Seat No.:

5
 Abstract

In an era marked by information overload, disinformation, and the rapid dissemination of

content, staying informed with relevant and trustworthy news has become both a necessity
and a significant challenge. This project introduces an AI-driven news aggregator designed
to provide real-time, personalized news updates by intelligently curating content from a
diverse range of credible sources. The goal is to help users navigate the complex media
landscape by delivering news that is not only relevant and timely but also balanced and
trustworthy.

At the core of the system lies an integration of natural language processing (NLP),
machine learning, and user behavior analysis. These technologies work in tandem to
understand individual user preferences, reading habits, and engagement patterns. Using this
data, the platform tailors news feeds dynamically, ensuring that each user receives content
that aligns with their interests while also introducing diverse viewpoints and avoiding
ideological echo chambers.

The aggregator leverages AI algorithms to assess and rank news articles based on relevance,
credibility, recency, and user-defined parameters such as preferred topics, sources, and
language. News data is fetched through a combination of automated web scraping, RSS
feeds, and APIs from reputable global media outlets, independent journalists, and specialized
publications. To enhance objectivity, the system includes bias-detection modules and
promotes exposure to multiple perspectives on trending topics.

Real-time updates ensure users receive the latest developments as they happen, while
contextual filtering enables a clutter-free reading experience, eliminating redundant or low
quality content. The platform's user-friendly interface and cross-device accessibility make it
suitable for casual readers and professionals alike.

This project aims to elevate the quality of news consumption by fostering media literacy,
supporting informed decision-making, and promoting digital well-being. By delivering
curated, credible, and personalized content, the AI-driven aggregator serves as a powerful
tool in empowering users to stay engaged with the world in a meaningful and responsible
way.

6
 Table of Contents

Declaration by the Candidate…………………………………………………………………

ii

Major Project Report Approval………………………………………………………………. i

v

Acknowledgement……………………………………………………………………………
v

Abstract………………………………………………………………………………………
vi

Table of content……………………………………………………………………………..
vii

List of
Abbreviation…………………………………………………………………………viii

1.Introduction…………………………………………………………………………………ix

1.1 Problem statement……………………..……………………………………………… x

1.2 Project Objectives……………………………………………………………………...

xi

1.3 Project Importance………………………….………………………………………….

xi

1.4 Scope of Project Work………………………………………………………………...

xii

1.5 Organisation of the Report……………………………………………………………

xii

2. Literature Review…………………………………………………………………………
xiii

2.1 Literature Review of Existing System……………………………………………….

xiii

2.2 The Identified Features for Proposed System………………………………………..

xiv

3.Proposed System…………………………………………………………………………. xv

3.1 Layers Breakdown…………………………………………………………………… xv

3.2 Requirement analysis………………………………………………………………...

xvi
7
4. Proposed Plan for Implementation………………………………………………………
xviii

5. Expected Result and Discussion………………………………………………………… xxi

6. Conclusion and Future work…………………………………………………………… xxii

7. References……………………………………………………………………………….
xxiii

8. Annexure…………………………………………….…………………………………..
xxiv

8
 List of Abbreviations
HTML HyperText Markup Language

CSS Cascading Style Sheets

JS JavaScript

NODE.JS JavaScript runtime environment

EXPRESS Web application framework for Node.js

Postgres Open-source relational database management system

STEM Science Technology Engineering Mathematics

1-on-1 One-on-One (Mentorship sessions)

HTTP Hypertext Transfer Protocol

HTTPS Hypertext Transfer Protocol Secure

CRUD Create Read Update Delete (database operations)

UI User Interface

UX User Experience

API Application Programming Interface

9
 1. Introduction

In today’s fast-paced digital world, accessing timely, relevant, and trustworthy news is more
important than ever. With the overwhelming volume of information available online, users
often struggle to find content that aligns with their interests without being exposed to bias or
misinformation. This project introduces an AI-driven news aggregator that delivers
personalized, real-time updates from a wide range of credible sources. By leveraging artificial
intelligence and machine learning, the system curates content based on individual preferences
while ensuring diversity and balance in coverage. The goal is to streamline news consumption,
enhance user engagement, and promote informed, critical thinking in daily media interactions..

Background and Motivation

The exponential growth of digital news platforms and social media has transformed how
people access information. However, this abundance often leads to information overload,
confusion, and exposure to biased or unreliable content. Traditional news aggregation tools
offer limited personalization and frequently reinforce filter bubbles, restricting diverse
viewpoints. With the increasing demand for tailored, trustworthy news experiences, there is a
critical need for intelligent systems that can adapt to individual interests while maintaining
content quality and balance.

