VISVESVARAYA TECHNOLOGICAL UNIVERSITY

BELAGAVI – 590018

Exploration on Open AI Tools with

“AI News Summarizer”
Submitted in partial fulfillment of the requirements for the award of Degree of

BACHELOR OF ENGINEERING
IN
COMPUTER SCIENCE AND ENGINEERING

Subject: ARTIFICIAL INTELLIGENCE [BCS515B]

Submitted By:
PRASHANTH S G [4JK21CS045]

AKHIL A [4JK22CS005]

AMAL NAHAN N [4JK22CS007]

DEEKSHITH V [4JK22CS012]

Under the guidance of

Prof. USHA C S
Assistant Professor
Department of Computer Science & Engineering

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

A.J INSTITUTE OF ENGINEERING & TECHNOLOGY
NH-66,KOTTARA CHOWKI,MANGALURU–575006
2024-2025

1
 A J. INSTITUTE OF ENGINEERING AND TECHNOLOGY
(A UNIT OF LAXMI MEMORIAL EDUCATION TRUST®)
(Approved by AICTE, New Delhi, Affiliated by Visveswaraya Technological University, Belagavi)
Accredited By NBA (BE: CV, CSE, ECE, ISE & ME)

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CERTIFICATE
This is to certify that the Assignment Work in entitled “AI News Summarizer” is a
bonafide work carried out by PRASHANTH S G USN: 4JK21CS045, AKHIL A
USN: 4JK22CS005, AMAL NAHAN N USN: 4JK22CS007 and DEEKSHITH V
USN: 4JK22CS012 students of 5th semester Bachelor of Engineering in
Computer Science and Engineering of Visvesvaraya Technological University,
Belagavi, submitted as a part of the course in Assignment during the academic year
2024-2025. It is to certify that all corrections/suggestions indicated for internal
assessment have been incorporated in the report. The project report has been approved
as it satisfies the academic requirements in respect of Project work prescribed for the
said degree.

Prof.Usha C S Dr.Antony PJ
Assistant Professor Vice Principal and HOD

2
 ACKNOWLEDGEMENT
The joy and satisfaction that accompany the successful completion of any task would be
incomplete without the mention of the people who made it possible.

We would like to express our gratitude to our Principal, Dr. Shantharama Rai C for
providing us a congenial environment for engineering studies and also for guiding us to carry
out the project.

We consider it a privilege to express our sincere thanks to Dr.Antony PJ, Professor and
Head, Department of computer Science and Engineering for his support and valuable
guidance throughout the tenure of this project.

We would like to thank our Guide Prof Usha C S, Assistant Professor, Department of
Computer Science and Engineering for her support, guidance, motivation, encouragement
for the successful completion of this project.

We intend to thank all the teaching and non-teaching staff of our Department of Information
Science and Engineering for their immense help and co- operation.

Finally, we would like to express our gratitude to our parents and friends who always stood
by us.

PRASHANTH S G [4JK21CS045]

AKHIL A [4JK22CS005]

AMAL NAHAN N [4JK22CS007]

DEEKSHITH V [4JK22CS012]

3
 ABSTRACT
The AI News Summarizer is a web-based application designed to provide concise summaries of news
articles and perform sentiment analysis on the content. Built using the Flask framework, this
application leverages Natural Language Processing (NLP) techniques to extract key points from
lengthy news articles, making it easier for users to quickly grasp essential information.

The system incorporates sentiment analysis to determine the emotional tone of the article—positive,
negative, or neutral—enhancing users' understanding of the context and perspective of the news. By
automating the summarization process, this project demonstrates the potential of AI in streamlining
information consumption and decision-making.

The development of the project focuses on simplicity, usability, and accuracy. It employs APIs to
fetch real-time news articles and integrates advanced text processing libraries to ensure the
summarization and sentiment analysis are effective and reliable. The project aims to showcase the
practical application of AI in solving everyday challenges and serves as an educational experience in
understanding the integration of machine learning with web technologies.

