The rapid evolution of video programming tutorials as a key educational resource has highlighted the need for effective code extraction methods. These tutorials, varying widely in video quality, present a challenge for accurately transcribing the embedded source code, crucial for learning and software development. This study investigates the impact of video quality on the performance of optical character recognition (OCR) engines and the potential of large language models (LLMs) to enhance code extraction accuracy. Our comprehensive empirical analysis utilizes a rich dataset of programming screencasts, involving manual transcription of source code and the application of both traditional OCR engines, like Tesseract and Google Vision, and advanced LLMs, including GPT-4V and Gemini. We investigate the efficacy of image super-resolution (SR) techniques, namely, enhanced deep super-resolution (EDSR) and multi-scale deep super-resolution (MDSR), in improving the quality of low-resolution video frames. The findings reveal significant improvements in OCR accuracy with the use of SR, particularly at lower resolutions such as 360p. LLMs demonstrate superior performance across all video qualities, indicating their robustness and advanced capabilities in diverse scenarios. This research contributes to the field of software engineering by offering a benchmark for code extraction from video tutorials and demonstrating the substantial impact of SR techniques and LLMs in enhancing the readability and reusability of code from these educational resources.

The Saudi General Aptitude Test (GAT) aims to measure the analytical and inferential learning abilities of high school graduates seeking admission to higher education institutions. Given the need for effective preparation tools, this study investigates the potential of chat generative pre-trained transformers to assist students in preparing for the GAT, especially in Arabic. The primary objective is to assess the effectiveness of Large Language Models (LLMs) in answering questions related to mental and logical abilities, specifically in Arabic. The performance of GPT-4, GPT-4o, and Gemini was examined through 21 experiments to determine their accuracy in answering a range of GAT-related questions. The findings indicate that although GPT-4 and GPT-4o outperformed Gemini in providing accurate answers for the GAT, their current accuracy levels still require improvement.

Developers often rely on online resources, such as Stack Overflow (SO), to seek assistance for programming tasks. To facilitate effective search and resource discovery, manual tagging of questions and posts with the appropriate programming language is essential. However, accurate tagging is not consistently achieved, leading to the need for the automated classification of code snippets into the correct programming language as a tag. In this study, we introduce a novel approach to automated classification of code snippets from Stack Overflow (SO) posts into programming languages using generative pre-trained transformers (GPT). Our method, which does not require additional training on labeled data or dependency on pre-existing labels, classifies 224,107 code snippets into 19 programming languages. We employ the text-davinci-003 model of ChatGPT-3.5 and postprocess its responses to accurately identify the programming language. Our empirical evaluation demonstrates that our GPT-based model (SCC-GPT) significantly outperforms existing methods, achieving a median F1-score improvement that ranges from +6% to +31%. These findings underscore the effectiveness of SCC-GPT in enhancing code snippet classification, offering a cost-effective and efficient solution for developers who rely on SO for programming assistance.