Unsupervised Detection of Violent Content in Arabic Social Media

Abdelfatah, Kareem; Terejanu, Gabriel; Alhelbawy, Ayman

doi:10.5121/csit.2017.70401

Cited by 12 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments revealed that combining the seed word list with the extended list generated the best F1 score of 60%. Authors in [4] presented a more detailed dataset for religious hate speech in dialectical Arabic. The dataset comprised 6,600 tweets using religious-related keywords.…”

Section: B Existing Arabic Datasetsmentioning

confidence: 99%

Data Mining Regarding Cyberbullying in the Arabic Language on Instagram Using KNIME and Orange Tools

Al-Zahrani

2022

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

This paper deals with data mining on verbal bullying by Instagram users. It tracks people who repeatedly have abusive behavior and may cause harm to other persons or groups. In this work, a dataset holding verbal bullying in the Arabic language was extracted from Instagram comments, and the entries were classified as regular verbal bullying and suspicious verbal bullying. KINIME and Orange open source data mining tools were utilized to discover comments that involved verbal bullying on Instagram and to delete previous comments while users sent their comments automatically and immediately. Classification algorithms Rule-Based in KNIME and Select Rows in Orange were used.

show abstract

Section: B Existing Arabic Datasetsmentioning

confidence: 99%

Data Mining Regarding Cyberbullying in the Arabic Language on Instagram Using KNIME and Orange Tools

Al-Zahrani

2022

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

show abstract

“…Abdelfatah et al (2017) [16] proposed a new framework aiming at separating violent and non-violent Arabic tweets over Twitter by using sparse Gaussian process latent variable model (SGPLVM) followed by k-means. Experiment started by collecting 16234 Arabic tweets then pre-processing tweets by removing stop word and web links, after that they annotated manually by at least five different annotators and only tweets have a confidence score more than 0.7 are applied, then two set of experiments have been carried out.…”

Section: Related Workmentioning

confidence: 99%

Violence Detection over Online Social Networks: An Arabic Sentiment Analysis Approach

Khalafat

Alqatawna²,

Al-Sayyed

et al. 2021

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

<p class="0abstract">Today, the influence of the social media on different aspects of our lives is increasing, many scholars from various disciplines and majors looking at the social media networks as the ongoing revolution. In Social media networks, many bonds and connections can be established whether being direct or indirect ties. In fact, Social networks are used not only by people but also by companies. People usually create their own profiles and join communities to discuss different common issues that they have interest in. On the other hand, companies also can create their virtual presence on the social media networks to benefit from this media to understand the customers and gather richer information about them. With all of the benefits and advantages of social media networks, they should not always be seen as a safe place for communicating, sharing information and ideas, and establishing virtual communities. These information and ideas could carry with them hatred speeches that must be detected to avoid raising violence. Therefore, web content mining can be used to handle this issue. Web content mining is gaining more concern because of its importance for many businesses and institutions. Sentiment Analysis (SA) is an important sub-area of web content mining. The purpose of SA is to determine the overall sentiment attitude of writer towards a specific entity and classify these opinions automatically. There are two main approaches to build systems of sentiment analysis: the machine learning approach and the lexicon-based approach. This research presents the design and implementation for violence detection over social media using machine learning approach. Our system works on Jordanian Arabic dialect instead of Modern Standard Arabic (MSA). The data was collected from two popular social media websites (Facebook, Twitter) and has used native speakers to annotate the data. Moreover, different preprocessing techniques have been used to show their effect on our model accuracy. The Arabic lexicon was used for generating feature vectors and separate them to features set. Here, we have three well known machine learning algorithms: Support Vector Machine (SVM), Naive Bayes (NB) and k-Nearest Neighbors (KNN). Building on this view, Information Science Research Institute’s (ISRI) stemming and stop word file as a result of preprocessing were used to extract the features. Indeed, several features have been extracted; however, using the SVM classifier reveals that unigram and features extracted from lexicon are characterized by the highest accuracy to detect violence.</p>

show abstract

From Machine Learning to Deep Learning for Detecting Abusive Messages in Arabic Social Media: Survey and Challenges

Azzi

Zribi

2021

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Unsupervised Detection of Violent Content in Arabic Social Media

Abstract: ABSTRACT

Cited by 12 publications

References 11 publications

Data Mining Regarding Cyberbullying in the Arabic Language on Instagram Using KNIME and Orange Tools

Data Mining Regarding Cyberbullying in the Arabic Language on Instagram Using KNIME and Orange Tools

Violence Detection over Online Social Networks: An Arabic Sentiment Analysis Approach

From Machine Learning to Deep Learning for Detecting Abusive Messages in Arabic Social Media: Survey and Challenges

Contact Info

Product

Resources

About