International audience

International audience

Nowadays, Learning Management Systems (LMS) play an intrinsic role in education. They gather traces about the learner (course view, wiki view, quiz attempt, etc.) in event logs. These logs offer the opportunity to provide dashboards and analysis on learners. There are several techniques that analyze event logs for different purposes (adaptation, recommendation, performance detection, etc.). Within this framework, our central focus is upon Educational Process Mining technique which generates process models for improving learning resource recommendation. We set forward an architecture leading to discover process models and recommend to the learner not only learning resource but also process models, each of which is relative to a specific learning resource. These models exert a certain influence on the result of learning resource recommendation. One of the reason that endows our work with an original aspect is that it automatically analyses event logs based on multi-features extracted from the learner’s profiles. However, the state of the art works require a manual analysis step based on learning results uniquely. We evaluated the discovered process models grounded on the event logs of Moodle LMS. These event logs contain 42,438 traces of 100 students who learned a course over one semester. Results corroborate the good performance of our work.

Nowadays, special attention is directed to trust issues in the Decentralized Online Social Network (DOSN). In a distributed system for social networking, interactions and collaborations can be unreliable because some users resort to malicious behaviors in order to increase their trust values in the network to be chosen later by others, and launch trust-related attacks. In this unreliable situation, users will not be able to estimate the trustworthiness of the received social services’ list of recommendations. Hence, a trust management model becomes a necessity in order to overcome its trust-related attacks and to recommend trustworthy social services. In this respect, we propose a new trust management model that helps prevent trust-related attacks in order to ensure a reliable environment. Towards this end, our suggested model implements a new technology, called blockchain. Based on the studied trust-related attacks, we intend to add logical security to blockchain since this technology takes into account only the physical security. Evaluation values show the effectiveness of our model.

Abstract Events represent a tipping point that affects users’ opinions and vary depending upon their popularity from local to international. Indeed, social media offer users platforms to express their opinions and commitments to events that attract them. However, owing to the volume of data, users are encountering a difficulty to accede to the preferred events according to their features that are stored in their social network profiles. To surmount this limitation, multiple event recommendation systems appeared. Nevertheless, these systems use a limited number of event dimensions and user’s features. Besides, they consider users’ features stored in a single user’s profile and disregard the semantic concept. In this research, an approach for multi-dimensional event recommendation is set forward to recommend events to users resting on several event dimensions (engagement, location, topic, time and popularity) and some user’s features (demographic data, position and user’s/friend’s interests) stored in multi-user’s profiles by considering the semantic relationships between user’s features, specifically user’s interests. The performance of our approach was assessed using error rate measurements (mean absolute error, root mean squared error and cross-validation). Experiment that results on real-world event data sets confirmed that our approach recommends events that fit the user more than the previous approaches with the lowest error rate values.

With the immense growth of online social applications, trust plays a more and more important role in connecting users to each other, sharing their personal information and attracting him to receive recommendations. Therefore, how to obtain trust relationships through mining online social networks became a critical issue. To calculate the level of trust between two users, many computational trust models are proposed which mainly rely on the social network structure, the explicit trust from user to another, the users' behaviors, or the users' similarity, etc. However, the majority of these models ignored the temporal factor. In this paper, we propose a trust relationship detection mechanism from an egocentric social network in order to compute the trust level between an active user and his directed friends. We propose a Level of social Trust model, that we called LoTrust, which is suitable for personalized recommendation purpose. This computational model founded on novel trust metric which is based not only on the users' interests similarity according to their semantic social profiles (RDF/FOAF), but also takes into account the time factor of the users' active interactions (e.g comments, share photo, wall posts, messages). We perform experiments on real life dataset extracted from Facebook. The experimental results demonstrated how our LoTrust model produces satisfactory results than other computational models.

Generally, many adaptive systems are developed and used in various fields. The effort to build the user's profile is repeated from one system to another due to the lack of interoperability and synchronization. Therefore, to provide an effective interoperability is a complex challenge due to the evolution of the user's profiles and its heterogeneity. The user's profiles evolution is not taken into account in the interoperable system. In our work, we are interested in the educational field. In this context, we propose a novel interoperable architecture allowing the exchange of the learner's profile information between different adaptive educational cross-systems to provide an access corresponding to the learners' needs. This architecture is automatically adapted to the learner's profiles that evolve over time and are syntactically, semantically and structurally heterogeneous. An experimental study shows the effectiveness of our architecture.

The adaptive educational systems include several solutions for providing personalized access to the learning process. The learner's profile constitutes the key element of these solutions. Therefore, an educational system represents the learner's profile by its own syntax, semantic and structure. Each system can have incomplete or partial learner's data. As a consequence, there is a strong need to exchange the learner's profiles between different systems to enhance and enrich the learner's knowledge. However, the data exchange between the learner's profiles implies interoperability problems. In our work, we are interested in the evolving learner's profiles interoperability problem. In this context, we propose an architecture allowing the data exchange of the learner's profile in educational cross-systems in order to improve the adaptation navigation. This architecture is automatically adapted to the learner's profiles that evolve over time. These latter are syntactically, semantically and structurally heterogeneous. The evaluation values show the effectiveness of our approach.

The access to heterogeneous data through their metadata needs a matching process of the metadata schemas. This process identifies the correspondence relations called “Mappings” between the schemas to identify a global schema. This latter allows a uniform access to heterogeneous data. In this context, several works are proposed. However, the obtained mappings and the global schema are identified regardless of the user's profile. Thus, the queries results are the same for any user despite the various profiles. In this paper, we present a matching process that (i) deals with the metadata schema heterogeneities and (ii) considers the users’ profile.

In a social context, the user is more and more an active contributor for producing social information. Then, he needs a tailored information reflecting his current needs and interests in every period of time. This aims to provide a better adaptation while accessing the information space by integrating users' interests dynamic. Indeed, users' interests may change and become “outdated” through time. So, an interest judged as relevant in a period of time may fluctuate in the next period of time. Moreover, analysing the classic user behaviour to deduce his current interests is a difficult task. In fact, his behaviour isn't always reflecting his real interests. In this paper, we propose a new approach for enriching the user profile in an evolutionary environment such as a social network. The enrichment takes into account: i) the social behaviour and more precisely the tagging behaviour (that reflects user's interests) and ii) the temporal information (that reflects the dynamic evolution of users' interests). Our approach focus on the concept of temperature that reflects the importance of a resource in each period of time. This concept is used to infer common interests of users tagging the same “important” resource. The originality of our approach relies on combining information tags, users and resources in a way that guarantees a better enrichment for the social user profile. Our approach has been tested and evaluated with the Delicious social database and shows interesting precision values.

Several systems such as adaptive systems, etc. provide responses to the user by taking into account, among other, his profile. After each user-system interaction, new information should be added to the user profile content. By the time and after several updating operations, the profile can become overloaded and the removal of irrelevant content is necessary. In this paper, we tackle the profile overloading problem. We propose a new method based on co-training algorithm for detecting and removing irrelevant elements. Our method is automatically adapted to the content of any profile and allows us to obtain the most generic classifier to each one. An experimental study by qualitative and comparative evaluations shows that the proposed method can detect and remove irrelevant profile content effectively.