About me

I am a third-year PhD student in Computer Science at the University of Luxembourg. Since 2016, I have been conducting research under the supervision of Prof. Dr. Steffen Rothkugel within the COaST research group. My research interests lie in the areas of e-learning, gamification and computer-based assessment. In particular, my research focuses on the integration of learning material through digital tools in different contexts. Along my research, I have also been involved in teaching activities, including the supervision of several Bachelor and Master thesis candidates.

Publications

The following list comprises all publications I have been author or co-author of. For any full-text requests, please visit my ResearchGate profile.

Joint International Semantic Technology Conference (JIST)

Rubén Manrique, Christian Grévisse, Olga Mariño, Steffen Rothkugel

The automatic identification of core concepts addressed by a learning resource is an important task in favor of organizing content for educational purposes and for the next generation of learner support systems. We present a set of strategies for core concept identification on the basis of a semantic representation built using the open and available knowledge in the so-called Knowledge Graphs (KGs). Different unsupervised weighting strategies, as well as a supervised method that operates on the semantic representation, were implemented for core concept identification. In order to test the effectiveness of the proposed strategies, a human-expert annotated dataset of 96 learning resources extracted from MOOCs was built. In our experiments, we show the capacity of the semantic representation for the core-concept identification task as well as the superiority of the supervised method.
World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education (E-Learn)

Christian Grévisse, Rubén Manrique, Olga Mariño, Steffen Rothkugel

Learners throughout different educational levels and study domains use a significant amount of time to consult learning material. In addition to the resources given by their teachers, further information might be required by the learner. However, leaving the study context to search for related material may lead to distraction or even abandonment of the learning task. Furthermore, traditional learning resources do not foster active learning. In this paper, we present SoLeMiO, a plugin for Office applications, which identifies key concepts in a document and thereby integrates related, heterogeneous resources from an open corpus. We employ concept recognition tools to determine concepts from different domains. Thereupon, resources from different repositories are suggested to the learner and can be consulted from within the current document. Aside from traditional learning resources, active learning is fostered through gamification activities. We showcase the applicability of our approach in multiple disciplines with concrete examples.

Ontology Coverage Tool and Document Browser for Learning Material Exploration

09/2018
IEEE International Conference on Digital Information Management (ICDIM)

Christian Grévisse, Jeff Meder, Jean Botev, Steffen Rothkugel

This paper received a Best Paper Award.

Document collections in e-learning can cause issues to both learners and teachers. On one hand, inquiry from the vast corpus of available resources is non-trivial without adequate formulation support and semantic information. Implicit links between documents are hardly understood without a proper visualization. On the other hand, it is difficult for teachers to keep track of the topics covered by a large collection. In this paper, we present an ontology coverage tool and document browser for learning material exploration. Both learners and teachers can benefit from a visualization of an ontology and the documents related to the comprised concepts, overcoming the limitations of traditional file explorers. Guiding users through a visual query process, learners can quickly pinpoint relevant learning material. The visualization, which has been implemented as a web application using the D3.js JavaScript library, can be integrated into different e-learning applications to further enhance the workflow of learners. Finally, teachers are provided an overview of topic coverage within the collection.
  • Document Collection Visualization
  • Learning Material
  • Visual Query Support
  • Ontology Coverage
  • Document Browser
Colombian Conference on Computing (CCC)

Christian Grévisse, Rubén Manrique, Olga Mariño, Steffen Rothkugel

Preparing high-quality learning material is a time-intensive, yet crucial task for teachers of all educational levels. In this paper, we present SoLeMiO, a tool to recommend and integrate learning material in popular authoring software. As teachers create their learning material, SoLeMiO identifies the concepts they want to address. In order to identify relevant concepts in a reliable, automatic and unambiguous way, we employ state of the art concept recognition and entity linking tools. From the recognized concepts, we build a semantic representation by exploiting additional information from Open Knowledge Graphs through expansion and filtering strategies. These concepts and the semantic representation of the learning material support the authoring process in two ways. First, teachers will be recommended related, heterogeneous resources from an open corpus, including digital libraries, domain-specific knowledge bases, and MOOC platforms. Second, concepts are proposed for semi-automatic tagging of the newly authored learning resource, fostering its reuse in different e-learning contexts. Our approach currently supports resources in English, French, and Spanish. An evaluation of concept identification in lecture video transcripts and a user study based on the quality of tag and resource recommendations yielded promising results concerning the feasibility of our technique.
  • Learning material
  • Authoring support
  • Knowledge graph
  • Concept recognition
International Conference of Education, Research and Innovation (ICERI)

Christian Grévisse, Jean Botev, Steffen Rothkugel

The ever-growing set of learning material challenges both students and teachers. While students often need to quickly retrieve resources on a certain topic, teachers have to author high quality documents in a limited amount of time, preferably using their favourite tools. In this paper, we propose an open ecosystem of plugins for popular authoring software, enabling teachers to annotate learning resources using domain concepts from ontologies. In addition, a plugin for the Moodle Learning Management System extracts these annotations from the metadata of the provided resources to allow students to get an overview of important concepts and efficiently retrieve corresponding material.
  • Authoring plugins
  • Learning material
  • Tagging
  • Resource retrieval
  • Learning management systems
Colombian Conference on Computing (CCC)

Christian Grévisse, Jean Botev, Steffen Rothkugel

This paper received the Best Paper Award in the category Full Paper in English.