The motivation behind this project stems from the desire to create a smarter, more usercentric
way of engaging with news. By harnessing artificial intelligence, particularly natural
language processing and machine learning, we aim to build a system that not only filters news
in real time but also evolves with the user’s preferences. This ensures a well-rounded,
accurate, and efficient news experience—empowering users to stay informed, reduce
misinformation exposure, and develop a broader understanding of global events.

Additionally, the project seeks to address the growing concerns around digital well-being by
minimizing distractions and reducing the time spent sifting through irrelevant content. By
delivering concise, personalized updates, the aggregator promotes meaningful engagement
with current events, supports critical thinking, and fosters a more informed and responsible
digital society.

10
1.1 Problem Statement

In today’s digital landscape, individuals are overwhelmed by the sheer volume of news and
information across various platforms. The absence of intelligent, personalized filtering leads
to time-consuming news consumption and exposure to misinformation or bias. Users often
struggle to access real-time, relevant, and trustworthy news that aligns with their interests.
This project aims to develop an AI-driven news aggregator that uses artificial intelligence to
deliver personalized, real-time updates from diverse and credible sources. By analyzing
user preferences, reading habits, and trending topics, the system will provide targeted content
while ensuring a balanced perspective. The solution will integrate natural language
processing (NLP) and machine learning models to curate and rank news effectively. The
system will be guided by existing research on information personalization and user
engagement to build a smart and user-centric platform accessible across all devices.

1.2 Project Objectives

• Software Development: Design and implement a responsive, user-friendly platform
that aggregates news in real time.
• Data Integration: Source and integrate news feeds from a wide array of verified,
multilingual, and global sources using APIs and web scraping.
• Personalized Curation: Apply AI techniques to tailor news recommendations based
on individual user profiles and behaviors.
• Bias and Credibility Control: Include mechanisms to verify credibility and detect
bias in articles using content analysis and source reputation tracking.
• Cross-Platform Accessibility: Ensure seamless user experience across web and
mobile devices, with intuitive navigation and accessibility features.

1.3 Project Importance

The proposed AI-driven news aggregator addresses a critical issue in modern news
consumption: the lack of personalized, real-time access to diverse, credible information. As
misinformation and content overload become increasingly prevalent, there is a growing need
for smart tools that can help users stay informed without overwhelming them. This platform
empowers users by providing news that is not only relevant but also balanced and timely. It
helps minimize digital fatigue, encourages media literacy, and supports informed
decisionmaking. By offering tailored content and reducing exposure to echo chambers, the
system promotes healthier media consumption habits. The integration of AI for news
recommendation ensures that the platform adapts to user preferences over time, providing a
dynamic and continuously improving experience.

11
1.4 Scope of Project Work
• Target Audience: General users, journalists, researchers, students, and professionals
seeking personalized, real-time news.
• Content Focus: Initially focus on mainstream and niche news across politics, science,
business, technology, health, and entertainment, with potential expansion into hyper-local and
community news.
• Geographic Reach: Begin with English-language sources and expand globally to
include multilingual and regional content feeds.

1.5 Organisation of the Report

A. Introduction and Background
The AI-driven news aggregator is designed to provide personalized, real-time news updates
tailored to individual preferences. With increasing concern over information overload and
digital misinformation, this system offers a practical solution by combining AI-powered
content filtering with intelligent recommendation engines. The platform curates news from
diverse sources and helps users consume information more efficiently and critically.

B. System Architecture and Implementation

• Frontend: Developed using modern web technologies (HTML, CSS,
JavaScript/React), ensuring a responsive and interactive user interface across all devices.
• Backend: Powered by Node.js and Express, handling real-time data ingestion, user
profile management, and recommendation logic. A PostgreSQL database stores user data,
content metadata, and interaction logs.
• System Architecture: Built on a microservices-based architecture using the MVC
pattern, promoting scalability, modularity, and efficient maintenance. RESTful APIs enable
communication between services and external data providers.

C. Conclusion and Recommendation

This platform addresses the challenges of modern news consumption by offering a smart,
adaptive solution that enhances user experience and promotes balanced information access.
Future developments could include integrating advanced AI models for sentiment analysis,
fact-checking features, and region-specific recommendations. Expanding source diversity and
language support will also further broaden the platform’s reach and impact.

