To avoid citizen disputes, hate speech on social media, such as Twitter, must be automatically detected. The current research in Indonesian Twitter focuses on developing better hate speech detection models. However, there is limited study on the explainability aspects of hate speech detection. The research aims to explain issues that previous researchers have not detailed and attempt to answer the shortcomings of previous researchers. There are 13,169 tweets in the dataset with labels like “hate speech” and “abusive language”. The dataset also provides binary labels on whether hate speech is directed to individual, group, religion, race, physical disability, and gender. In the research, classification is performed by using traditional machine learning models, and the predictions are evaluated using an Explainable AI model, such as Local Interpretable Model-Agnostic Explanations (LIME), to allow users to comprehend why a tweet is regarded as a hateful message. Moreover, models that perform well in classification perceive incorrect words as contributing to hate speech. As a result, such models are unsuitable for deployment in the real world. In the investigation, the combination of XGBoost and logical LIME explanations produces the most logical results. The use of the Explainable AI model highlights the importance of choosing the ideal model while maintaining users’ trust in the deployed model.

Big data analytics has become a key element in research and development in various fields. With the ability to analyze large and complex amounts of data, this technology allows researchers to identify patterns, trends, and insights that were not seen before. This article explores how big data analytics is applied in various disciplines, including computer science, engineering, and mathematics. We use Python for data processing and analysis, as well as VOSviewer for in-depth bibliometric visualization. The study highlights recent developments in big data analysis methodologies, the challenges they face, and the potential for the future. Our findings suggest that the integration of advanced analytical techniques can accelerate scientific discovery and improve understanding across different research domains.

Text encryption is one of the techniques used to maintain the confidentiality of information in digital communications. In this study, we propose to apply a combination of the Unimodular Hill Cipher and RSA methods to a text encryption algorithm using the Python programming language. The Unimodular Hill Cipher method uses an unimodular matrix to replace text characters with encrypted characters, while RSA (Rivest-Shamir-Adleman) is a public key encryption algorithm that relies on modulo arithmetic properties. The purpose of this research is to combine the strengths of the two methods and produce a more secure text encryption system. Unimodular Hill Cipher provides the advantage of randomizing text characters by using matrix modulo operations, while RSA provides a high level of security through the use of public and private key pairs. In this study, we explain in detail the basic theory and algorithms of the Unimodular Hill Cipher and RSA. We also describe the implementation steps of both methods in the Python programming language. The text data used in this study went through a preprocessing stage before being encrypted. We also analyze the results of the encryption using several statistical methods to measure how close the relationship between the original text and the result of the encryption is. In a comparative analysis with the previous paper, in this study, the use of the Unimodular Hill Cipher and RSA methods in the context of Python provides additional insight into the performance and level of security of both. The experimental results show that the combination of the Unimodular Hill Cipher and RSA methods can produce a higher level of security in text encryption. It is hoped that this research can contribute to the development of a more effective and secure text encryption algorithm.

This research aims to propose a safe digital video data alternative employing symmetric cryptography and an encryption technique using Partition. The Hill Cipher method requires a square key matrix with an inverse modulo the unimodular matrix is one of the unique matrices with an inverse. The encryption mechanism is modulo matrix multiplication, with shift cipher encryption employed to encrypt defective partitions. The results reveal that the videos are well encrypted and difficult for third parties to read the partition encryption technology assures that the encrypted and decrypted file sizes are the same. The background of this topic is that digital data security is increasingly important due to the increasing use of digital technology. This research aims to develop a more secure and effective video encryption algorithm by combining several cryptographic methods such as Hill cipher, partition, the shift cipher, unimodular matrix, and binary file concept logistic function. The method used in this study is experimental by using the Python programming language to implement the encryption algorithm. The trials were carried out by comparing the performance of the algorithms developed using different key sizes and variations of the combination methods used. The results show that the developed algorithm can provide a high level of security in the video encryption process with good effectiveness. The use of a combination of different cryptographic methods also has a positive impact on the resulting level of security. Therefore, the developed encryption algorithm can be a good alternative for use in securing sensitive video data.

The LSB method in steganography usually only uses the last bit or the last few bits that are the same for all pixels. This is very easy to solve by using a bitwise shift left operation so that the last bit becomes the leading bit (MSB). Some techniques combine steganography and cryptography through two different processes. In this study, a new technique is proposed to perform steganography and cryptography together. The random sequence obtained from the logistic map is used to determine the number of bits in the LSB method. Furthermore, testing was carried out on several grayscale images. The result obtained is that the hidden images cannot be opened easily. The level of sensitivity is very small, reaching 10^-15.

The advancement and sophistication of technology in the present era have resulted in millions of people interacting and sharing data through the internet using various platforms such as email, chat applications, and others. This has led to the dissemination of personal information and data worldwide through the internet, which also poses the possibility of data interception by unauthorized parties. Data breaches occur when data is not securely protected. One way to secure data is by using the concept of cryptography. In this paper, a modification will be made to the classical cryptography algorithm, Hill Cipher, by incorporating the chaos function of Henon Map in generating unimodular key matrices. Based on the design and development results, the modified algorithm of Hill Cipher is capable of securing data quite effectively with a sufficiently large key space and a wide encryption set. The modified algorithm of Hill Cipher will be implemented in a data sender application.