Phone: +41 26 429 65 97
Commitee member of the HES-SO CCN (Center for Digital Competences)
Role: Main Applicant
Smart Living Lab
Description du projet :
Le confort au travail est un enjeu qui implique les employé.e.s et la direction de l’entreprise. Pour faciliter l’implémentation de mesures préventives et correctives des problèmes et vérifier leur effet, SpotOn vise à fournir un système de gestion du confort au sein d’une entreprise (diagnostic et espace de communication), basé sur une analyse multidimensionnelle du confort ressenti, et adaptée aux besoins spécifiques de son contexte d’utilisation.
Research team within HES-SO:
, Radu Florinel
, Chabbi Houda
, Jan Nicole
Durée du projet:
Des études récentes ont mis en évidence le besoin accru des commerces de proximité en matière d’expériences d’achat personnalisées. En même temps, la situation sanitaire incite les commerces à utiliser la technologie pour faciliter l’expérience d’achat à distance. Aujourd'hui plus que jamais, avec la crise sanitaire COVID-19, la société exploite les outils de téléprésence pour maintenir la connectivité, tant au niveau professionnel que personnel. A la différence des applications traditionnelles d’e-commerce proposant des produits commandables par internet, le projet collaboratif « Flower Cam » cherche à personnaliser et intégrer l’expérience d’achat à distance dans l’environnement de vente. Le but est de ramener le client connecté virtuellement à distance au lieu du commerce, et de lui permettre de suivre et interagir avec le vendeur et l’environnement, par le biais d’un agent robotique de téléprésence. Ainsi, le client pourra bénéficier de conseils d’achat personnalisés, avec une flexibilité horaire et géographique.
Research team within HES-SO:
, Noth Léonard Nikita
, Iseli Yael
Partenaires professionnels: Chantal Robin, CCIF; Adrien Hertig, Hertigfleurs; Frédéric Kolly, Meubles Kolly; Fabienne Ottiger, Bull'shop
Durée du projet:
Url of the project site:
Le but de ce projet et de co-concevoir et développer une application ouverte, de type serious game qui se déclinerait sous plusieurs formes (desktop et réalité virtuelle) pour répondre aux différents besoins des thérapies utilisées de manière ciblée. La co-conception se faisant avec des partenaires théfrapeutes afin de répondre précisement à leur demande. Cette application doit avoir la caractéristique d’être intuitive à utiliser et configurable pour permettre son adéquation à différents niveaux d’utilisation.
La première déclinaison que nous envisageons sera dédiée aux patients « addicts » à l’alcool. Cette déclinaison pourra par exemple être facilement adaptée par la suite aux personnes « addicts » à la cigarette et à d’autres formes d’addiction.
Research team within HES-SO:
, Ingram Sandy
This project aims at developing a unified user-centered recommendation framework and proof-of-concept based on deep reinforcement learning, specifically tailored to aggregated social streams and news recommendation, and able to simultaneously: (1) target long-term user satisfaction, (2) automatically update recommendations based on online user feedback (3) improve the target user’s well-being and time spent passively « scrolling » online, by injecting into the social news feed, the « right » type and « amount » of micro-learning information bits at the « right » intervals, based on learned user interests and feedback.
Research team within HES-SO:
, Ingram Sandy
Durée du projet:
01.09.2020 - 01.09.2022
This project broadens the scope of the current strategic Swiss and European initiatives on open digital education, to the emerging and also strategic Swiss and European initiatives on open science and especially open data, strengthening as such the international leadership of Switzerland in these areas. Targeted research communities include not only education, digital education, and human computer interaction, but also information systems and knowledge management.
Research team within HES-SO:
, Nwachukwu Uchendu
Partenaires académiques: Gillet Denis, VD - EPFL - REACT Group; Arnaud Legourriérec, HEP Bejune; Boechat-Heer Stéphanie, HEP Bejune
Durée du projet:
01.02.2021 - 30.06.2022
Smart Living Labs
L'apparition de nouveaux types d'environnement de travail cherchant à la fois la satisfaction des usagers et l'accord avec des types de travail spécifiques à l'organisation des entreprises demande une compréhension systémique du confort de l'usager dans les bureaux. Le projet Multi-Confort répond à cet enjeu en prenant en compte les trois composantes du confort (physiologique, psychologique et fonctionnel) et en cherchant les corrélations entre les facteurs ambiants, les types (routines) de travail, l'occupation effective et l'usage des équipements.