12
2 . Literature Review

2.1 Literature Review of Existing System

13
 2.2 Identified Features for the Proposed System
1. User Registration and Profile Management

Users can register and create personalized profiles containing preferences such as
news categories (e.g., politics, science, sports), preferred sources, language
preferences, and regions of interest. Profiles can be updated to reflect evolving
interests, enabling dynamic content recommendations over time.

2. Real-Time News Aggregation

The system continuously gathers news from diverse, credible sources using APIs and
web scraping. Content is updated in real-time to ensure users have access to the latest
information as it unfolds globally or locally.

3. AI-Powered Personalized Recommendations

Leveraging machine learning and natural language processing (NLP), the platform
analyzes users’ reading habits, interactions, and preferences to deliver tailored news
feeds. Content relevancy increases with continued use as the AI learns user behavior
patterns.

14
 4. News Categorization and Filtering

News articles are automatically categorized into themes such as Technology,

Business, Health, Environment, and more. Users can apply filters based on categories,
regions, sentiment, or source credibility for a customized reading experience.

5. Multi-Source Perspective & Bias Detection

Articles on the same topic from multiple sources are grouped together to encourage
balanced understanding. A bias-detection module highlights potential bias in articles
using sentiment analysis and source evaluation.

6. Interactive User Interface

The platform features a modern, user-centric design with an intuitive interface. Users
can swipe, bookmark, share, or react to articles. Advanced search functionality allows
deep exploration of topics and archives.

7. User Feedback and Engagement System

Users can rate articles, give feedback on recommendations, and report issues. This
feedback loop refines the recommendation engine and helps surface high-quality,
relevant content.

8. Mobile Responsiveness and Cross-Platform Access

Designed with a mobile-first approach, the platform ensures consistent, responsive

performance across devices (phones, tablets, desktops) using progressive web app
(PWA) techniques.

9. Support, FAQs, and Help Center

A dedicated support section provides answers to frequently asked questions, user

guides, troubleshooting help, and live support/chat options for real-time assistance.

These features aim to provide a seamless, informed, and engaging news reading experience
while combating misinformation and information overload through personalized, credible,
and diversified content delivery.

3. Proposed System
Introduction

The proposed system is an AI-driven news aggregator designed to deliver personalized,

real-time news updates to users based on their preferences, reading habits, and global trends.
The system architecture follows a multi-layered, modular approach to ensure scalability,
performance, and user-centric experience. By leveraging advanced AI technologies, the
platform not only automates content aggregation but also ensures that users receive accurate,
balanced, and meaningful news coverage.

15
The system supports interaction for different types of users—regular readers, journalists,
researchers, and administrators. Each user has a tailored interface and feature set to enhance
their specific experience and usage needs.

3.1 Layers Breakdown

1. Client Layer
User Roles:

• Reader: Primary user interested in receiving personalized news feeds.

• Editor/Journalist: May submit verified news for niche categories (future
integration).
• Admin: Oversees content sources, user moderation, system configurations, and
analytics.

Interaction:
All users interact through responsive web or mobile interfaces. Readers interact by selecting
preferences, reading content, saving articles, and managing notifications.

2. Presentation Layer
The frontend is built using React.js for a dynamic and responsive interface. It uses REST
APIs to communicate with the backend and displays personalized feeds, grouped news
articles, trending topics, and user settings.
Key Features:

• Responsive design (desktop, tablet, mobile)

• Light/dark mode
• Dynamic content cards for real-time article updates
• Bookmarking and history tracking

3. Business Logic Layer

Handles all data processing and AI-driven decisions. This layer includes:

• NewsAggregationService: Pulls news from various sources using APIs or scrapers,

removes duplicates, and stores metadata.
• RecommendationEngine: Uses collaborative and content-based filtering to curate
personalized feeds.
• BiasAnalyzer: Flags articles with extreme sentiment or bias using NLP.
• TrendAnalyzer: Detects trending topics by monitoring article frequency and
popularity across sources.
• AuthService: Manages login, session handling, password encryption, and tokenbased
authentication.
• NotificationService: Sends alerts for breaking news or updates in subscribed topics.

16
 • FeedbackHandler: Collects and analyzes user feedback to improve content
recommendations.

4. Data Layer
The data layer uses MongoDB for structured user and article data, and Elasticsearch for
fast full-text searching and trend analysis. Stores user profiles, reading history, source
credibility scores, and feedback.
• Manages CRUD operations for user actions, source management, and AI learning
logs.
• Stores article metadata (title, content, source, timestamp, category, sentiment score,
etc.).