4
 TABLE OF CONTENT

S.No TITLE PAGE

List of figures 6

1 Introduction 7

1.1 Objectives of the Project 8

1.2 Significance of the project 9

2 SoftwareRequirement 10
Specification

2.1 Hardware Requirements 11

2.2 Software Requirements 12

3 Design and Implementation 13

3.1 System Design 13

3.2 Sequence diagram 14

3.3 Class diagram 14

3.4 Modules with description 16

3.5 Model setup 19

4 Result and Conclusion 22

3.1.2 Snapshot with description 22

3.1.3 Conclusion 24

3.2 Future Enhancement 25

3.2.1 References 26

5
 LIST OF FIGURES

FIGURE No. DESCRIPTION PAGE

3.1.1 Flowchart of chatbot 13

3.1.2 Sequence diagram of chatBot 14

3.1.3 Class diagram of chatBot 15

3.2.1 Snapshot of index.html 17

3.2.2 Snapshot of index.html file 17

3.2.3 Snapshot of index.html file 18

3.2.4 Snapshot of model.py 19

3.2.5 Snapshot of model.py 20

3.2.6 Snapshot of model.py 21

4.1 Snapshotofuserinterface 22

4.2 Snapshotofuserinterface with 23

user input

4.3 Snapshot of Ai new 23

summarizer output

6
CHAPTER 1
INTRODUCTION
In the digital age, the volume of information accessible online has grown exponentially, making
it challenging for individuals to stay informed without investing significant time. News articles,
blogs, and online reports often contain extensive details, leaving readers overwhelmed when
they seek quick, relevant information. The AI News Summarizer is a solution designed to
simplify this process by leveraging advanced natural language processing (NLP) techniques to
generate concise, accurate summaries of news articles.

The primary objective of this project is to create a web-based application capable of

automatically extracting key information from lengthy news content. In addition to
summarization, the application includes sentiment analysis to provide users with insights into
the emotional tone of the news, such as whether it is positive, negative, or neutral. This dual
functionality makes the tool a valuable resource for readers who wish to quickly grasp the
essence of an article and understand its broader implications.

This project has been developed using Flask as the web framework, integrating various NLP
libraries and models to handle text processing tasks efficiently. The AI News Summarizer not
only demonstrates the potential of artificial intelligence in solving real-world problems but also
highlights its practical applications in the field of text analysis and data extraction.

By automating the summarization and sentiment analysis process, the tool saves users time and
effort, offering a seamless experience. Furthermore, it can serve as a foundation for more
advanced applications in journalism, content curation, and data-driven decision-making. This
project exemplifies the importance of AI in enhancing user interaction with digital information
and addresses the growing need for accessible, time-efficient solutions.

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 7

 1.1 Objectives of the Project

The objectives of a AI News Summarizer are:

1. Automated News Summarization: Develop an AI-based system that processes lengthy

news articles and generates concise summaries to save users' time and provide quick
insights.
2. Sentiment Analysis: Analyze the sentiment of news articles to help users understand
the overall tone (positive, negative, or neutral) of the content.
3. Improved Accessibility: Enable users to access essential information quickly,
especially in time-critical scenarios, by presenting key points from articles in an easily
digestible format.
4. Multi-Domain Coverage: Ensure that the system can handle articles from diverse
domains, including politics, technology, sports, entertainment, and more.
5. User-Friendly Interface: Design a simple and intuitive interface for users to input news
articles or URLs and view summarized content along with sentiment analysis results.
6. Real-Time Processing: Provide quick and efficient processing of news articles to
deliver summaries and sentiment analysis in real time.
7. Scalability: Build a scalable architecture capable of handling a large volume of news
articles with consistent accuracy and performance.
8. Integration of Advanced NLP Techniques: Leverage state-of-the-art Natural
Language Processing (NLP) models and techniques, such as transformers, to ensure
accurate and meaningful summarization and sentiment analysis.
9. Adaptability: Design the system to adapt to updates and improvements in NLP
technologies, ensuring its relevance over time.
10. Ethical Considerations: Ensure the system avoids bias in summarization and sentiment
analysis and respects user privacy.

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 8

 1.2 Significance of the Project

The AI News Summarizer is a valuable tool in today's information-driven world, where

individuals are often overwhelmed by the sheer volume of news articles and updates. The
significance of this project lies in its ability to address this challenge by providing concise,
meaningful summaries of lengthy news articles.