Research team within HES-SO:
, Bacher Jean-Philippe
, Ingram Sandy
, Iseli Yael
, Nwachukwu Uchendu
, Spoto Martin
Durée du projet:
01.09.2011 - 31.12.2020
Requérant(e)s: Masset Philippe, VD- EHL
HES-SO - Projet Innovation Pédagogique
La «Gamification des apprentissages» (GA) repre'sente une approche théoriquement idéale pour enrichir les expériences d'apprentissages des étudiants. Mais, en pratique, elle reste peu employée du fait de la nature souvent technologique, peu flexible et dispendieuse de ses applications. Ce projet a pour objectif d'élaborer un guide des bonnes pratiques complémenté par un ensemble d'exemples commentés. Ainsi les enseignants pourront aisément s'approprier la démarche GA, ce qui permettra de renforcer l'acquisition des compétences pour les étudiants.
Philippe Masset, VD- EHL; Ingram Sandy, FR - EIA - Institut iSIS; Truchot-Cardot Dominique, Institut et Haute Ecole de Santé La Source; Andrianantenaina Miharisoa, FR - EIA - Institut iSIS
Research team within HES-SO:
, Andrianantenaina Miharisoa Hanitrarivony
, Iseli Yael
, Islambouli Rania
Partenaires académiques: Masset Philippe, VD- EHL; Truchot-Cardot Dominique, Institut et Haute Ecole de Santé La Source; WeissKopf Jean-Philippe, VD- EHL
Durée du projet:
01.03.2019 - 31.12.2020
InnoSuisse (Innovation Check)
By 2018, 40% of B2B digital commerce sites will dynamically configure product pricing using price optimization algorithms. Adapting product prices dynamically as demand, transportation pathway costs, and predicted product success fluctuates over time, contributes to increasing revenue margin. Considering the increasing demand for dynamic price optimization algorithms, OrchardAi aims at developing a global, business-agnostic yet customisable framework for dynamic price optimization. Preliminary research initiated by OrchardAi shed light on the use of reinforcement learning for dynamic price optimization.
Results: A proof of concept of the reinforcement learning approach proposed, was implemented and packaged as a library. The proof of concept used dynamic programming to find the optimal the commission at each time period based on expected cumulative reward. A web-based parametrisable simulation tool was also provided to allow OrchardAi to experiment with the proof of concept and data provided.
Research team within HES-SO:
, Goetschi Damien
Partenaires professionnels: Hamilton-Smith Robert, OrchardAI
Durée du projet:
Ingram Sandy, Nwachukwu Uchendu, Jan Nicole, Bacher Jean-Philippe, Radu Florinel
Lecture Notes in Computer Science Proceedings of HCI-2021: International Conference on Human-Computer Interaction Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. Human Body, Motion and Behavior, 19-24 July 2020, Copenhagen, Denmark, 2021
Link to the publication
This paper presents a novel approach for assessing comfort at the workplace, resulting from an interdisciplinary work between researchers in hman-computer interaction, architecture, social sciences, smart buildings and energy management. A systemic comfort elicitation model including but not limited to thermal comfort, is suggested. A proof-of-concept prototype application developed based on the proposed model is also presented. The results of a first evaluation of the application's acceptability in a real working environment are discussed.
Mael Guillemot, Jean-Marc Odobez, Alessandro Vinciarelli, Ingram Sandy
IEEE MultiMedia, 2015 , vol.
The main motivations behind the webcasting company, Klewel, were to go beyond text-based conference proceedings to offer a user-friendly way to browse and replay presentations, access slides, and search for specific information within a recording. As the project got under way, the team came together, and eventually an innovative webcasting solution saw the light of day. Learn how the company moved from research to technology by focusing on multidisciplinary research, early real-world prototyping and testing, collaboration, and client needs.
Chidansh Amitkumar Bhatt, Popescu-Belis Andrei, Maryam Habibi, Ingram Sandy, Stefano Masneri, Fergus McInnes, Nikolaos Pappas, Oliver Schreer
Proceedings of the 21st ACM international conference on Multimedia, 2013 , pp.
This paper presents the MUST-VIS system for the MediaMixer/VideoLectures .NET Temporal Segmentation and Annotation Grand Challenge. The system allows users to visualize a lecture as a series of segments represented by keyword clouds, with relations to other similar lectures and segments. Segmentation is performed using a multi-factor algorithm which takes advantage of the audio (through automatic speech recognition and word-based segmentation) and video (through the detection of actions such as writing on the blackboard). The similarity across segments and lectures is computed using a content-based recommendation algorithm. Overall, the graph-based representation of segment similarity appears to be a promising and cost-effective approach to navigating lecture databases.
