MMMalak Mashaabi

Malak Mashaabi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Malak Mashaabi has a total of 6 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Survey of Large Language Models for Arabic Language and its Dialects

    by Malak Mashabi, Shahad Al-Khalifa, Hend Al-Khalifa

    This survey presents a comprehensive review of Large Language Models (LLMs) developed for the Arabic language and its dialects. It categorizes models by architecture (encoder-only, decoder-only, and encoder-decoder) and by linguistic form, including Classical Arabic, Modern Standard Arabic, and Dialectal Arabic. We analyze monolingual, bilingual, and multilingual models, evaluating their performance on tasks such as sentiment analysis, named entity recognition, and question answering. The survey also assesses model openness, considering factors like access to source code, training data, weights, and documentation. Our findings highlight a concentration of resources on MSA, a lack of diverse dialectal datasets, and limited transparency across many models. This work offers the first systematic comparison of openness and linguistic coverage in Arabic LLMs and outlines key challenges and research opportunities to support more inclusive, reproducible, and representative Arabic NLP.


  • Open Access

    Mumtathil: Automatic PDPL compliance identification system of Arabic privacy policies documents

    by Malak Mashaabi, Hend Al-Khalifa

    In the digital era, the extensive collection and use of personal data by websites and applications has prompted various countries to implement data protection laws. The Kingdom of Saudi Arabia introduced the Personal Data Protection Law (PDPL) to regulate the handling of personal data. However, manually assessing compliance with these laws is time-consuming, and costly. This paper presents an automated system named Mumtathil (مُمتثِل) that evaluates the compliance of Arabic privacy policies with the PDPL using multi-label classification (MLC) techniques. Our experiments demonstrated that the Support Vector Machine (SVM) outperformed other machine learning models and transformer-based models like CamelBERT and AraBERT, achieving an F-score of 92%. The system addresses dataset imbalance by augmenting the Saudi Privacy Policy Dataset with recent privacy policies and synthetic data generated using ChatGPT. The Mumtathil tool simplifies compliance assessment, reducing time, cost, and effort while enhancing transparency and data protection in the digital landscape.

  • Open Access

    IoT Based Accident Prevention System using Machine Learning techniques

    by Raghad Alnashwan, Malak Mashaabi, Areej Alotaibi, Hala Qudaih, Lamya Albraheem

    The likelihood of car accidents increases during extreme weather conditions, such as fog, winds, snow, rain, etc. While it may not be possible to prevent all such accidents, their incidence can be reduced by taking proper measures. Therefore, an intelligent accident-avoidance system is necessary to predict the severity of accidents based on weather and road conditions. This research paper suggests three machine learning (ML) methods for an Internet of Things (IoT)-based accident severity prediction system. The methods are Random Forest, LightGBM, and XGBoost.The aim is to predict the severity of car accidents based on various weather features using a machine learning model. However, considering the previous work, we observed that the size of datasets is frequently minimal, and some of the research discusses the influence of the weather on the number of accidents. Therefore, we used the Countrywide Traffic Accident Dataset, which covers 2.8 million vehicle accidents in the United States from 2016 to 2021. In conclusion, our methodology appears to be efficient in predicting the severity of car accidents. Among the three methods, LightGBM achieved the highest prediction accuracy (72%), precision (70%), recall (70%), F1-scores (70%), and area curve (AUC) (0.86) of the receiver operating characteristic (ROC) curve.