3.2 Requirements Analysis

Functional Requirements
• User Authentication: Secure registration, login, and role-based access control.
• Real-Time Aggregation: Continuous data ingestion from selected sources with
redundancy filtering.
• AI-Based Personalization: Adaptive feed generation using user data and AI analysis.
• Content Categorization: Automatic classification of articles by topic and relevance.
• Bias Detection: Highlight articles that may be biased or sensationalized.
• Search and Filtering: Advanced search with filtering by date, sentiment, topic, and
source.
• Mobile Compatibility: Fully responsive interface optimized for small and large
screens.
• Notification System: Real-time notifications based on user-defined topics.

• Admin Dashboard: For managing sources, users, flagged articles, and analytics
reports.

System Architecture Diagram

17
 Non-Functional Requirements
• Scalability:
The system must be capable of supporting a growing number of users and large-scale
data ingestion from multiple news sources without performance degradation.
• Security:
User data, including reading preferences, login credentials, and engagement analytics,
must be encrypted and handled securely using HTTPS, secure storage practices, and
token-based authentication.
• Performance:
The platform should deliver fast content loading times and real-time updates.
Personalization algorithms and news retrieval should execute with minimal latency.
• Maintainability:
The system architecture should follow a modular design with loosely coupled
services. This allows for independent updates, feature enhancements, and bug fixes
without affecting other components.

4. Proposed Plan for Implementation

Phase 1: Requirements Gathering and Planning

• Identify core features based on user expectations and challenges in consuming digital
news.
• Define clear objectives for the aggregator such as personalization, source diversity,
bias detection, and trend analytics.
• Prepare a project roadmap with timelines and assign responsibilities to team members.

18
Phase 2: Design
Frontend Design

• Create wireframes for key pages: homepage (feed), category explorer, trending topics,
saved articles, user preferences.
• Design a clean and intuitive UI/UX that supports personalized dashboards and quick
topic switching.
• Implement responsive design principles using media queries, CSS Grid, and Flexbox
to ensure device compatibility.

Backend Design

• Plan a relational schema in MongoDB to manage user profiles, preferences, news

metadata, session history, and feedback.
• Design RESTful API endpoints for fetching news, updating preferences, user
login/logout, and feedback submission.
• Implement secure data handling: hashed passwords, role-based access control, and
SSL for all data exchanges.

Phase 3: Frontend Development

UI Development

• Build the interface using HTML5, CSS3, and JavaScript (React or Vue) to create a
dynamic and responsive single-page application.
• Develop components for article display, category filters, bookmarks, and trend
analytics widgets.

Responsive Design

• Utilize mobile-first design strategies with responsive breakpoints to ensure

functionality across devices.

User Experience Enhancements

• Use animations and transitions to enhance navigation and engagement.

• Add notification banners for trending news or breaking headlines.

Phase 4: Backend Development

API Development

• Build a Node.js + Express backend to manage business logic and route data between
the frontend and external news APIs.
• Core APIs will include:
o /register and /login for user auth o
/news to fetch personalized news o

19
 /preferences to update reading interests
o /feedback for user input collection

Database Management

• Use MongoDB to define and manage data models (users, articles, topics, sources, user
history).
• Implement indexing and caching mechanisms (e.g., Redis) for improved performance.

Third-Party Integrations

Integrate news APIs (e.g., NewsAPI, Google News, RSS feeds).

• Use email/SMS services (SendGrid, Twilio) to notify users about major headlines or
saved article reminders.

Phase 5: Integration
• Connect the frontend and backend through REST APIs to deliver seamless, real-time
content updates and personalization.
• Conduct API testing using Postman to verify request-response integrity and error
handling.
• Finalize third-party integrations for news data, alerts, and user communication.

Phase 6: Testing
Unit Testing

• Test individual frontend components (news cards, search filters) and backend
endpoints for stability and correctness.

Integration Testing

• Validate the full data flow from news retrieval to user feed personalization and
feedback loops.

Usability Testing

• Recruit real users to test the system’s intuitiveness, engagement features, and
responsiveness across devices.

Security Testing

• Implement testing for vulnerabilities like XSS, CSRF, and injection attacks. Introduce
input validation, sanitization, and throttling as needed.

20
Phase 7: Deployment
• Host the full-stack application on cloud services like AWS, Azure, or Google Cloud.
• Use CI/CD pipelines (GitHub Actions, GitLab CI) for automated deployment, testing,
and rollback capabilities.
• Deploy PostgreSQL on scalable cloud-hosted services (e.g., Amazon RDS, Railway)
to support real-time access and analytics.