Semantic web technologies such as ontologies can foster the reusability of learning material by introducing common sets of concepts for annotation purposes. However, suggesting learning material from an open, heterogeneous corpus is a nontrivial problem. In this paper, we propose an extensible and lightweight modular ontology for programming education. Its main purpose is to integrate annotated learning material related to programming into an IDE such as Eclipse. Our ontology is based on a modular architecture, which is extensible with respect to different programming languages. Aligning language-specific concepts with user-specific tags allows us to suggest learning resources for code elements in a fine-grained and cross-curricular way. Our concrete implementation establishes relations between learning aspects in Java or C code and annotated resources such as articles on online question-and-answer sites.
  • Modular ontology
  • Programming education
  • Annotations
  • Learning material

Christian Grévisse, Jean Botev, Steffen Rothkugel

Student response systems as an active learning strategy have shown to be useful in different study domains. With the advent of gamification, these environments have become very popular to improve student engagement. However, existing solutions only provide a static set of activity types and limit their use to classrooms. In this paper, we present Yactul, an extensible game-based student response framework for active learning. Our ecosystem fosters continuous learning both in the collaborative setting of the classroom and the private study environment of the student. Our modular architecture enables a seamless integration of activities from a broad and extensible set. In addition, a mobile app for offline learning extends the experience outside the classroom and allows to replay quizzes anywhere and anytime, track the progress of an individual learner and suggest activities on topics that require more studying.
  • Student response systems
  • Gamification
  • Active learning
International Technology, Education and Development Conference (INTED)

Christian Grévisse, Jean Botev, Steffen Rothkugel

The retrieval of appropriate learning material from a heterogeneous, open corpus is a challenge in project-based learning. In addition, with the authoring of high-quality learning resources being a time-intensive task, reusability in different contexts is desirable. In this paper, we propose to move from a material-centric to a student-centric approach, integrating learning material in an advanced project-based learning support platform. Our ecosystem, relying on semantic web technologies, comprises plugins for common authoring and project realization tools.
  • Learning Material
  • Integration
  • Authoring
  • Ontology
  • Learning Support Platform
ACM Conference on User Modeling, Adaptation and Personalisation (UMAP) [Doctoral Consortium Poster]

Christian Grévisse

The growing amount of available learning material nowadays requires a significant filtering effort by students for problem solving tasks. In addition, the choice of the appropriate type of learning material differs depending on the individual learner's preferences. In this work, we suggest to move from a material-centered to a student- and task-centered approach by integrating and suggesting learning material based on the user's literacy and the context of the task to be completed. Data from social networking platforms may both enrich the available learning material and give insights on the user's preferences, to adequately match material and learner in the given context. Finally, computer-based assessment may give insights on the learner's progress and the proposed study material.
  • Adaptive learning
  • Recommender systems
  • Social media
  • 21st century literacies
  • Computer-based assessment
Congreso Argentino de Ciencias de la Computación (CACIC)

Christian Grévisse, Steffen Rothkugel

In-Vehicle Infotainment systems nowadays are largely limited to one-to-one relationships with the drivers’ mobile phone. In this paper, we propose Tumaco, a SOA-based IVI system, which enables the seamless integration of all devices of all passengers. Collaborative services can be executed within a cross-platform ecosystem through the use of semantic hypermedia. In addition, passengers may customize their own user experience in order to reduce mental workload. Our prototypical implementation showed the benefits of opening the user experience to all passengers on a car. Finally, we present a framework that enables developers to provide their own services within our ecosystem.
  • In-Vehicle Infotainment Systems
  • Collaborative Computing
  • Customization
  • Hypermedia

Towards Unlimited Mobile Application Collaboration

09/2015
Master Thesis

Jury: Steffen Rothkugel, Denis Zampunieris

This thesis was awarded the Prix Germain Dondelinger for the best Master thesis at the Faculty of Science, Technology and Communication (FSTC) in 2015.

