Mihaela Cocea

Log file analysis for disengagement detection in e-Learning environments

Most e-Learning systems store data about the learner’s actions in log files, which give us detailed information about learner behaviour. Data mining and machine learning techniques can give meaning to these data and provide valuable information for learning improvement. One area that is of particular importance in the design of e-Learning systems is learner motivation as it is a key factor in the quality of learning and in the prevention of attrition. One aspect of motivation is engagement, a necessary condition for effective learning. Using data mining techniques for log file analysis, our research investigates the possibility of predicting users’ level of engagement, with a focus on disengaged learners. As demonstrated previously across two different e-Learning systems, HTML-Tutor and iHelp, disengagement can be predicted by monitoring the learners’ actions (e.g. reading pages and taking test/quizzes). In this paper we present the findings of three studies that refine this prediction approach. Results from the first study show that two additional reading speed attributes can increase the accuracy of prediction. The second study suggests that distinguishing between two different patterns of disengagement (spending a long time on a page/test and browsing quickly through pages/tests) may improve prediction in some cases. The third study demonstrates the influence of exploratory behaviour on prediction, as most users at the first login familiarize themselves with the system before starting to learn.

Cross-system validation of engagement prediction from log files

Engagement is an important aspect of effective learning. Time spent using an e-Learning system is not quality time if the learner is not engaged. Tracking the student disengagement would give the possibility to intervene for motivating the learner at appropriate time. In previous research we showed the possibility to predict engagement from log files using a web-based e-Learning system. In this paper we present the results obtained from another web-based system and compare them to the previous ones. The similarity of results across systems demonstrates that our approach is system-independent and that engagement can be elicited from basic information logged by most e-Learning systems: number of pages read, time spent reading pages, number of tests/ quizzes and time spent on test/ quizzes.

Eliciting Motivation Knowledge from Log Files Towards Motivation Diagnosis for Adaptive Systems

Motivation is well-known for its importance in learning and its influence on cognitive processes. Adaptive systems would greatly benefit from having a user model of the learners motivation, especially if integrated with information about knowledge. In this paper a log file analysis for eliciting motivation knowledge is presented, as a first step towards a user model for motivation. Several data mining techniques are used in order to find the best method and the best indicators for disengagement prediction. Results show a very good level of prediction: around 87% correctly predicted instances of all three levels of engagement and 93% correctly predicted instances of disengagement. Data sets with reduced attribute sets show similar results, indicating that engagement level can be predicted from information like reading pages and taking tests, which are common to most e-Learning systems.

Rule Based Systems for Big Data: A Machine Learning Approach

The ideas introduced in this book explore the relationships among rule based systems, machine learning and big data. Rule based systems are seen as a special type of expert systems, which can be built by using expert knowledge or learning from real data. The book focuses on the development and evaluation of rule based systems in terms of accuracy, efficiency and interpretability. In particular, a unified framework for building rule based systems, which consists of the operations of rule generation, rule simplification and rule representation, is presented. Each of these operations is detailed using specific methods or techniques. In addition, this book also presents some ensemble learning frameworks for building ensemble rule based systems.

Assessment of motivation in online learning environments

This research outline refers to the assessment of motivation in online learning environments. It includes a presentation of previous approaches, most of them based on Keller’s ARCS model, and argues for an approach based on Social Cognitive Learning Theory, in particular building on self-efficacy and self-regulation concepts. The research plan includes two steps: first, detect the learners in danger of dropping-out based on their interaction with the system; second, create a model of the learner’s motivation (including self-efficacy, self-regulation, goal orientation, attribution and perceived task characteristics) upon which intervention can be done.

Learning Sentiment from Students’ Feedback for Real-Time Interventions in Classrooms

Knowledge about users sentiments can be used for a variety of adaptation purposes. In the case of teaching, knowledge about students sentiments can be used to address problems like confusion and boredom which affect students engagement. For this purpose, we looked at several methods that could be used for learning sentiment from students feedback. Thus, Naive Bayes, Complement Naive Bayes (CNB), Maximum Entropy and Support Vector Machine (SVM) were trained using real students’ feedback. Two classifiers stand out as better at learning sentiment, with SVM resulting in the highest accuracy at 94%, followed by CNB at 84%. We also experimented with the use of the neutral class and the results indicated that, generally, classifiers perform better when the neutral class is excluded.

