The most commonly used algorithm in recommendation systems is collaborative filtering. However, despite its wide use, the prediction accuracy of this algorithm is unexceptional. Furthermore, whether ...quantitative data such as product rating or purchase history reflect users’ actual taste is questionable. In this article, we propose a method to utilise user review data extracted with opinion mining for product recommendation systems. To evaluate the proposed method, we perform product recommendation test on Amazon product data, with and without the additional opinion mining result on Amazon purchase review data. The performances of these two variants are compared by means of precision, recall, true positive recommendation (TPR) and false positive recommendation (FPR). In this comparison, a large improvement in prediction accuracy was observed when the opinion mining data were taken into account. Based on these results, we answer two main questions: ‘Why is collaborative filtering algorithm not effective?’ and ‘Do quantitative data such as product rating or purchase history reflect users’ actual tastes?’
While modelling students’ learning behavior or preferences has been found as a crucial indicator for their course achievement, very few studies have considered it in predicting achievement of ...students in online courses. This study aims to model students’ online learning behavior and accordingly predict their course achievement. First, feature vectors are developed using their aggregated action logs during a course. Second, some of these feature vectors are quantified into three numeric values that are used to model students’ learning behavior, namely, accessing learning resources (content access), engaging with peers (engagement), and taking assessment tests (assessment). Both students’ feature vectors and behavior model constitute a comprehensive students’ learning behavioral pattern which is later used for prediction of their course achievement. Lastly, using a multiple criteria decision-making method (i.e., TOPSIS), the best classification methods were identified for courses with different sizes. Our findings revealed that the proposed generalizable approach could successfully predict students’ achievement in courses with different numbers of students and features, showing the stability of the approach. Decision Tree and AdaBoost classification methods appeared to outperform other existing methods on different datasets. Moreover, our results provide evidence that it is feasible to predict students’ course achievement with a high accuracy through modelling their learning behavior during online courses.
Video scene segmentation is very important research in the field of computer vision, because it helps in efficient storage, indexing and retrieval of videos. Achieving this kind of scene segmentation ...cannot be done by just calculating the similarity of low-level features presented in the video; high-level features should also be considered to achieve a better performance. Even though much research has been conducted on video scene segmentation, most of these studies failed to semantically segment a video into scenes. Thus, in this study, we propose a Deep-learning Semantic-based Scene-segmentation model (called DeepSSS) that considers image captioning to segment a video into scenes semantically. First, the DeepSSS performs shot boundary detection by comparing colour histograms and then employs maximum-entropy-applied keyframe extraction. Second, for semantic analysis, using image captioning that benefits from deep learning generates a semantic text description of the keyframes. Finally, by comparing and analysing the generated texts, it assembles the keyframes into a scene grouped under a semantic narrative. That said, DeepSSS considers both low- and high-level features of videos to achieve a more meaningful scene segmentation. By applying DeepSSS to data sets from MS COCO for caption generation and evaluating its semantic scene-segmentation task results with the data sets from TRECVid 2016, we demonstrate quantitatively that DeepSSS outperforms other existing scene-segmentation methods using shot boundary detection and keyframes. What’s more, the experiments were done by comparing scenes segmented by humans and scene segmented by the DeepSSS. The results verified that the DeepSSS’ segmentation resembled that of humans. This is a new kind of result that was enabled by semantic analysis, which was impossible by just using low-level features of videos.
Artificial neural networks (ANNs) have proven to be among the most important artificial intelligence (AI) techniques in educational applications, providing adaptive educational services. However, ...their educational potential is limited in practice due to challenges such as the following: (i) the difficulties in incorporating symbolic educational knowledge (e.g., causal relationships and practitioners’ knowledge) in their development, (ii) a propensity to learn and reflect biases, and (iii) a lack of interpretability. As education is classified as a ‘high-risk’ domain under recent regulatory frameworks like the EU AI Act—highlighting its influence on individual futures and discrimination risks—integrating educational insights into ANNs is essential. This ensures that AI applications adhere to essential educational restrictions and provide interpretable predictions. This research introduces NSAI, a neural-symbolic AI approach that integrates neural networks with knowledge representation and symbolic reasoning. It injects and extracts educational knowledge into and from deep neural networks to model learners’ computational thinking, aiming to enhance personalized learning and develop computational thinking skills. Our findings revealed that the NSAI approach demonstrates better generalizability compared to deep neural networks trained on both original training data and data enriched by SMOTE and autoencoder methods. More importantly, we found that, unlike traditional deep neural networks, which mainly relied on spurious correlations in their predictions, the NSAI approach prioritizes the development of robust representations that accurately capture causal relationships between inputs and outputs. This focus significantly reduces the reinforcement of biases and prevents misleading correlations in the models. Furthermore, our research showed that the NSAI approach enables the extraction of rules from the trained network, facilitating interpretation and reasoning during the path to predictions, as well as refining the initial educational knowledge. These findings imply that neural-symbolic AI not only overcomes the limitations of ANNs in education but also holds broader potential for transforming educational practices and outcomes through trustworthy and interpretable applications.