1. Time Efficiency: The summarizer saves time by distilling lengthy news content into
short, easily digestible summaries, enabling users to stay informed without reading full
articles.
2. Enhanced Comprehension: By highlighting the key points of an article, the tool
improves the user's understanding of critical information quickly and effectively.
3. Personalization: With integrated sentiment analysis, users can filter news based on
positive, negative, or neutral tones, making the consumption of news more tailored to
their preferences.
4. Accessibility: The summarizer is beneficial for students, professionals, and general
readers who need quick updates on current affairs or specific topics without investing
excessive time.
5. Real-World Applications: This tool can be used in industries like journalism,
education, and corporate environments where quick and accurate information
dissemination is critical.

By implementing natural language processing (NLP) techniques, this project demonstrates the
practical application of artificial intelligence in solving real-world problems. The project also
provides a learning platform for understanding core AI concepts, such as text summarization,
sentiment analysis, and Flask web application development.

Overall, this project not only serves as a solution for information overload but also as a stepping
stone for exploring advanced AI-driven applications in the future.

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 9

 CHAPTER 2
SOFTWARE REQUIREMENT SPECIFICATION

Introduction
The hardware and software requirements for the AI News Summarizer are designed to ensure
seamless performance and accessibility. On the hardware side, any standard desktop or laptop
with a stable internet connection is sufficient, as the application operates entirely in a web
browser. To ensure optimal functionality, an internet connection is required to fetch real-time
news data from external sources. Overall, the system is lightweight and designed to run
efficiently on most modern devices without requiring high-end hardware.

Purpose
The hardware ensures that the AI News Summarizer runs efficiently on standard devices,
providing the necessary resources for processing and real-time interaction. The software
enables the application’s functionality, using HTML, CSS, and Python to deliver an intuitive
user interface and handle back-end operations. Together, they create a seamless experience for
users to receive personalized summaries and sentiment analysis with minimal delay.

Scope
The scope of the AI News Summarizer extends to transforming the news consumption process
by offering personalized summaries and sentiment analysis for individual users. Specific
capabilities include:

• Summarizing lengthy news articles into concise and relevant information

• Providing sentiment analysis (positive, neutral, or negative) for the summarized content
• Accepting URLs or raw text input for news articles
• Offering a web-based user interface accessible across devices
• Logging and tracking user interactions for potential future improvements

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 10

 2.1Hardware Requirements

The hardware requirements for the AI News Summarizer depend on the scale of the application
and whether the system is being run locally for development or deployed in a production
environment. Below are the general hardware specifications for both cases:

1. Processor (CPU):
o Minimum: Dual-core processor (Intel i5 or equivalent)
o A multi-core processor helps in faster data processing and model computation
when using machine learning libraries such as Transformers
2. RAM:
o Minimum: 4 GB / 8 GB or higher
o The amount of RAM is essential when working with large datasets, particularly
during text processing and model inference
3. Storage:
o Minimum: 1 GB of available disk space
o Sufficient storage is needed to store logs, models, and any other resources
o While a GPU is not strictly necessary for this project since it’s not deeply reliant
on deep learning models, a basic GPU (such as Intel HD Graphics or equivalent)
can be helpful for scaling the system to handle more complex models in the
future

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 11

2.2 Software Requirements

The AI News Summarizer relies on various software tools and libraries that enable the
development, deployment, and functioning of the summarization and sentiment analysis
system. Below are the software requirements for the project:

• Operating System:
o Windows, macOS, or Linux (Ubuntu preferred) to support Python, Flask, and
development tools
• Programming Languages:
o Python 3.x: Backend development, text summarization, and sentiment analysis.
o HTML: Frontend structure and styling
• Databases/Storage:
o SQLite or PostgreSQL for storing user data and logs
• Libraries and Tools:
o NLTK (Natural Language Toolkit) for text processing
o Transformers (Hugging Face) for summarization models
o Flask for web application development
• API Integration:
o News API or similar services for fetching articles (optional)

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 12

 CHAPTER 3
DESIGN AND IMPLEMENTATIONS
The design of the AI News Summarizer focuses on providing an efficient and user-friendly
platform for quick and concise news updates. The tool's intuitive interface enables users to input
news articles or URLs seamlessly, making the summarization process straightforward and
accessible.

