• International Journal of Computer Science & Network Security
• /
• v.21 no.3
• /
• pp.112-119
• /
• 2021

Social media has become a global means of communication in people's lives. Most people are using Twitter for communication purposes and its inappropriate use, which has negative effects on people's lives. One of the widely common misuses of Twitter is cyberbullying. As the resources of dialectal Arabic are rare, so for cyberbullying most people are using dialectal Arabic. For this reason, the ultimate goal of this study is to detect and classify cyberbullying on Twitter in the Arabic context in Saudi Arabia. To help in the detection and classification of tweets, Pointwise Mutual Information (PMI) to generate a lexicon, and Support Vector Machine (SVM) algorithms are used. The evaluation is performed on both methods in terms of the F1-score. However, the F1-score after applying the PMI is 50%, while after the SVM application on the resampling data it is 82%. The analysis of the results shows that the SVM algorithm outperforms better.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.115-126
• /
• 2022

The goal of this research is to look into different techniques to solve the problem of authorship verification for Arabic short writings. Despite the widespread usage of Twitter among Arabs, short text research has so far focused on authorship verification in languages other than Arabic, such as English, Spanish, and Greek. To the best of the researcher's knowledge, no study has looked into the task of verifying Arabic-language Twitter texts. The impact of Stylometric and TF-IDF features of very brief texts (Arabic Twitter postings) on user verification was explored in this study. In addition, an analytical analysis was done to see how meta-data from Twitter tweets, such as time and source, can help to verify users perform better. This research is significant on the subject of cyber security in Arabic countries.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.120-128
• /
• 2023

In this work, we have presented ATSA, a hierarchical attention deep learning model for Arabic sentiment analysis. ATSA was proposed by addressing several challenges and limitations that arise when applying the classical models to perform opinion mining in Arabic. Arabic-specific challenges including the morphological complexity and language sparsity were addressed by modeling semantic composition at the Arabic morphological analysis after performing tokenization. ATSA proposed to perform phrase-chunks sentiment embedding to provide a broader set of features that cover syntactic, semantic, and sentiment information. We used phrase structure parser to generate syntactic parse trees that are used as a reference for ATSA. This allowed modeling semantic and sentiment composition following the natural order in which words and phrase-chunks are combined in a sentence. The proposed model was evaluated on three Arabic corpora that correspond to different genres (newswire, online comments, and tweets) and different writing styles (MSA and dialectal Arabic). Experiments showed that each of the proposed contributions in ATSA was able to achieve significant improvement. The combination of all contributions, which makes up for the complete ATSA model, was able to improve the classification accuracy by 3% and 2% on Tweets and Hotel reviews datasets, respectively, compared to the existing models.

• International Journal of Computer Science & Network Security
• /
• v.21 no.3
• /
• pp.206-211
• /
• 2021

Internet users are increasingly invited to express their opinions on various subjects in social networks, e-commerce sites, news sites, forums, etc. Much of this information, which describes feelings, becomes the subject of study in several areas of research such as: "Sensing opinions and analyzing feelings". It is the process of identifying the polarity of the feelings held in the opinions found in the interactions of Internet users on the web and classifying them as positive, negative, or neutral. In this article, we suggest the implementation of a sentiment analysis tool that has the role of detecting the polarity of opinions from people about COVID-19 extracted from social media (tweeter) in the Arabic language and to know the impact of the pre-processing phase on the opinions classification. The results show gaps in this area of research, first of all, the lack of resources when collecting data. Second, Arabic language is more complexes in pre-processing step, especially the dialects in the pre-treatment phase. But ultimately the results obtained are promising.

• International Journal of Computer Science & Network Security
• /
• v.23 no.2
• /
• pp.13-30
• /
• 2023

Since the COVID-19 vaccine became available, people have been sharing their opinions on social media about getting vaccinated, causing discussions of the vaccine to trend on Twitter alongside certain events, making the website a rich data source. This paper explores people's perceptions regarding the COVID-19 vaccine during certain events and how these events influenced public opinion about the vaccine. The data consisted of tweets sent during seven important events that were gathered within 14 days of the first announcement of each event. These data represent people's reactions to these events without including irrelevant tweets. The study targeted tweets sent in Arabic from users located in Saudi Arabia. The data were classified as positive, negative, or neutral in tone. Four classifiers were used-support vector machine (SVM), naïve Bayes (NB), logistic regression (LOGR), and random forest (RF)-in addition to a deep learning model using BiLSTM. The results showed that the SVM achieved the highest accuracy, at 91%. Overall perceptions about the COVID-19 vaccine were 54% negative, 36% neutral, and 10% positive.

• The Journal of the Korea Contents Association
• /
• v.16 no.4
• /
• pp.434-441
• /
• 2016

Using bigdata analysis procedures, the present study sought to review and explore the various aspects of self-disclosure and boundary impermeability of worldwide twitter users. A total of 415 million tweets issued by 54 million users were collected during 6 months and the users of top 10 languages were investigated. And the effect of languages of twitter users on the boundary impermeability, disclosure rate of user profile, profile image, geographical information, URL in profile and user description were analyzed in this study. The results showed that the boundary impermeability and all the self-disclosure rates of twitter users (profile, profile image, geographical information, URL in profile, user description) were significantly (p<0.001) different among language groups of users. The self-disclosure rates and the average points of Portuguese, Indonesian and Spanish users were higher than those of Arabic, Japanese, Turkish and Korean users. The results also showed a positive relationship between boundary impermeability and the number of tweets (including retweets) issued by each users.