Digital game-based learning has received increased attention in education. As the key stakeholders in education, students, parents, and teachers may have different perceptions and attitudes towards ...game-based learning, which have a great impact on its adoption and dissemination. However, there is a lack of research examining how the perceptions of different stakeholders towards digital educational games may differ and influence each other. This study aimed to address the gap by investigating the perceptions of students, parents and teachers towards digital educational games, the differences and relationships between their perceptions, and possible sources of their perceptions. The study was conducted with 415 participants in China, a country that has tension between play and learning in its traditional values. The results reveal that most students, parents and teachers have certain experience playing mobile games, but with limited knowledge about educational digital games. Students have more positive perceptions towards digital educational games than teachers and parents, and the perceptions of teachers and parents are correlated with each other. After an introduction to an educational digital game, students’ and parents’ intention to recommend game-based learning increased, which, however, was not the case for teachers. Implications of the findings were discussed.
Data mining approaches have proven to be successful in improving learners' interaction with educational computer games. Despite the potential of predictive modelling in providing timely adaptive ...learning and gameplay experience, there is a lack of research on the early prediction of learners' performance in educational games. In this research, we propose an early predictive modelling approach, called GameEPM, to estimate learners' final scores in an educational game for promoting computational thinking. Specifically, the GameEPM approach models the sequence of learners' actions and then uses a limited sequence of the actions to predict the final score of the game for each learner. The findings from our initial trials show that our approach can accurately and robustly estimate the learners' performance at the early stages of the game. Using less than 50% of learners' action sequences, the cross-validated deep learning model achieves a squared correlation higher than 0.8 with a relative error of less than 8%, outperforming a range of regression models like linear regression, random forest, neural networks, and support vector machines. An additional experiment showed that the validated deep learning model can also achieve high performance while tested on an independent game dataset, showing its applicability and robustness in real-world cases. Comparing the results with traditional machine learning methods revealed that, in the validation and application phases, up to 0.30 and 0.35 R2 gain is achieved in favor of the deep learning model, respectively. Finally, we found that while the lengths of action sequences influence the predictive power of the traditional machine learning methods, this effect is not substantial in the deep learning model.
With the increasing pervasiveness of smart phones and smart devices, dialogue systems are gaining ever growing attention from both academic and industry. These systems can be broadly classified into ...two categories, one that is aimed at helping user to gain new knowledge and one that can chat with users without completing any specific tasks. Although dialogue systems are improving substantially, the user experience of such systems are still unsatisfactory as there are no specific rules covering all possible situations of real human–machine dialogue, resulting in breakdowns. There are two technical issues affecting the detection of dialogue breakdown in an open domain conversation: human resources to prepare and annotate a large chunk of conversation data and dialogue histories containing words that don’t appear directly in training data. To tackle these issues, we propose a novel encoding method for temporal utterances with memory attention based on end-to-end dialogue breakdown detection. Specifically, long short-term memory (LSTM) is employed to encode each word of all previous user and system utterances. Encoded vectors from LSTM (user and system utterances), along with system and user utterances from sentence embedding, are then stored in memory wherein an attention mechanism is applied to select the most relevant piece of words from system and user utterances for breakdown detection. An evaluation of the proposed approach on a breakdown detection task (DBDC3) showed that the model for single-labeled breakdown detection outperforms other state-of-the-art methods in a classification task. In conclusion, a more effective knowledge gain and management can be achieved by integration of our proposed breakdown detection into dialogue systems.
Neural and symbolic architectures are key techniques in AI for learner modelling, enhancing adaptive educational services. Symbolic models offer explanation and reasoning for decisions but require ...significant human effort. On the other hand, neural architectures demand less human input and yield better predictions, yet lack interpretability. Given the high-risk nature of education and that incorrectly tailored support can negatively affect learning outcomes, the integration of neural and symbolic architectures becomes crucial. This research proposes a novel neural-symbolic AI approach for temporal learner modelling, called TemporaLM, that leverages unsupervised deep neural networks (i.e., autoencoders enriched with symbolic educational knowledge) and dynamic Bayesian networks for learners’ knowledge tracing over time. The approach employs a dynamic Bayesian network for temporal knowledge tracking in learners' computational thinking and employs a knowledge-based autoencoder to enhance predictive performance through synthetic data augmentation. Our findings from both cross-validation and practical application demonstrate that the TemporaLM approach, trained on the neural-symbolic AI augmented dataset, achieves better generalizability, yielding an accuracy of 85% and an F1 score of 87%. This surpasses the dynamic Bayesian network trained solely on original and autoencoder-augmented data. Notably, by leveraging the transformed dataset for model training, improvements of up to 8% in F1 score and 5% in accuracy were achieved compared to the original dataset, observed in both cross-validation and application stages. The augmented prediction capabilities, coupled with interpretable knowledge tracing, cultivate trust among educators and learners in data-driven decisions. These findings underline the potential of neural-symbolic family of AI to improve limitation of existing (symbolic) AI methods in education, advancing AI's potential in education and enabling trustworthy and interpretable applications.
Predictive learner modelling is crucial for personalized education. While convolutional neural networks (CNNs) have shown great success in education, their potential in learner modelling via image ...data is unexplored. This research introduces a novel and interpretable approach for Image-based Learner Modelling (ImageLM) using CNNs and transfer learning to model learners’ performance and accordingly classify their computational thinking solutions. The approach integrates Grad-CAM, enabling it to provide insights into its decision-making process. Findings show that our custom CNN outperforms other models (namely ResNet, VGG, and Inception), with 83% accuracy in predicting solution correctness. More importantly, the ImageLM approach identifies the regions that contribute the most to the predictions, shedding light on learners' computational thinking knowledge and advancing toward trustworthy AI for education. These results underline the potential of utilizing imagery data from learners’ activities during the learning process to predict their performance, especially in challenging environments like programming where traditional feature extraction and learning might struggle.