The summarizer's conversational and responsive design ensures that users receive accurate and
relevant summaries tailored to their needs. Additionally, the tool incorporates sentiment analysis
to help users gauge the tone of the news at a glance, enhancing the decision-making process.

The backend is powered by advanced NLP techniques, leveraging state-of-the-art AI models for
summarization and sentiment detection, ensuring high-quality results while maintaining a fast
response time. This ensures a seamless experience for users who seek both speed and precision
in their news consumption.

3.1 System Design

Flowchart
In figure 3.1.1, a flowchart is a diagram that visually represents the sequence of steps or
processes in a system or workflow

Figure3.1.1: Flowchart of AI News Summarizer

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 13

3.2 Sequence diagram
In figure3.1.2, a sequence diagram is a type of interaction diagram that shows how objects in
a system interact with each other over time, focusing on the order of messages exchanged. It
visually represents the sequence of events and the flow of communication between
components in a specific use case or scenario.

Figure3.1.2: Sequence Diagram of AI News Summarizer

3.3 Class diagram

In figure 3.1.3, a class diagram is a type of structural diagram in UML (Unified Modeling
Language) that shows the static structure of a system by representing its classes, attributes,
methods, and the relationships between them. It illustrates the system's object-oriented design,
helping to visualize how different classes are organized and how they interact with one another.

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 14

 Figure3.1.3: Class Diagram of AI News Summarizer

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 15

 3.4 Modules with description
3.4.1 Frontend Design(index.html)

Figure 3.2.1 is a simple and interactive interface for the AI News Summarizer application,
created using HTML and CSS. The index.html file provides the foundational structure and
design for the user interface, enabling users to input URLs of news articles for
summarization.The file includes a dark-themed layout styled with embedded CSS, enhancing
readability and user experience. It also incorporates Bootstrap for responsiveness and a clean
design

File:index.html

Figure3.2.1:Snap shot of index.html file

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 16

 Figure3.2.2 :Snap shot of index.html file

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 17

 Figure3.2.3:Snap shot of index.html file

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 18

3.5 Model Setup(model.py)
In the figure 3.2.5, app.py file is where the news summarization and sentiment analysis logic
resides. It uses Natural Language Processing (NLP) techniques to summarize news articles and
analyze their sentiment.
File:model.py

Figure3.2.4:Snap shot of model.pyfile

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 19

 Figure3.2.5:Snap shot of model.pyfile

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 20

 Figure3.2.6:Snap shot of model.pyfile

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 21

CHAPTER 4
RESULTAND CONCLUSION
The results of the AI News Summarizer project demonstrate its ability to effectively summarize
news articles and provide sentiment analysis based on the content, offering a seamless and
informative user experience. By leveraging Natural Language Processing (NLP) techniques,
the application accurately extracts key information from articles and delivers concise,
meaningful summaries along with sentiment classification, enhancing the user's understanding
of the content.

4.1 Snap shot with description

The figure 4.1 displays the user interface where the user can input the link to a news article.
The interface allows users to submit the URL, and the system processes the article to generate
a concise summary along with sentiment analysis, providing an intuitive and user-friendly
experience.

Figure4.1:Snap shot of User Interface

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 22

 The figure 4.2 depicts the process after the user provides a link to a news article. The system
extracts additional details, such as the article's title, authors, publish date, and top image, and
displays them to provide users with comprehensive context. Therefore extracted information
is presented along a side the generated summary and sentiment analysis, offering a complete
and informative user experience.

Figure4.2:Snap shot of User interface with user input

The figure 4.3 displays the output of the AI News Summarizer, showcasing the summarized
content, sentiment analysis, and additional article details. Users also have the option to
download the summary as a text file for offline use.

Figure4.3:Snap shot of the AI News Summarizer Output

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 23

 Conclusion
AI news summarizers have become essential tools in today’s digital world, helping users
manage the ever-growing volume of information. By leveraging AI, natural language
processing, and machine learning, these systems provide concise, accurate, and quick
summaries, allowing users to stay informed without spending excessive time reading lengthy
articles.