Yao Lu, Ingram Sandy, Denis Gillet
Proceedings of the 22nd International Conference on World Wide Web, 2013 , pp.
In this paper, a hybrid recommender system for job seeking and recruiting websites is presented. The various interaction features designed on the website help the users organize the resources they need as well as express their interest. The hybrid recommender system exploits the job and user profiles and the actions undertaken by users in order to generate personalized recommendations of candidates and jobs. The data collected from the website is modeled using a directed, weighted, and multi-relational graph, and the 3A ranking algorithm is exploited to rank items according to their relevance to the target user. A preliminary evaluation is conducted based on simulated data and production data from a job hunting website in Switzerland.
Ingram Sandy, Hervé Bourlard, Marc Ferras, Nikolaos Pappas, Popescu-Belis Andrei, Steve Renals, Fergus McInnes, Peter J Bell, Maël Guillemot
First Workshop on Speech, Language and Audio in Multimedia, 2013
In the inEvent EU project, we aim at structuring, retrieving, and sharing large archives of networked, and dynamically changing, multimedia recordings, mainly consisting of meetings, videoconferences, and lectures. More specifically, we are developing an integrated system that performs audiovisual processing of multimedia recordings, and labels them in terms of interconnected “hyper-events”(a notion inspired from hyper-texts). Each hyper-event is composed of simpler facets, including audio-video recordings and metadata, which are then easier to search, retrieve and share. In the present paper, we mainly cover the audio processing aspects of the system, including speech recognition, speaker diarization and linking (across recordings), the use of these features for hyper-event indexing and recommendation, and the search portal.
Proceeding of The Fourth International Conferences on Pervasive Patterns and Applications, 2012 , pp.
Zhou Lei, Ingram Sandy, Laurent Moccozet, Laurent Opprecht, Omar Benkacem, Christophe Salzmann, Denis Gillet
International Conference on Web-Based Learning, 2012 , vol.
Springer, Berlin, Heidelberg
From e-commerce to social networking sites, recommender systems are gaining more and more interest. They provide connections, news, resources, or products of interest. This paper presents a federated recommender system, which exploits data from different online learning platforms and delivers personalized recommendation. The underlying educational objective is to enable academic institutions to provide a Web 2.0 dashboard bringing together open resources from the Cloud and proprietary content from in-house learning management systems. The paper describes the main aspects of the federated recommender system, including its adopted architecture, the common data model used to harvest the different learning platforms, the recommendation algorithm, as well as the recommendation display widget.
Evgeny Bogdanov, Ingram Sandy, Freddy Limpens, Na Li, Christophe Salzmann, Denis Gillet
Proceedings of the 2012 IEEE Global Engineering Education Conference (EDUCON), 2012 , pp.
This paper reports on the successful use of Graasp, a social media platform, by university students for their collaborative work. Graasp features a number of innovations, such as administrator-free creation of collaborative spaces, a context-aware recommendation and privacy management. In the context of a EU-funded project involving large test beds, we have been able to extend this platform with lightweight tools (widgets) aimed for learning and competence development and to validate its usefulness in a collaborative learning context.
Sten Govaerts, Ingram Sandy, Eric Duval, Denis Gillet
Proceedings of the 2nd International Workshop on Social Recommender Systems (SRS 2011) in conjunction with the 2011 ACM Conference on Computer Supported Cooperative Work (CSCW 2011), 2011 , pp.
This paper presents a federated search and social recommen-dation widget. It describes the widget’s interface and the un-derlying social recommendation engine. A preliminary eval-uation of the widget’s usability and usefulness involving 15 subjects is also discussed. The evaluation helped identify us-ability problems that will be addressed prior to the widget’s usage in a real learning context.
Felix Modritscher, Barbara Krumay, Ingram Sandy, Denis Gillet, Alexander Nussbaumer, Albert Dietrich, Ingo Dahn, Carsten Ullrich
Digital Education Review, 2011 , vol.
Personal learning environment (PLE) solutions aim at empowering learners to design (ICT and web-based) environments for their learning activities, mashingup content and people and apps for different learning contexts. Widely used in other application areas, recommender systems can be very useful for supporting learners in their PLE-based activities, to help discover relevant content, peers sharing similar learning interests or experts on a specific topic. In this paper we examine the utilization of recommender technology for PLEs. However, being confronted by a variety of educational contexts we present three strategies for providing PLE recommendations to learners. Consequently, we compare these recommender strategies by discussing their strengths and weaknesses in general.
