Virtual classrooms based on the metaverse or virtual reality are useful and effective for imparting basic chemistry concepts. Interactive and immersive environments can effectively teach fundamental chemistry concepts, such as chemical bonding and formulas, thereby making these otherwise abstract and intangible ideas more accessible and understandable. With the outbreak of Covid-19, e-learning platforms have also been developed for chemistry education. However, these platforms are unable to make learning chemistry interactive and enjoyable. Therefore, there is a need to motivate students to learn basic chemistry concepts in an immersive and interactive environment. In this paper, we propose an immersive virtual reality-based Virtual Chemistry Classroom for Chemical Bonding (VC3B) to facilitate the learning of chemical bonding and formulas through a game-based learning approach. It includes two different games for learning chemical bonding and formulas. In the first game, molecule construction, students reconstruct the structure of molecules by rearranging the atoms in order to learn about chemical bonding. In the second game, chemical formula, students compose the chemical formula of a given compound to help them memorize chemical formulas. The study, conducted on 90 middle school students, employed a randomized controlled study design, dividing participants into three groups. Each group learned about chemical bonding and formulas through three different mediums. After conducting the experiment, the students were given a questionnaire to evaluate the usability of VC3B. The results of the study were positive, with participants finding the VC3B to be more interactive than traditional book and online lecture methods. Participants were also motivated to learn and enhance their knowledge of chemistry.

In science education laboratory experimentation has a vital role for students’ learning enhancement. Keeping in view the importance of modern day technologies in teaching learning process, various interactive laboratories (ISLs) have been developed to assist students in hands-on experiments in science education. In this paper we describe the potential contributions of existing interactive science laboratories (ISLs) in the major subjects of science, i.e., chemistry, biology and physics. The existing ISLs include virtual labs and simulation software where users performed their experiments. Important problems and challenges in the existing ISLs are highlighted. The systematic literature review (SLR) methodology is used for article searching, selection, and quality assessments. For this study, 86 articles after final selection using SLR are selected and classified into different categories. Each article is selected after briefly studying its different information, including category of the article, key idea, evaluation criterion, and its strengths and weaknesses. A subjective study with field experts was also conducted to investigate one of our existing virtual lab about the practical implementation and to find out the key issues in its implementation and use. Then, considering the suggestions of the subjective study, some guidelines are proposed for the improvement of future ISLs.

Education is crucial for leading a productive life and obtaining necessary resources. Higher education institutions are progressively incorporating artificial intelligence into conventional teaching methods as a result of innovations in technology. As a high academic record raises a university’s ranking and increases student career chances, predicting learning success has been a central focus in education. Both performance analysis and providing high-quality instruction are challenges faced by modern schools. Maintaining high academic standards, juggling life and academics, and adjusting to technology are problems that students must overcome. In this study, we present a comprehensive dataset, SAPEx-D (Student Academic Performance Exploration), designed to predict student performance, encompassing a wide array of personal, familial, academic, and behavioral factors. Our data collection effort at Air University, Islamabad, Pakistan, involved both online and paper questionnaires completed by students across multiple departments, ensuring diverse representation. After meticulous preprocessing to remove duplicates and entries with significant missing values, we retained 494 valid responses. The dataset includes detailed attributes such as demographic information, parental education and occupation, study habits, reading frequencies, and transportation modes. To facilitate robust analysis, we encoded ordinal attributes using label encoding and nominal attributes using one-hot encoding, expanding our dataset from 38 to 88 attributes. Feature scaling was performed to standardize the range and distribution of data, using a normalization technique. Our analysis revealed that factors such as degree major, parental education, reading frequency, and scholarship type significantly influence student performance. The machine learning models applied to this dataset, including Gradient Boosting and Random Forest, demonstrated high accuracy and robustness, underscoring the dataset’s potential for insightful academic performance prediction. In terms of model performance, Gradient Boosting achieved an accuracy of 68.7% and an F1-score of 68% for the eight-class classification task. For the three-class classification, Random Forest outperformed other models, reaching an accuracy of 80.8% and an F1-score of 78%. These findings highlight the importance of comprehensive data in understanding and predicting academic outcomes, paving the way for more personalized and effective educational strategies.