Academic dishonesty, particularly source-code plagiarism, poses significant ethical challenges in educational institutions and online coding platforms. It undermines the integrity of the learning and teaching process as well as the credibility of students and institutions. To address these challenges, this study developed a code similarity assessment tool utilizing deep neural networks, specifically character-level recurrent neural networks (char-RNN) and long short-term memory networks (LSTM), to detect source-code plagiarism. It leverages the strengths of both models while minimizing their weaknesses, allowing it to learn and capture both low-level and short-term patterns as well as complex and long-term dependencies in the source code. The dataset used was mainly from the "IR Plag Dataset", and data augmentation and various preprocessing techniques were performed. The final model configuration of the hybrid neural network architecture resulted in training and validation accuracy of 99% and 90% , respectively. Its evaluation was conducted using various metrics such as precision, recall, and Fl -score. The hybrid neural network architecture achieved a precision of 0.94, a recall of 0.935, an Fl -score of 0.94, and a final accuracy of 93.75% In addition, the tool was also evaluated on real-world data and discovered to be capable of identifying a range of code similarities, providing assurance that the tool can effectively differentiate authentic or original work from work that may have been plagiarized. However, the evaluation also revealed the presence of false positives and negatives, which leaves room for improvement.

Learning is deeply influenced by motivational factors, and gamification has emerged as a tool to enhance student engagement by incorporating game elements into educational settings. Despite initial positive responses, sustaining long-term intrinsic motivation remains a challenge. This research investigates the relationship between intrinsic motivation and gamified learning, employing Self-Determination Theory to guide the analysis and design construct. It aims to balance intrinsic and extrinsic motivators in designing gamified educational platforms. The study evaluates the intrinsic motivation of students using a gamified platform called Flou. Findings show that user motivation did not necessarily lead to higher levels of intrinsic motivation or engagement compared to those who did not use the application. Moreover, the implored user-centric gamified design on Intrinsic Motivators had little to no interactions among the user—with which only elements from Competence have found to have most engagements from the user, mainly attaining badges. Recommendations are made for designing balanced gamified educational experiences. The study offers insights into designing gamified platforms that enhance students' intrinsic motivation and engagement while promoting meaningful educational outcomes. The findings of the study are used to formulate recommendations towards the design of a balanced gamification to be used in an educational context. This study aims to contribute to the evolving field of gamification in education by addressing the challenge of sustaining students' motivation and promoting self-directed learning within gamified platforms.

This paper introduces an image-based Pili fruit variety classifier application for teaching biodiversity and crop science courses. For this study, the project uses Pili (Canarium ovatum, Engl.) as the pilot species in developing a non-invasive image-based classifier. The application not only provides insights into biodiversity but also showcases Al's potential in agricultural education.

Natural Language Processing (NLP), a subfield of Artificial Intelligence (Al), has gained traction in management research, particularly linguistics. However, only High-resource language is being established in NLP. This paper aims to analyze morphological patterns of Low-resource languages with limited linguistic data and resources available for NLP tasks such as Rinconada Bikol Language (RBL). This paper proposed a framework suited for RBL as the approach to developing the RBL Morphological Analyzer. This paper utilized the framework and evaluated it using Morphological Accuracy, revealing an impressive 90% accuracy in identifying correct analysis and stemming. The system's precision stands at 0.90, with a perfect recall of 1.00, resulting in an Fl score of 0.95. This high level of performance indicates the system's strong ability to recognize morphological features and patterns within the dataset effectively. The findings also reveal that the framework could also accurately analyze the morphological structure of RBL sentences.

We investigate the Incubation Effect (IE), a phenomenon by which a momentary break facilitates the generation of a solution to a problem, and its relationship with both achievement and affect of middle school students playing Physics Playground. Statistical data reports no significant improvement in the overall performance when breaks are done. Also, the success rate of solving problems after taking a break has no significant difference with the success rate of attempts without breaks. This could be attributed to the fact that the activity done during breaks is very similar to the problem-solving task, but further investigation needs to be done for validation. The results may say IE has not improved the in-game achievement of students, however, majority of IE occurrences resulted to success. This is evidence to support the positive effect of incubation. Also, a significant positive correlation was found between IE incidence and frustration.