Evgeny Bogdanov, Ingram Sandy, Stéphane Sire, Christophe Salzmann, Denis Gillet
CHI'10 Extended Abstracts on Human Factors in Computing Systems, 2010 , pp.
In this paper we describe Graaasp, a social software currently under development to support the creation of a real usage database of social artifacts. Our goals are twofold: First to offer a generic aggregation service and user interface to people and communities. Second, to experiment with recommendation and reputation models and algorithms in e-learning.
Ingram Sandy, Na Li, Denis Gillet
IEEE Third International Conference on Advances in Computer-Human Interactions, 2010 , pp.
This paper discusses the adoption of bottom- up social software tools in formal learning environments. This is believed to enhance the learning experience of today's young generation characterized by being technology savvy and keen on social networking. As a first step towards this objective, the 3A interaction model that aims at aiding the design of personal and collaborative learning platforms is presented. It accounts for interaction paradigms widely used in Web 2.0 applications and builds on Distributed Cognition and Activity Theory while remaining at the right level of abstraction to be easily ¿translatable¿ into tangible applications supporting both formal and informal learning.
Ingram Sandy, Christophe Salzmann, Denis Gillet
Journal of Universal Computer Science, 2010 , vol.
This paper discusses the 3A recommender system that targets CSCL (computersupported collaborative learning) and CSCW (computer-supported collaborative work) environments. The proposed system models user interactions in a heterogeneous graph. Then, it applies a personalized, contextual, and multi-relational ranking algorithm to simultaneously rank actors, activity spaces, and assets. The results of an empirical evaluation carried out on an Epinions dataset indicate that the proposed recommendation approach exploiting the trust and authorship networks performs better than user-based collaborative filtering in terms of recall.
Ullrich Carsten, Ingram Sandy, Denis Gillet
(Springer) International Conference on Web-Based Learning, 2010 , pp.
This paper discusses the potential role of social software in supporting teamwork and collaborative project management in higher education. Based on the fact that social software has been widely spread among young students nowadays, using it for collaborative learning is believed to increase students’ involvement and create learning incentives. Two social software platforms, Graaasp and Google Wave are examined in terms of sustaining collaborative learning activities. Relevant existing features and possible extensions that enhance the learning experience are addressed. Benefits and challenges resulting from the bottom-up learning paradigm are also presented.
Ingram Sandy, Denis Gillet, Christophe Salzmann, Chiu Man Yu
Second IEEE International Conferences on Advances in Computer-Human Interactions, 2009 , pp.
This paper presents the findings of a study on the acceptability in higher education of a Web 2.0 collaborative application, namely eLogbook. The latter offers several features for sustaining collaboration and supporting personal and group learning. It was introduced to students taking a laboratory course that spans over one semester and mainly consists of in-class group experiments. In this paper, we present eLogbook. We then describe our hypotheses as well as the qualitative and quantitative methods used to evaluate the usefulness and usability of eLogbook in a formal learning context. Finally, we discuss our findings and its implications.
Ingram Sandy, Christophe Salzmann, Stéphane Sire, Denis Gillet
Proceedings of the third ACM conference on Recommender systems, 2009 , pp.
In this paper, we propose a personalized and contextual ranking algorithm implemented on top of the 3A interaction model. The latter is a generic model intended for designing and describing social and collaborative learning platforms integrating Actors, Assets and group Activities (the 3" A"). The target user's interactions with his/her environment are modeled in a heterogeneous graph. Then, the algorithm is applied to simultaneously rank actors, assets and group activities taking into account the target user and his/her context. As an illustrative application and a preliminary evaluation, we apply the algorithm on data related to the activities carried out in a European Research Project, especially the collaboration between its members through the joint production of deliverables in workpackages.
Denis Gillet, Ingram Sandy, Christophe Salzmann, Chiu Man Yu
First international conference on advances in computer-human interaction, 2008 , pp.
In the framework of the European Integrated Project PALETTE, the Ecole Polytechnique Federale de Lausanne (EPFL) is developing the eLogbook Web 2.0 social software. The purpose of eLogbook is to support tacit and explicit knowledge management in communities of practice. It can be customized by the users to serve as an asset management system, as a task management system or as a discussion platform. In this paper, the innovative Computer-Human Interaction features of eLogbook are introduced and its deployment scenario to support collaborative laboratory activities in engineering education is described. The main idea is to sustain interaction for learning purpose within self-organized teams that integrate -on a seamless level- both human actors (students, teaching assistants) and non-human actors such as laboratory equipments or software agents.