Phase 8: Feedback and Refinement

• Collect user feedback via embedded surveys, feedback buttons, and engagement
analytics.
• Analyze feedback to refine the personalization algorithm, article relevance, and
interface usability.
• Continuously fix bugs and optimize performance based on logs and user reports.

5. Expected Result and Discussion

Expected Results
1. Personalized News Feed:
Users will receive real-time news tailored to their reading habits and preferences,
improving content relevance.
2. Balanced Perspectives:
The platform will highlight multiple viewpoints on the same topic to counteract bias
and encourage critical thinking.
3. Trend Awareness:
Users will stay up to date with trending stories and breaking news through live
updates and push notifications.
4. Enhanced Engagement:
A clean UI, interactive features, and responsive performance will lead to higher user
retention and longer session durations.
5. Content Credibility and Trust:
By curating articles from verified sources and flagging potential misinformation, the
platform promotes trust and reliability.
6. Community Development (Future):
The platform may expand into a news discussion community, where users can share
opinions, follow topics, and interact in forums.

Discussion
The AI-driven news aggregator provides a much-needed solution to modern content
consumption challenges. Its focus on real-time curation, personalization, and balanced
reporting makes it a powerful tool for information discovery. Unlike traditional platforms,
this system adapts to individual user behavior and preferences while maintaining content
diversity and source credibility. The inclusion of AI and NLP offers a smarter way to
navigate vast streams of news data efficiently and responsibly.

21
 6. Conclusion and Future Work

Conclusion
The news aggregator platform offers a comprehensive, intelligent solution for managing how
users access and engage with news. By combining AI-powered personalization, real-time
aggregation, and credibility analysis, the platform enables users to make more informed,
faster, and bias-aware decisions. A modular architecture ensures scalability and
maintainability, while responsive design guarantees accessibility on any device.

Future Work
1. Multilingual Expansion:
Add support for news in various languages and region-specific content to reach a
global audience.

2. Deeper AI Integration:
Implement advanced machine learning models for sentiment prediction, trend
forecasting, and personalized story ranking.
3. News Discussion & Community:
Introduce features like comments, voting, and group discussions to foster a sense of
community.
4. Voice Assistant Integration:
Enable voice-based news summaries and interactions using tools like Google
Assistant or Amazon Alexa.
5. Mobile App Launch:
Develop a native mobile app for Android and iOS to enhance offline access and
notifications.

7 . References

Ahmed, S., Maurya, S. P., & Khalane, V. (2018). Real-time News Aggregation and
Analysis Using AI Tools. International Journal of Computer Applications.

Yadav, S. K., Singh, S. J., Bora, A. M., & Thakur, S. N. (2016). News Tracking and
Recommendation System Using NLP. Journal of Emerging Trends in Computing and
Information Sciences.

Mohammed, K. F., Gawade, S., & Nimkar, V. (2017). Personalized News Aggregation
Using Adaptive Learning and Content Ranking. IEEE International Conference on
Information Processing.

Supriyanto, G., Widiaty, I., Abdullah, A. G., & Yustiana, Y. R. (2019). AI-Based Expert
System for Personalized News Distribution. Indonesian Journal of Information Systems.

Too, F. (2017). Mobile Application for AI-Powered News Filtering Based on Reader
Behavior. Faculty of Information Technology, Strathmore University, Nairobi, Kenya.

22
 Supriyanto, G., Widiaty, I., Abdullah, A. G., & Yustiana, Y. R. (2019). Recommender
Systems in Intelligent News Applications. Procedia Computer Science.

Udemy Web Development Course – Complete Web Developer Bootcamp.

https://www.udemy.com/share/1013gG3@amLdOUBSiwB0W

Athena Education – Source for student behavior analytics and career insights.
https://www.athenaeducation.co.in

SetMyCareer.com – AI integration and decision-support models.

https://www.setmycareer.com

YouTube Playlist – AI and News Aggregators

https://youtube.com/playlist?list=PLjiHFwhbHYlHSpAflJwjsKAyMaMhASm0F

1. YouTube Playlist – Building News Apps with React and Node.js

https://youtube.com/playlist?list=PLspW40rZgNemcESvd7g9mz8gldTKTLy-d YouTube
Playlist – NLP and Machine Learning for Real-Time Applications
https://youtube.com/playlist?list=PLdvOfoe7PXT0ouChAnR1nHlT8BJIo5hP_

8 . Annexure

Home Page:

23
24
25
26