Abstract In recent years, large language models (LLMs) have gained significant traction across various domains, including education. This paper explores the application of LLMs in grading programming assignments. By leveraging data collected from existing programming assignments and their corresponding grades, we aim to develop a robust LLM-based grading system. We also incorporate augmented data representing various grading scenarios to enhance the model’s performance and ensure comprehensive coverage across all grading levels. Our approach involves training the LLM on this combined dataset to enable accurate and consistent evaluation of programming assignments. The proposed model, BeGrading, aims to reduce the grading burden on educators and provide timely and objective feedback to students. Compared to the Codestral model, our proposed model demonstrates an absolute difference rate of 19%, equivalent to $$\pm 0.95$$ ± 0.95 out of 5. This is acceptable for using a small, fine-tuned model with optimized data. Additionally, the Codestral model compared to the dataset optimized score shows a difference of 15% equivalent to a margin of $$\pm 0.75$$ ± 0.75 out of 5. Preliminary results demonstrate the potential of LLMs to perform grading tasks with a high degree of reliability, opening avenues for further research and practical applications in automated education systems.

Abstract IoT devices convert billions of objects into data-generating entities, enabling them to report status and interact with their surroundings. This data comes in various formats, like structured, semi-structured, or unstructured. In addition, it can be collected in batches or in real time. The problem now is how to benefit from all of this data gathered by sensing and monitoring changes like temperature, light, and position. In this paper, we propose a predictive analytics framework constructed on top of open-source technologies such as Apache Spark and Kafka. The framework focuses on forecasting temperature time series data using traditional and deep learning predictive analytics methods. The analysis and prediction tasks were performed using Autoregressive Integrated Moving Average (ARIMA), Seasonal Autoregressive Integrated Moving Average (SARIMA), Long Short-Term Memory (LSTM), and a novel hybrid model based on Convolution Neural Network (CNN) and LSTM. The purpose of this paper is to determine whether and how recently developed deep learning-based models outperform traditional algorithms in the prediction of time series data. The empirical studies conducted and reported in this paper demonstrate that deep learning-based models, specifically LSTM and CNN-LSTM, exhibit superior performance compared to traditional-based algorithms, ARIMA and SARIMA. More specifically, the average reduction in error rates obtained by LSTM and CNN-LSTM models were substantial when compared to other models indicating the superiority of deep learning. Moreover, the CNN-LSTM-based deep learning model exhibits a higher degree of closeness to the actual values when compared to the LSTM-based model.

The vast growth of online and offline data has revolutionized how we gather, evaluate, and understand information. Comprehending lengthy text documents and extracting crucial details from them can be difficult and time-consuming. In response to these challenges, text summarization techniques have emerged to condense long texts while retaining their essential content. These techniques rely on delivering filtered, high-quality information promptly to users. However, due to the enormous volume of data generated from various sources and technologies, automatically summarizing large-scale data remains a difficult task. This paper introduces a novel problem-solving paradigm by integrating two powerful transformer models: Neural Machine Translation (NMT) using Helsinki Transformer and text summarization using the mT5_mutilingual_XLSum on WikiHow and BBC Arabic news datasets. Our approach transcends traditional methods, offering a fresh perspective on maintaining coherence and naturalness in generated summaries. It aims to produce more fluent and context-aware summaries, particularly tailored to the intricacies of the Arabic language. With this integration, we can harness the capabilities of NMT models to produce concise and coherent summaries of text in various languages, such as Arabic. The proposed approach automatically translates English text to be summarized as Arabic text through the presented integration, addressing the lack of Arabic language resources. This integration significantly improves the quality and precision of Arabic text summaries, giving promising results on the mixed dataset between WikiHow and BBC Arabic News.

Arabic Dialect Identification (ADI) is the task of automatically detecting the regional dialect of the Arabic language from a given text or speech sample. It has gained significant attention due to the increasing demand for language-processing tasks in many applications such as social media analysis, content localization, and even dialectal text analysis. In this paper, an ADI system is built using a country-level Arabic dataset. The approach taken in this paper is to run a set of experiments using CAMeL Tools which is a machine learning-based model built for Arabic Natural Language Processing(NLP). Transformer-based models are tested such as the following BERT-based pre-trained models: AraBERT, CAMeLBERT and RoBERTa. In addition to GPT-based models: Alpaca and ChatGPT which have never been experimented before on a country-level dialectal dataset. This paper evaluates and discusses the performance of the mentioned models and tools on a dialectal Arabic dataset taking into consideration the base training data and model behavior. These experiments have shown that GPT-based models are considerably distant from effectively performing the dialect classification task. BERT-based models showed overfitting, and the fine-tuned Roberta almost exceeded the task-specific CAMeL BERT before fine-tuning. According to these findings, there is no qualified dialectal dataset to generalize over the task needed.

In recent years, Long language models have made significant progress, enabling machines to interpret and process human language. However, the Arabic language presents unique challenges due to its rich morphology and diverse sentence structures. The development of specialized language models for Arabic question answering has implications for improved human- computer interaction, cultural preservation, and accessibility. This paper aims to enhance the comprehension and contextual understanding of Arabic-posed questions by leveraging the capabilities of the LLaMa language model and the XLNet transformer. The ARCD dataset, which mainly consists of an Arabic dataset for question-answering, was used to fine- tune the LLaMa 2.0 and XLNet. By utilizing LLaMA and XLNet transformers separately, This paper contributes to the construction of an NLP pipeline that can properly understand and process Arabic text to provide answers depending on a particular Arabic context by using LLaMA and XLNet transformers individually. It is important to note that Arabic datasets were not previously used to train the LLaMa language model. The LLaMA language model received accuracy scores of 93.70