Evgeny Bogdanov, Ingram Sandy, Christophe Salzmann, Denis Gillet
EC-TEL08-Workshop on Mash-Up Personal Learning Environments (MUPPLE’08), 2008
Despite the extreme diversity of Web applications, one can find similarities among them. This paper proposes an answer to the question of knowing whether it is possible to conceptually represent different Web applications in a common manner such that they can generically be integrated in other Web applications. The 3A model developed at EPFL in the framework of the European PALETTE project is used to generalize the visual and functional properties of Web applications. A Web 2.0 personal learning environment based on the 3A model called eLogbook is used as a mashup container to integrate existing Web applications. The mapping procedure is described and illustrated with the example of an instant messaging application, showing that mashup is possible with 3A model.
Denis Gillet, Ingram Sandy, Christophe Salzmann, Rekik Yassin Aziz
12th International Conference, HCI International 2007, 2007 , pp.
Denis Gillet, Sandy El Helou, Yassin Rekik, Chr Salzmann
Rekik Yassin Aziz, Ingram Sandy, Denis Gillet, Christophe Salzmann
International Journal of Web-Based Learning and Teaching Technologies (IJWLTT), 2007 , vol.
Convinced by the important role of CoPs (communities of practice) and the innovative learning modality they offer, the École Polytechnique Fédérale de Lausanne is currently developing a framework to sustain interaction, collaboration, and learning in laboratory-oriented CoPs, namely the eLogBook. This paper describes the services provided by this framework, the 3A model on which it is based, and the main features it presents. The eLogBook presents several innovative features that make it different from other classical collaboration workspaces. The eLogBook offers a high level of flexibility and adaptability so that it can fit the requirements of various CoPs. It allows CoPs’ members to define their own rules, protocols, and vocabularies. The eLogBook also focus on usability and user acceptance thanks to its personalization and contextualization mechanisms.
Ingram Sandy, Bernadette Charlier, Aida Boukottaya, Amaury Daele, Yannick Naudet, Nathalie Deschryver
TEL-CoPs’ 07: 2nd International Workshop on Building Technology Enhanced Learning Solutions for Communities of Practice, 2007
In this contribution, we specify and categorize CoPs’ needs (this includes the analysis of CoPs practices, resources and environments) in order to identify specific functions that meet these needs. This enables the efficient identification of possible interactions between PALETTE services’ categories that will be used as the basis to refine functional specifications of PALETTE services and enhance the development guidelines.
Juan Carlos Farah, Sandy Ingram, Basile Spaenlehauer, Fanny Kim-Lan Lasne, Denis Gillet
Proceedings of the 22nd International Conference on Web-Based Learning (ICWL 2023), 26th - 28th November 2023, Sydney, Australia ; Advances in Web-Based Learning – ICWL 2023
Link to the conference
The recent rise in both popularity and performance of large language models has garnered considerable interest regarding their applicability to education. Technologies like ChatGPT, which can engage in human-like dialog, have already disrupted educational practices given their ability to answer a wide array of questions. Nevertheless, integrating these technologies into learning contexts faces both technological and pedagogical challenges, such as providing appropriate user interfaces and configuring interactions to ensure that conversations stay on topic. To better understand the potential large language models have to power educational chatbots, we propose an architecture to support educational chatbots that can be powered by these models. Using this architecture, we created a chatbot interface that was integrated into a web application aimed at teaching software engineering best practices. The application was then used to conduct a case study comprising a controlled experiment with 26 university software engineering students. Half of the students interacted with a version of the application equipped with the chatbot, while the other half completed the same lesson without the chatbot. While the results of our quantitative analysis did not identify significant differences between conditions, qualitative insights suggest that learners appreciated the chatbot. These results could serve as a starting point to optimize strategies for integrating large language models into pedagogical scenarios.
Juan Carlos Farah, Basile Spaenlehauer, Sandy Ingram, Aditya K. Purohit, Adrian Holzer, Denis Gillet
Proceedings of the 26th International Conference on Interactive Collaborative Learning (ICL 2023), 26-29 September 2023, Madrid, Spain
In recent years, the use of chatbots in education has been driven by advances in natural language processing and the increasing availability of digital education platforms. Although the added value of educational chatbots appears promising, researchers have noted that there is a need for empirical studies that explore the effects of incorporating chatbots into different learning scenarios. In this paper, we report on the integration of a rule-based chatbot into an information technology course. We conducted a controlled experiment in which half of the students were able to interact with the chatbot during Python lab sessions while the other half completed the sessions without the chatbot. Our results suggest that educational chatbots powered by short, simple, interactive scripts could have a positive impact on the user experience offered by learning technologies and could be pertinent to educators looking to integrate chatbots into their practice.
