Hybrid Knowledge-based E-Learning Resources Recommendation Methods

Recent years has witnessed substantial increase of learning resources available on the World Wide Web.As a result,there has been a remarkable growth in the utilization of online learning resources by learners in developed countries.However,despite this growth in usage of e-learning resources in developed countries,the learners in the developing countries do not take similar advantages.Many difficulties such as the retrieval of relevant learning resources are accoutered due to information overload.Recommender systems are software tools that have been largely accepted as useful solutions to alleviate the problem of information overload.They play a beneficial educational role in e-learning by assisting learners to access relevant learning resources that match their learning needs.In the context of e-learning,collaborative filtering recommendation approach recommends learning items to the target learner similar to the ones liked by other learners with similar preferences.A rating is used to measure the degree of usefulness of an item to a user.Ratings of learning resources by the learners are used to measure similarity of learners or learning resources.Content-based recommendation approach recommends learning resources to the target learner that are similar in content features to those liked by the learner in the past.Conventional recommendation methods do not incorporate additional learner information such as learner characteristics,learner context and learner's sequential access patterns in generating recommendations for the learner.Besides,conventional recommendation approaches experience the cold-start and sparsity problems,making them unreliable in e-learning scenarios.Majority of the recommendation methods currently in use still face similar challenges due to lack of incorporation of additional learner information in their recommendation processes.As such,most of the existing recommendation methods are likely to generate recommendations with lower accuracy and poor personalization to learner preferences in e-learning environments.In addition,most of the contents that are recommended to the developing countries,for example,in sub-Saharan African,are not suitable.The target learners do not have the necessary Information and Communication Technology(ICT)knowledge and equipments to access similar contents as in developed countries.This is because of regional technology is not advanced,social economic differences,cultural differences,digital divide,differences in learning interests,etc.Therefore,when recommending learning resources to the developing countries,computing analysis integrating data mining,computational models in education,and Information extraction are necessary to study ICT fluency,digital divide,and other attributes while associating the relevant results with learning resources recommendation methods.To date,recommendation approaches that incorporate additional learners' information such as the learner's region local characteristics into the recommendation process are required.The main contributions of this dissertation are summarized as follows:1.A Prediction Method for ICT Attitudes Factors based on Multiple Linear Regression: this prediction model applies computer attitude scale and proposes a prediction model based on multiple linear regression to discover the key factors affecting computer attitudes for the implementation of the ICT-based learning environment.The evaluation is performed in East African nations and the model increased the prediction optimization of the significant factors;2.Determinants of ICT Fluency and Evolution of Digital Divide: we proposed two measurement models: one is based on concentration index,and it is used to measure the evolution of the digital divide.The contribution of this model is to associate the learners' external and internal characteristics into one model which increases the optimizations of the measurements in the developing countries(especially,in East Africa and South Africa).The other model is based on logistic regression and it is used to measure the determinants of ICT fluency among students in the developing countries based on educational data mining technology.In case of measuring the factors affecting ICT fluency among the learners,this model's main role is to increase the measurements' effectiveness while considering the local context;3.A General Extended Technology Acceptance Model: this model adds more other 9 variables to the Ordinary Technology Acceptance Model(TAM)that is used to test the learners' behavioral intentions over the adoption of e-learning by measuring the learner's level of Perceived Usefulness,Attitude,Perceived Ease of Use,and Behavior Intentions towards technology.The extended model enhances the effectiveness of testing the Behavior Intentions over the adoption of technology among the learners from the developing nations,specifically,in East African countries;4.A Hybrid Knowledge-based LOs Recommendation: the two developed methods consider the above ascertainments and take into account the additional learner information such as learner characteristics,learner behavioral context,and learner's world region(especially in South-East Africa)context in recommendation process using the hybrid knowledge-based,fuzzy logic,and information extraction technologies.It increases the accuracy of the recommended e-learning resources personalization for both learners and teachers based on their ICT competences.