Rule based networks: an efficient and interpretable representation of computational models

Abstract Due to the vast and rapid increase in the size of data, data mining has been an increasingly important tool for the purpose of knowledge discovery to prevent the presence of rich data but poor knowledge. In this context, machine learning can be seen as a powerful approach to achieve intelligent data mining. In practice, machine learning is also an intelligent approach for predictive modelling. Rule learning methods, a special type of machine learning methods, can be used to build a rule based system as a special type of expert systems for both knowledge discovery and predictive modelling. A rule based system may be represented through different structures. The techniques for representing rules are known as rule representation, which is significant for knowledge discovery in relation to the interpretability of the model, as well as for predictive modelling with regard to efficiency in predicting unseen instances. This paper justifies the significance of rule representation and presents several existing representation techniques. Two types of novel networked topologies for rule representation are developed against existing techniques. This paper also includes complexity analysis of the networked topologies in order to show their advantages comparing with the existing techniques in terms of model interpretability and computational efficiency.

Interpretability of computational models for sentiment analysis

Sentiment analysis, which is also known as opinion mining, has been an increasingly popular research area focusing on sentiment classification/regression. In many studies, computational models have been considered as effective and efficient tools for sentiment analysis . Computational models could be built by using expert knowledge or learning from data. From this viewpoint, the design of computational models could be categorized into expert based design and data based design. Due to the vast and rapid increase in data, the latter approach of design has become increasingly more popular for building computational models. A data based design typically follows machine learning approaches, each of which involves a particular strategy of learning. Therefore, the resulting computational models are usually represented in different forms. For example, neural network learning results in models in the form of multi-layer perceptron network whereas decision tree learning results in a rule set in the form of decision tree. On the basis of above description, interpretability has become a main problem that arises with computational models. This chapter explores the significance of interpretability for computational models as well as analyzes the factors that impact on interpretability. This chapter also introduces several ways to evaluate and improve the interpretability for computational models which are used as sentiment analysis systems. In particular, rule based systems , a special type of computational models, are used as an example for illustration with respects to evaluation and improvements through the use of computational intelligence methodologies.

Automatic Content Related Feedback for MOOCs Based on Course Domain Ontology

MOOCs offer free access to educational materials, leading to large numbers of students registered in MOOCs courses. The MOOCs forums allow students to post comments and ask questions; due to the number of students, however, the course facilitators are not able to provide feedback in a timely manner. To address this problem, we identify content-knowledge related posts using a course domain ontology and provide students with timely informative automatic feedback. Moreover, we provide facilitators with feedback of students posts, such as frequent topics students ask about. Experimental results from one of the courses offered by Coursera show the potential of our approach in creating a responsive learning environment.

Network based rule representation for knowledge discovery and predictive modelling

Due to the vast and rapid increase in data, data mining has been an increasingly important tool for the purpose of knowledge discovery to prevent the presence of rich data but poor knowledge. In this context, machine learning can be seen as a powerful approach to achieve intelligent data mining. In practice, machine learning is also an intelligent approach for predictive modelling. A special type of machine learning methods, which are known as rule based methods such as decision trees, can be used to build a rule based system as a special type of expert systems for both knowledge discovery and predictive modelling. A rule based system may be represented through different structures. The techniques for representing rules are known as rule representation, which is significant for knowledge discovery in relation to the interpretability of the model, as well as for predictive modelling with regard to efficiency in predicting unseen instances. This paper justifies the significance of rule representation. Some networked topologies for rule representation are introduced against existing techniques. The network topologies are validated using complexity analysis in order to show their advantages comparing with the existing techniques in terms of model interpretability and computational efficiency.