Juan Carlos Farah, Basile Spaenlehauer, Sandy Ingram, Fanny Kim-Lan Lasne, Maria Jesus Rodriguez-Triana, Adrian Holzer, Denis Gillet
Driven by the rising popularity of chatbots such as ChatGPT, there is a budding line of research proposing guidelines for chatbot design, both in general and specifically for digital education. Nevertheless, few researchers have focused on providing conceptual tools to frame the chatbot design process itself. In this paper, we present a model to guide the design of educational chatbots. Our model aims to structure participatory design sessions in which different stakeholders (educators, developers, and learners) collaborate in the ideation of educational chatbots. To validate our model, we conducted an illustrative study in which 25 software design students took part in a simulated participatory design session. Students were divided into eight groups, assigned the role of one of the different stakeholders, and instructed to use our model. The results of our qualitative analysis suggest that our model helped structure the design process and align the contributions of the various stakeholders.
Rania Islambouli, Sandy Ingram, Isabelle Vonèche Cardia, Denis Gillet
Proceedings of the IEEE International Conference on Advanced Learning Technologies (ICALT) 2023, 10-13 July 2023, Orem, UT, USA
Social media have become an indispensable part of daily life, particularly among university students, who regularly browse social news feeds in their spare time. Due to their pervasiveness, social media platforms provide an opportunity for influencing user behavior and encouraging informal learning. In this paper, we present an experiment using an online video recommendation application designed to blend micro-informative content with general content according to user preferences and activity history. Based on a one-week study, we conclude that injecting micro-informative content into video streaming platforms has the potential to improve the perceived satisfaction of users and can act as a potential catalyst to motivate users to consume more informative content online.
Juan Carlos Farah, Basile Spaenlehauer, Maria Jesus Rodriguez-Triana, Sandy Ingram, Denis Gillet
Proceedings of 25th International Conference on Interactive Collaborative Learning (ICL 2022), 27-30 September 2022, Vienna, Austria
Proceedings of ICALT 2022 – 22nd IEEE International Conference on Advanced Learning Technologies, 1-4 July 2022, Bucharest, Romania
Peer code review has proven to be a valuable tool in software engineering. However, integrating code reviews into educational contexts is particularly challenging due to the complexity of both the process and popular code review tools. We propose to address this challenge by designing a code review application (CRA) aimed at teaching the code review process directly within existing online learning platforms. Using the CRA, instructors can scaffold online lessons that introduce the code review process to students through code snippets, following a format resembling computational notebooks. We refer to this online lesson format as the code review notebook format. Through a case study comprising an online lesson on code quality standards completed by 23 university students, we evaluated the usability of the CRA and the code review notebook format, obtaining positive results for both. These results are a first step toward integrating code review notebooks into software engineering education.
Juan Carlos Farah, Sandy Ingram, Basile Spaenlehauer, Denis Gillet
Proceedings of Conversational User Interfaces (CUI) 2022, 26-28th July 2022, Glasgow, UK
Over the past few years, there has been an increase in the use of chatbots for educational purposes. Nevertheless, the chatbot technologies and architectures that are often applied to educational contexts are not necessarily designed for such contexts. While general-purpose chatbot technologies can be used in educational contexts, there are some challenges specific to these contexts that need to be taken into consideration. Namely, chatbot technologies intended for education should, by design, integrate directly within online learning applications and focus on achieving learning goals by supporting learners with the task at hand. In this paper, we propose a blueprint for an architecture specifically aimed at integrating task-oriented chatbots to support learners in educational contexts. We then present a proof-of-concept implementation of our blueprint as a part of a code review application designed to teach programming best practices. Our blueprint could serve as a starting point for developers in education looking to build chatbot technologies targeting educational contexts and is a first step toward an open chatbot architecture explicitly tailored for learning applications.
Juan Carlos Farah, Sandy Ingram, Denis Gillet
Proceedings of 8th International Conference on Higher Education Advances (HEAd’22), 14-17 June 2022, Valencia, Spain
As more educational activities are conducted online, the need for interactive applications (apps) that can effectively support educators in their practice is increasing. These apps are often created by web developers or by researchers, educators, and even students with programming experience. While a large body of work has focused on incorporating these apps into educational contexts, fewer studies have focused on their development. In this paper, we first present the design and implementation of an app development framework aimed at supporting developers in creating apps for education. We then report the results of a study comprising interviews with 12 developers who used the framework. Our findings highlight that while the creation of web apps for education can be facilitated by a purely software-based app development framework, effectively exploiting such a framework requires domain knowledge that could be acquired through in-depth documentation, tutorials, and collaboration between developers and educators.
