Sentiment analysis refers to the task of identifying polarity of positive and negative for particular text that yield an opinion. Arabic language has been expanded dramatically in the last decade especially with the emergence of social websites (e.g. Twitter, Facebook, etc.). Several studies addressed sentiment analysis for Arabic language using various techniques. The most efficient techniques according to the literature were the machine learning due to their capabilities to build a training model. Yet, there is still issues facing the Arabic sentiment analysis using machine learning techniques. Such issues are related to employing robust features that have the ability to discriminate the polarity of sentiments. This paper proposes a hybrid method of linguistic and statistical features along with classification methods for Arabic sentiment analysis. Linguistic features contains stemming and POS tagging, while statistical contains the TF-IDF. A benchmark dataset of Arabic tweets have been used in the experiments. In addition, three classifiers have been utilized including SVM, KNN and ME. Results showed that SVM has outperformed the other classifiers by obtaining an f-score of 72.15%. This indicates the usefulness of using SVM with the proposed hybrid features.
<p>With the rapid growth of the Internet and mobile devices, the need for hidden communications has significantly increased. Steganography is a technique introduced for establishing hidden communication, Most steganography techniques have been applied to audio, images, videos, and text. Many researchers used steganography in Arabic texts to take advantage of adding, editing or changing letters or diacritics, but lead to notable and suspicious text. In this paper, we propose two novel steganography algorithms for Arabic text using the Holy Quran as cover text. The fact that it is forbidden to add, edit or change any letter or diacritics in the Holy Quran provides the valuable feature of its robustness and difficulty as a cover in steganography. The algorithms hide secret messages elements within Arabic letters benefiting from the existence of sun letters (Arabic: ḥurūf shamsīyah) and moon letters (ḥurūf qamarīyah). Also, we consider the existence of some Arabic language characteristics represented as small vowel letters (Arabic Diacritics). Our experiments using the proposed two algorithms demonstrate high capacity for text files. The proposed algorithms are robust against attack since the changes in the cover text are imperceptible, so our contribution offers a more secure algorithm that provides good capacity.</p>
Nowadays, organizations are widely using a cloud database engine from the cloud service providers. Privacy still is the main concern for these organizations where every organization is strictly looking forward more secure environment for their own data. Several studies have proposed different types of encryption methods to protect the data over the cloud. However, the daily transactions represented by queries for such databases makes encryption is inefficient solution. Therefore, recent studies presented a mechanism for classifying the data prior to migrate into the cloud. This would reduce the need of encryption which enhances the efficiency. Yet, most of the classification methods used in the literature were based on string-based matching approach. Such approach suffers of the exact match of terms where the partial matching would not be considered. This paper aims to take the advantage of N-gram representation along with Support Vector Machine classification. A real-time data will used in the experiment. After conducting the classification, the Advanced Encryption Standard algorithm will be used to encrypt the confidential data. Results showed that the proposed method outperformed the baseline encryption method. This emphasizes the usefulness of using the machine learning techniques for the process of classifying the data based on confidentiality.
Steganography is one of the cryptography techniques where secret information can be hidden through multimedia files such as images and videos. Steganography can offer a way of exchanging secret and encrypted information in an untypical mechanism where communicating parties can only interpret the secret message. The literature has shown a great interest in the least significant bit (LSB) technique which aims at embedding the secret message bits into the most insignificant bits of the image pixels. Although LSB showed a stable performance of image steganography yet, many works should be done on the message part. This paper aims to propose a combination of LSB and Deflate compression algorithm for image steganography. The proposed Deflate algorithm utilized both LZ77 and Huffman coding. After compressing the message text, LSB has been applied to embed the text within the cover image. Using benchmark images, the proposed method demonstrated an outperformance over the state of the art. This can proof the efficacy of using Deflate as a data compression prior to the LSB embedding.
Splitting identifiers is a task that has been addressed in the past few years in order to contribute toward improving the Feature Location task. Feature Location aims at determining the exact position of a specific feature within a source code. Several research studies have addressed the process of splitting multi-word identifiers. However, one of the endure gaps that still face the use of machine learning lies on using probabilistic algorithms which may seem insufficient compared to other sophisticated algorithms such as the Backpropagation Neural Network (BPNN). Therefore, this paper proposes a BPNN for the splitting identifiers task. A benchmark of source code dataset has been used in the experiments. In addition, different objective functions have been used including Tanh, Sigmoid and Softmax. Results showed that Softmax has outperformed the other objective funciton by achieving a 71.4% of f-measure. This results implies the usefulness of BPNN in terms of handling character-based problems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.