In-Vehicle Infotainment systems are very common in today's cars, offering a mix of information and entertainment to the driver. The ubiquity of smart, mobile devices opened new possibilities of innovation to car manufacturers. However, the relationship between a car's IVI system and the driver's mobile phone is a one-to-one mapping, limiting the set of available features and data. In this thesis, we present Tumaco, a cross-platform, extensible in-vehicle infotainment ecosystem. Inspired by already existing SOA-based approaches, we extended popular mobile platforms without requiring changes to the genuine distribution. This allowed us to break the current one-to-one relationship between a driver's mobile phone and the IVI in order to seamlessly integrate all present mobile devices aboard a car. Collaboration between the IVI and mobile devices is reached through the exchange of data and the use of both local and remote services. Collaboration between services run on different platforms may be engaged within workflows. Enriched with semantic hypermedia, exchanged data is platform-independent, self-descriptive and meaningful. Furthermore, each passenger is enabled to customize his user experience. This may be done for the overall IVI layout, for specific components and for services. The first two elements can be customized due to the use of Web Components, a recent technology to create reusable UI components for web pages, which can be provided with semantically annotated data. The last point can be realised through Tumacokit, a framework we developed to enable third-party developers to integrate their apps, data and services within the Tumaco ecosystem. This way, we achieved to extend our system with further application functionality without requiring architectural modifications. The different use cases presented throughout this work have been realised in a prototypical implementation.
  • In-Vehicle Infotainment Systems
  • Collaborative Computing
  • Customization
  • Hypermedia
  • Mobile Computing
  • Ubiquitous Computing
IEEE Symposium Series on Computational Intelligence (SSCI)

Christian Grévisse, Ian Muller, Juan Luis Jimenez Laredo, Marek Ostaszewski, Grégoire Danoy, Pascal Bouvry

In molecular biology, it is estimated that there is a correlation between the secondary structure of a protein and its functionality. While secondary structure prediction is ultimately possible in wet lab, determining a correlation with the functionality is a hard task which can be facilitated by a computational model. In that context, this paper presents an automated algorithm for the visualization and classification of enzymatic proteins with the aim of examining whether the functionality is correlated to the secondary structure. To that end, up-to-date protein data was acquired from publicly accessible databases in order to construct their secondary structures. The resulting data were injected into a tailored version of a Kohonen Self-Organizing Map (SOM). Part of the work was to determine a proper way of reducing large secondary structures to a common length in order to be able to cope with the constant dimensionality requirement of SOMs. The final contribution consisted in the labeling of the trained nodes. Eventually, we were able to get a visual intuition and some quantified assessment on the nature of this correlation.
World Conference on Educational Media, Hypermedia and Telecommunications (EdMedia)

Laurent Kirsch, Christian Grévisse, Jean Botev, Steffen Rothkugel

Active learning requires practical experimentation for fully comprehending a new concept. This is hampered by current learning materials, which mostly consist of static content. The discussed operating system environment allows for the convenient integration of dynamic with static content, thus enabling materials encompassing interactive scenarios and experiments. This greatly benefits the active learner, who is not limited to playing around with the teacher’s pre-defined example set. Individual functional elements of this set can be reused in the learner’s custom scenarios, allowing for isolating the functionality involved and further inspecting its behavior. Hence, a better overall comprehension can eventually be achieved. For showcasing the wide applicability of reusable functional elements and how they support active learning, a set of interdisciplinary scenarios is discussed. The enabling architectural approach and a conceptual set of user interface elements that allow for the definition of custom experiments are also introduced.

Teaching

Programming 1 - Lab

WS 16/17, WS 17/18, WS 18/19

Introduction to (object-oriented) programming in Java.

Operating Systems 1 - Lab

WS 16/17, WS 17/18, WS 18/19

Introduction to basic Linux administration, including shell scripts.

Programming 2 - Lab

SS 16/17, SS 17/18

Programming in C and Swift.

Introduction to LaTeX

WS 16/17, WS 17/18

Tutoring session on the use of LaTeX for all first-semester Bachelor and Master students at the FSTC.

Mobile Computing - Project

SS 15/16, SS 16/17

Project on the creation of a distributed mobile game. Introduction to Swift and selected Apple frameworks.

Thesis Supervision

SS 15/16
  • Bachelor Davide Belpassi: A Game-Based Student Response Framework for Interactive Education — Offline Coaching
SS 16/17
  • Bachelor Jeff Meder: Cross-Domain Recommendations: Streaming Music Services meet Social Media
  • Master Jo Schimberg: Incorporating Learning Material and Personalised Feedback into a Serious Mobile Game
SS 17/18
  • Bachelor Sam Ries: Integration of Solfège Learning Material in a Music Notation Software
  • Master Laurent Hentges: Active Learning - Integrating Reflection and Feedback through Continuous Games
  • Master Dren Gashi: A Graph-Oriented Generic Data Model for Game-based Student Response Systems
  • Master Nicolas Mayer: Collaborative Learning Support in a Serious Mobile Game

Skills & Tools

  • Python
  • Java
  • PHP
  • Swift
  • JavaScript
  • C

Others

  • Git
  • LaTeX
  • Office Add-ins
  • Photoshop
  • Illustrator
  • InDesign

Education

  • Master in Information & Computer Sciences
    University of Luxembourg
    2013 - 2015
  • Bachelor en Informatique
    University of Luxembourg
    2010 - 2013

Languages

  • Luxembourgish (Native)
  • German
  • French
  • English
  • Spanish

Interests

  • Music
  • Airplanes
  • South America