Houda Chabbi, Sandy Ingram, Florian Hofmann, Vinh Nguyen, Yasser Khazaal
Proceedings of 24th International Conference on Human-Computer Interaction (HCII), 26 June - 1st July 2022, Gothenburg, Sweden (Virtual Event)
Psychological disorders are often associated with a lack of inhibitory and interference control. In this paper, we present the software architecture design of a configurable serious game dedicated to inhibitory and interference control tests. The proposed architecture is based on generic components that are reusable across different game platforms and modes. Our design enables mental health practitioners to easily configure the serious game to adapt it to their test objectives and patients’ profile. The proposed game facilitates the tracking and analysis of inhibitory and interference control and their evolution over time, as data is logged over different gaming sessions. As a proof of concept, we implement a pilot application based on the proposed architecture, in both the 2D and VR modes. The developed application implements a gamified Stop Signal task (SST) augmented with interferences. We report the results of an empirical study assessing the perceived usability of the 2D and VR pilot games, using a standard usability test.
Juan Carlos Farah, Basile Spaenlehauer, Xinyang Lu, Sandy Ingram, Denis Gillet
Proceedings of 4th International Workshop on Bots in Software Engineering (BotSE 2022) in conjunction with the 44th International Conference on Software Engineering (ICSE 2022), 9 May 2022, Pittsburgh, PA, USA (Virtual Event)
The widespread use of bots to support software development makes social coding platforms such as GitHub a particularly rich source of data for the study of human-bot interaction. Software development bots are used to automate repetitive tasks, interacting with their human counterparts via comments posted on the various discussion interfaces available on such platforms. One type of interaction supported by GitHub involves reacting to comments using predefined emoji. To investigate how users react to bot comments, we conducted an observational study comprising 54 million GitHub comments, with a particular focus on comments that elicited the laugh reaction. The results from our analysis suggest that some reaction types are not equally distributed across human and bot comments and that a bot’s design and purpose influence the types of reactions it receives. Furthermore, while the laugh reaction is not exclusively used to express laughter, it can be used to convey humor when a bot behaves unexpectedly. These insights could inform the way bots are designed and help developers equip them with the ability to recognize and recover from unanticipated situations. In turn, bots could better support the communication, collaboration, and productivity of teams using social coding platforms.
Juan Carlos Farah, Basile Spaenlehauer, Vandit Sharma, Maria Jesus Rodriguez-Triana, Sandy Ingram, Denis Gillet
Proceedings of the 2022 IEEE Global Engineering Education Conference (EDUCON), 28-31 March 2022, Tunis, Tunisia
Over the past decade, the use of chatbots for educational purposes has gained considerable traction. A similar trend has been observed in social coding platforms, where automated agents support software developers with tasks such as performing code reviews. While incorporating code reviews and social coding platforms into software engineering education has been found to be beneficial, challenges such as steep learning curves and privacy considerations are barriers to their adoption. Furthermore, no study has addressed the role chatbots play in supporting code reviews as a pedagogical tool. To help address this gap, we developed an online learning application that simulates the code review features available on social coding platforms and allows instructors to interact with students using chatbot identities. We then embedded this application within a lesson on software engineering best practices and conducted a controlled in-class experiment. This experiment examined the effect that explaining content via chatbot identities had on three aspects: (i) students’ perceived usability of the lesson, (ii) their engagement with the code review process, and (iii) their learning gains. While our findings show that it is feasible to simulate the code review process within an online learning platform and achieve good usability, our quantitative analysis did not yield significant differences across treatment conditions for any of the aspects considered. Nevertheless, our qualitative results suggest that students expect explicit feedback when performing this type of exercise and could thus benefit from automated replies provided by an interactive chatbot. We propose to build on our current findings to further explore this line of research in future work.
Sandy Ingram, Rania Islambouli, Miharisoa Andrianantenaina, Jean-Philippe Weisskopf, Philippe Masset, Nicole Baudat
Proceedings of CSCI 2021 : The 2021 International Conference on Computational Science and Computational Intelligence, 15-17 December 2021, Las Vegas, USA
This paper presents an empirical case study on applying game-based learning in an undergraduate finance course. The paper describes the experimental study context, protocol, and results. Using multivariate regression analysis, a significant game effect on student performance is observed for competitive strategy-based games.