The primary benefit of AI news summarizers is their ability to process large amounts of content
and distill the most important information. They offer personalized summaries based on user
preferences and provide sentiment analysis, helping users gauge the emotional tone of
articles—whether positive, negative, or neutral. This feature enhances the summarization
experience, offering deeper insights into news content.

These tools are available 24/7, ensuring users can access the latest summaries at any time. The
scalability of AI news summarizers means they can handle vast amounts of data, making them
suitable for businesses, media organizations, and individuals alike. As AI continues to evolve,
these summarizers will become even more accurate, intelligent, and context-aware, providing
users with tailored news experiences.

Looking ahead, the integration of multilingual capabilities, IoT, and AR/VR will further
enhance the functionality of AI news summarizers, allowing users to interact with news in new
and innovative ways. The ongoing development of emotional intelligence in these systems will
ensure more personalized and intuitive interactions.

In conclusion, AI news summarizers are transforming the way we consume news by offering
faster, more efficient, and personalized solutions. As the technology advances, their potential
to revolutionize news consumption, providing relevant and timely information, will only
continue to grow.

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 24

 Future Enhancement
• Handling Variability:
Enhance the summarizer's robustness to handle diverse writing styles, tones, and
formats in news articles, ensuring consistent and high-quality summaries
• Real-Time Summarization:
With optimized algorithms and enhanced processing, enable faster and more accurate
summarization of breaking news in real-time
• Context Awareness:
Incorporate contextual information such as trending topics or user preferences to
generate relevant and engaging summaries
• Federated Learning:
Adopt decentralized learning models to train on user-specific data locally, ensuring data
privacy while improving personalized summaries
• Misinformation Detection:
Implement advanced algorithms to identify and flag fake news, ensuring users receive
reliable and credible summaries
• Inclusive Datasets:
Train the summarizer on diverse datasets to minimize bias and deliver unbiased
summaries across various cultures and perspectives
• Generative AI:
Utilize cutting-edge AI models like GPT for producing more natural, nuanced, and
detailed summaries that feel human-written
• Explainable AI:
Develop transparent summarization models that provide insights into how summaries
are generated, enhancing trust and usability
• Multimodal Integration:
Combine text summaries with other media, such as audio or video clips, to create richer
and more interactive news experiences
• Augmented Reality (AR):
Leverage AR to display personalized news summaries in real-time, offering an
immersive and engaging way to consume content

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 25

 References

[1] Sethi, P., Sonawane, S., Khanwalker, S., & Keskar, R. B. (2017, December). Automatic
text summarization of news articles. In 2017 International Conference on Big Data, IoT
and Data Science (BID) (pp. 23-29). IEEE.
[2] Gupta, A., Chugh, D., Anjum, & Katarya, R. (2022). Automated news summarization
using transformers. In Sustainable Advanced Computing: Select Proceedings of ICSAC
2021 (pp. 249-259). Singapore: Springer Singapore
[3] Malhotra, S., & Dixit, A. (2013). An effective approach for news article
summarization.International Journal of Computer Applications, 76(16).
[4] Akhmedova, A., Zhazhneva, I., & Galimov, G. (2024, September). System for News
Summarizing Using a Neural Network Algorithm. In 2024 International Russian
Automation Conference (RusAutoCon) (pp. 307-312). IEEE.
[5] Compaoré, I. F., Rodrique, K., Kader, K. A., & Aminata, S. (2024). AI-driven
Generation of News Summaries: large Leveraging GPT and Pegasus Summarizer for
Efficient Information Extraction
[6] Garg, A., Adusumilli, S., Yenneti, S., Badal, T., Garg, D., Pandey, V., ... & Agarwal, R.
(2021). NEWS article summarization with pretrained transformer. In Advanced
Computing: 10th International Conference, IACC 2020, Panaji, Goa, India, December
5–6, 2020, Revised Selected Papers, Part I 10 (pp. 203-211). Springer Singapore.
[7] Liu, Y. L., Cao, M., Blodgett, S. L., Cheung, J. C. K., Olteanu, A., & Trischler, A.
(2023). Responsible AI Considerations in Text Summarization Research: A Review of
Current Practices. arXiv preprint arXiv:2311.11103.
[8] Georgiev, G. (2023). Analyzing the performance of AI summarization with limited
resource allocation.

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING,AJIET(2024-2025) 26