Final Year Project on Automated Text Summarizer with AES Encryption & Decryption
Are you searching for developing the project in a new concept rather than a management system? If yes, then you are in the right place. In this tutorial, I will explain about the final year project on Automated Text Summarizer in brief. This is the project which was accepted in the final year exam of BSC CSIT (TU University) and got the title of "★The Best Project of the Year★". Choosing the right project topic is very difficult at first. I think this project will help you to take the reference. This system is based on two main algorithm Text rank algorithm for text summarization and AES for encryption and decryption. You are also allowed to download the source code and documentation. You can see the demo video on youtube (Youtube link is given in last).
Abstract:
In the modern Internet age, there has been an explosion in the amount of text data from various sources. This volume of text can be an invaluable source of information and knowledge which needs to be effectively summarized to be meaningful. Automated Text Summarizer with encryption and decryption is a web application designed with the Textrank Algorithm to generate concise and fluent summary conveying the key information preserving overall meaning in the input and the AES algorithm to encrypt and decrypt the text. There are generally two types of automatic text summarization approaches: extractive and abstractive. This project will focus on using text mining techniques, statistical and linguistic models for extractive summarization on long texts. It uses features such as word embedding, word frequency, and phrase frequency to extract important sentences from the text for summarization purposes. Results have shown that picking the shortest-clause from the most important sentences chosen by the Textrank Algorithm appears to have the best performance. In addition, the application will also save the history of the summary and let the user see their summary later.
Problem
Statement:
With a big amount of data circulating in the digital space, it is a challenging and time-consuming the process to read whole information. Researchers and students constantly
face this scenario: It is almost impossible to read most if not all of the
newly published papers to be informed of the latest progress and when they work
on a research project, the time spent on reading literature review seems
endless. There are two
possible solutions to solve this problem: manual summarization and automatic
summarization. However, manual summarization usually can provide quality
results but it is time-consuming and costly with need for human interaction. So,
there is a need to develop such a system that can automatically shorten longer
texts and deliver accurate summaries fluently passing the intended messages. Furthermore,
applying text summarization reduces reading time, speed of the process of
researching for vast information from the Internet, and increases the amount of
information that can suit in an area.
With the using more and more technologies in daily life, large amounts of data are generated, a great share of which is sensitive data. If someone else gets hold of that data, there may be a risk of information theft. Encryption changes the information so that it is incomprehensible and therefore unusable to anyone who does not have the key.
Statement:
In this modern era, where tremendous information is available on the Internet, it is essential to develop an efficient & effective ATS for the following objectives:
· To address the problem of selecting the most important portions of the text.
· To make human life more comfortable by reducing the reading time.
· To solve the problem of identifying the essential, meaningful information in a document or blog by summarizing them preserving its core meaning that is less biased than human summarizers.
· To implement AES algorithm for encryption and decryption techniques to ensure security of textual data.
User Login:
The login modal is designed for the user side interface. This modal is designed in such a way that users can enter the registered username and password in order to login to the system successfully. The system also offers the OAuth2 authentication for login through Google API or Facebook API.
Algorithm used:
Two
main algorithms used in this system are the Textrank algorithm and the AES algorithm. Textrank the algorithm used for text summarization and the AES algorithm used for encryption and
decryption. Textrank is an algorithm
inspired by Google’s PageRank algorithm that helps identify key sentences from
a large text the idea behind this algorithm
is that the sentence that is similar to most other sentences in the passage is
probably the most important sentence in the passage.
This algorithm is best suited for extractive summarization
Text Rank Algorithm
1. Take the input from the user either in the form of URL or document.
2. If the input is URL, then go to 4.
3. If the input is document, then go to 5.
4. Extract the right content from a given URL, then go to 6.
5. Take the full CONTENT from the provided document.
6. Split the whole text into PARAGRAPH.
7. Split each PARAGRAPH into SENTENCES.
8. Find word embeddings for each and every sentence
9. Split each sentence into words
10. Remove the stop words
11. Remove abbreviations and sentences with only two words
12. Compare every sentence with every other. This is done by Counting the number of common words and then Normalize this by dividing by average number of words per sentence
13. These intermediate scores/values are stored in an INTERSECTION matrix
14. Construct the similarity matrix between sentences
15. Create the key-value dictionary - Key: Sentence - Value: Sum of intersection values with this sentence
16. From every paragraph, extract the sentences with the highest score.
17. Sort the selected sentences in order of appearance in the original text to preserve content and meaning.
Advanced Encryption
Standard (AES) Algorithm
Another main algorithm used in this system for encryption and
decryption is AES algorithm. The AES was published by NIST in 2001. It is a 128-block
cipher and widely used for both government and commercial purposes. The
Rijndael proposal for AES defined a cipher in which the block length and the
key length can be independently specified to be 128, 192 0r 256 bits. The AES the specification uses the same three key size alternatives but limits the block
length to 128 bits.
Steps in AES algorithm
1. Derive the set of round keys from the cipher key.
2. Initialize the state array with the block data (plaintext).
3. Add the initial round key to the starting state array.
4. Perform nine rounds of state manipulation.
5. Perform the tenth and final round of state manipulation.
6. Copy the final state array out as the encrypted data (ciphertext).
Four different
operations in each round
· Add Round Keys
· Substitute Bytes
· Shift Rows
· Mix Columns
To download the source code goto my youtube channel and watch the video. Do subscribe, like, and share my video and then the link for source code is given in the description of the video. Download the code and enjoy it 😎
0 Comments