Rania Islambouli, Sandy Ingram, Denis Gillet
Proceedings of ICMLA 2021, International Conference on Machine Learning and Applications, 13-16 December 2021, virtual event
Spending an uncontrolled quantity and quality of time on digital news and social media platforms can negatively influence mental health and decrease cognitive abilities. In this paper, we propose a sequential news recommendation system employing deep reinforcement learning to capture the user’s short and long-term interests while blending social news with microlearning informative news items that can help users derive useful outcomes out of their online presence. In the absence of a publicly available dataset, we developed a simulation model to synthesize data and evaluate the proposed news recommendation system. We train and evaluate our model on synthesized data and show an improvement in user satisfaction.
Juan Carlos Farah, Vandit Sharma, Sandy Ingram, Denis Gillet
Proceedings of HAI '21: Proceedings of the 9th International Conference on Human-Agent Interaction, 9-11 November 2021, Virtual Event, Japan
Chatbots have long been advocated for computer-assisted language learning systems to support learners with conversational practice. A particular challenge in such systems is explaining mistakes stemming from ambiguous grammatical constructs. Misplaced modifiers, for instance, do not make sentences ungrammatical, but introduce ambiguity through the misplacement of an adverb or prepositional phrase. In certain cases, the ambiguity gives rise to humor, which can serve to illustrate the mistake itself. We conducted an online experiment with 400 native English speakers to explore the use of a chatbot to harness such humor. In an interaction resembling an advanced grammar exercise, the chatbot presented participants with a phrase containing a misplaced modifier, explained the ambiguity in the phrase, acknowledged (or ignored) the humor that the ambiguity gave rise to, and suggested a correction. Participants then completed a questionnaire, rating the chatbot with respect to ten traits. A quantitative analysis showed a significant increase in how participants rated the chatbot’s personality, humor, and friendliness when it acknowledged the humor arising from the misplaced modifier. This effect was observed whether the acknowledgment was conveyed using verbal, nonverbal (emoji), or mixed cues.
Juan Carlos Farah, Joana Soares Machado, Pedro Torres da Cunha, Sandy Ingram, Denis Gillet
Proceedings of 19th International Conference on Information Technology Based Higher Education and Training (ITHET), 4-6 November 2021, Sydney, Australia
Despite the importance of learning analytics in digital education, there is limited support for researchers in education to generate, access, and share experimental data while complying with ethical and privacy legislation. We propose a set of related tools that support researchers with these tasks and present a blueprint for how these tools can be integrated with existing platforms, enabling researchers to run studies within learning environments, adhere to legal and ethical privacy frameworks, and share their anonymous or anonymized data with a wider audience. We demonstrate the integration of these features into an existing online learning platform.
Proceedings of 4th Workshop on Human Factors in Hypertext, 30 July- 3 August, 2021, Virtual Event, Ireland
Spending an uncontrolled quantity and quality of time on digital information sites is affecting our well-being and can lead to serious problems in the long term. In this paper, we present a sequential recommendation framework that uses deep reinforcement learning to capture the users' short and long-term interests, with a proposed use case of blending social news with recommended micro-learning informative news items that can help users derive useful outcomes out of their presence online.
Sandy Ingram, Uchendu Nwachukwu, Nicole Jan, Jean-Philippe Bacher, Florinel Radu
Lecture Notes in Computer Science Proceedings of HCI-2021: International Conference on Human-Computer Interaction Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. Human Body, Motion and Behavior, 24-29 July 2021, Virtual event
Uchendu Nwachukwu, Sandy Ingram, Juan Carlos Farah, Denis Gillet
Proceedings of FECS'21 - The 17th International Conference on Frontiers in Education: Computer Science and Computer Engineering, 26-29 July 2021, Las Vegas, USA
Despite the rise in services generating learning analytics, there is a lack of standard models and guidelines for data integration and aggregation to inform the design choices of applications supporting learning analytics. We propose a bottom up, user-driven apporach enabling educators to select, match, and contextualize activity traces from several data sources to perform and visualize meaningful learning analytics. To facilitate the process, the proposed apporach recommends building customized auxiliary plugins that can be shared and re-purposed. We present the implementation of a use case following this approach. This use case focuses on supporting the import and side-by-side comparison of activity traces from multiple data surces that teachers might use in their practice. Implications of this approach on cross-platform learning analytics and future work are discussed.