No abstract

Massive Open Online Courses (MOOCs) are increasingly used by learn-ers to acquire knowledge and develop new skills. MOOCs provide a trove of data that can be leveraged to better assist learners, including behavioral data from built-in collaborative tools such as discussion boards and course wikis. Data tracing social interactions among learners are especially inter-esting as their analyses help improve MOOCs’ effectiveness. We particular-ly perform sentiment analysis on such data to predict learners at risk of dropping out, measure the success of the MOOC, and personalize the MOOC according to a learner’s behavior and detected emotions. In this pa-per, we propose a novel approach to sentiment analysis that combines the advantages of the deep learning architectures CNN and LSTM. To avoid highly uncertain predictions, we utilize a Bayesian neural network (BNN) model to quantify uncertainty within the sentiment analysis task. Our em-pirical results indicate that: 1) The Bayesian CNN-LSTM model provides interesting performance compared to other models (CNN-LSTM, CNN, LSTM) in terms of accuracy, precision, recall, and F1-Score; and 2) there is a high correlation between the sentiment in forum posts and the dropout rate in MOOCs.

No abstract

<p>Nowadays, there is a huge production of Massive Open Online Courses MOOCs from universities around the world. The enrolled learners in MOOCs skyrocketed along with the number of the offered online courses. Of late, several universities scrambled to integrate MOOCs in their learning strategy. However, the majority of the universities are facing two major issues: firstly, because of the heterogeneity of the platforms used (e-learning and MOOC platforms), they are unable to establish a communication between the formal and non-formal system; secondly, they are incapable to exploit the feedbacks of the learners in a non-formal learning to personalize the learning according to the learner’s profile. Indeed, the educational platforms contain an extremely large number of data that are stored in different formats and in different places. In order to have an overview of all data related to their students from various educational heterogeneous platforms, the collection and integration of these heterogeneous data in a formal consolidated system is needed. The principal core of this system is the integration layer which is the purpose of this paper. In this paper, a semantic integration system is proposed. It allows us to extract, map and integrate data from heterogeneous learning platforms “MOOCs platforms, elearning platforms” by solving all semantic conflicts existing between these sources. Besides, we use different learning algorithms (Long short-term memory LSTM, Conditional Random Field CRF) to learn and recognize the mapping between data source and domain ontology.</p>

No abstract