Improving M-Learners’ Performance Through Deep Learning Techniques by Leveraging Features Weights

Abstract

Mobile learning (M-learning) has gained tremendous attention in the educational environment in the past decade. For effective M-learning, it is important to create an efficient M-learning model that can identify the exact requirements of mobile learners (M-learners). M-learning model is composed of features that are generated during M-learners' interaction with mobile devices. For an adaptive M-learning model, not only learning features are required, but it is also important to determine how they differ for various M-learners, their weights, and interrelationship. This study proposes a robust and adaptive Mlearning model that is based on machine learning and deep learning (ML/DL) techniques. The proposed M-learning model dynamically explores learning features, their corresponding weights, and association for M-learners. Based on learning features, the M-learning model categorizes M-learners into different performance groups. The M-learning model then provides adaptive content, suggestions, and recommendations to M-learners in order to make learning adaptive and stimulating. For comparative analysis, the prediction accuracy of five baseline ML models was compared with the deep Artificial Neural Network (deep ANN). The results demonstrated that deep ANN and Random Forest (RF) models exhibited better prediction accuracy. Subsequently, both models were selected for developing the M-learning model which included the performance categorization of M-learners under a five-level classification scheme and assigning weights to various features for providing adaptive help and support to M-learners. Our explanatory analysis has shown that behavioral features besides contextual features also influence the learning performance of M-learners. As a direct outcome of this research, more efficient, interactive, and useful mobile learning applications can be developed that accurately predict learning objectives and requirements of diverse Mlearners thus helping M-learners in enhancing their study behavior.

Behavioral Involvement, Technology Acceptance, and Failure in Mobile Learning: A Systematic Review

“…As stated in Ref. (Adnan, Habib, Ashraf, Shah, et al, 2020), deep ANN and RF models were utilized to improve M-learners' performance, demonstrating the best performance over five baseline models. In the manuscript (Zhao, 2022), intelligent reinforcement learning technology was leveraged, achieving an accuracy rate of 98.78% when compared to traditional Q-learning mechanisms.…”

“…In this work (Liao, 2022), an AI-powered English learning mobile app's importance of trust factors that determine service reliability, influenced by machine learning, achieving 97.24% convergence speed was demonstrated. In (Adnan, Habib, Ashraf, Shah, et al, 2020), the role of behavioral and contextual features in influencing learning performance, showcasing robust modeling through deep ANN and RF models was emphasized. In the following manuscript (Akour et al, 2021), machine learning algorithms were employed to predict intentions to use mobile learning platforms, with the J48 classifier showing superior performance.…”

“…Recent studies in the field of Mobile Learning are increasingly exploring machine learning algorithms to predict failure in learning, focusing on both engagement and technology acceptance (Tan et al, 2014), (Padhy et al, 2018), and (Adnan et al, 2019). Diverse sources of data, such as MOODLE platforms and student data are used to implement these predictive models (Adnan, Habib, Ashraf, Shah, et al, 2020), (Moslehi & Haeri, 2020). Key influential factors like trust, attitude, and quality of technology have been identified as crucial in leveraging machine learning algorithms (Tan et al, 2014), (Adnan, Habib, Ashraf, Mussadiq, et al, 2020), and (Akour et al, 2021).…”

Semantic Orientation of Crosslingual Sentiments: Employment of Lexicon and Dictionaries

“…Figure 3, 4, 5 presents it clearly that the outcomes of HF-CSA are better in comparison with baseline systems over informal, anglicized and Crosslingual contents. Existing Literature of deep learning methods, Urdu transliterations systems [41], [42], [43], [44], [45], [46], [47], [48] and experimental setup revealed that unsupervised lexicon based systems generate satisfactory outcomes for standard, formal, informal as well as multilingual text of resource poor languages.…”

Memory Load and Performance-based Adaptive Smartphone E-learning Framework for E-commerce Applications in Online Learning

“…Recently, many educational institutions have started integrating and using Massive Open Online Courses (MOOCs) to support traditional classroom procedures. Many MOOC platforms provide the facility to instructors to create their own Small Private Online Courses (SPOC) to support them in providing distance-learning education [22][23]. However, despite supporting a large volume of data and students, these platforms are limited in creating certain online classes with no collaboration among students.…”