2024

The Social Computing group was present at the 18th ACM Conference on Recommender Systems (RecSys 2024) in Bari, Italy, from October 14-18, 2024. RecSys is the premier international forum for the presentation of new research results, systems, and techniques in the broad field of recommender systems, well attended by researchers and industries around the globe. We were excited to present our latest work on user control and transparency at the 11th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS). At the workshop, Qurat Ul Ain presented our paper titled "Designing and Evaluating an Educational Recommender System with Different Levels of User Control", contributing valuable insights into the impact of control levels on transparency, trust, and satisfaction. Here is the link to the paper.

On September 2 & 3, 2024, Qurat Ul Ain and Shoeb Joarder attended the 3rd Learning AID at the Ruhr-University of Bochum. The conference and workshop were organized by the state-funded project KI:edu.nrw – a project to promote Didactics, Ethics, and Technology of Learning Analytics and AI in Higher Education.  The event focused on the practical use of learning analytics, artificial intelligence, and data mining in higher education.

Qurat presented our ongoing research on transparent recommender systems and demonstrated how our MOOC platform CourseMapper enables user interaction and control over the input, process, and output of an educational recommender system to enhance the learning experience. CourseMapper is available here.

Shoeb presented our ongoing Human-Centered Learning Analytics (HCLA) research and demoed the Indicator Editor in our Open Learning Analytics Platform (OpenLAP). The Indicator Editor provides an intuitive user interface that supports self-service learning analytics by empowering end-users to take control of the indicator development process. A demo can be found here.

After a lengthy review process, our paper "Visualization for Recommendation Explainability: A Survey and New Perspectives" has just been published in the prestigious ACM Transactions on Interactive Intelligent Systems and is now available online. This publication is particularly relevant for those who want to learn more about the theoretical background of visual explanations in AI and recommender systems and how to systematically develop explanatory visualizations in recommender systems. For more details, you can read the paper here. And, here is the link to the paper on arXiv.

The Social Computing Group was present at the 32nd ACM Conference on User Modeling, Adaptation and Personalization (UMAP'24) in Cagliari, Sardinia, Italy, from July 1-4, 2024. UMAP is the premier international conference for researchers and practitioners working on systems that adapt to individual users, to groups of users, and that collect, represent, and model user information. We presented our ongoing work on GNN-based user modeling in the context of our project CourseMapper. At the 1st International Workshop on User-Centered Practices of Knowledge Discovery in Educational Data (UKDE 2024), Rawaa Alatrash presented our paper titled "Transparent Learner Knowledge State Modeling using Personal Knowledge Graphs and Graph Neural Networks", available in UMAP24 Adjunct Proceedings here.

On June 19, 2024, Shoeb Joarder attended the event Learning Analytics in Practice (LAP24). LAP24 is a 24-hour, global online event that is intended to highlight and feature learning analytics practitioners around the world discussing and showcasing learning analytics in practice. Shoeb presented our ongoing research on Human-Centered Learning Analytics (HCLA) and gave a demo on the human-centered design and implementation of learning analytics indicators using OpenLAP. We received positive feedback from LAP24 participants, demonstrating the potential of the OpenLAP ISC Creator and OpenLAP Editor to actively involve different stakeholders in the learning analytics process. A demo can be found here.

Our paper "Transparent Learner Knowledge State Modeling using Personal Knowledge Graphs and Graph Neural Networks" got accepted at the workshop on User-Centered Practices of Knowledge Discovery in Educational Data (UKDE 2024) in conjunction with the 32nd ACM Conference on User Modeling, Adaptation and Personalization (ACM UMAP 2024). A preprint version of the paper is available here.

Just in time for the start of the summer semester of 2024, we are super excited to announce the launch of the pilot phase of our MOOC platform CourseMapper. CourseMapper will be used this semester to support collaborative learning in our Advanced Web Technologies (AWT) lecture course and Interactive Data Exploration and Analytics (IDEA) lab course.

Please feel free to test CourseMapper yourself here. If you have any questions, need more information, would like to join us in the further development of CourseMapper, or would like to collaborate on a research project around CourseMapper to democratize learning, please do not hesitate to contact us.

The Social Computing Group was present at the prestigious International Learning Analytics and Knowledge Conference (LAK24) in Kyoto, Japan, from March 18-22, 2024. LAK is the premier conference in the field of learning analytics and educational data science. We presented two papers in the context of our ongoing projects CourseMapper and OpenLAP. Qurat Ul Ain presented our full paper "Learner Modeling and Recommendation of Learning Resources using Personal Knowledge Graphs", available as open access here. Shoeb Joarder presented our poster paper "A No-Code Environment for Implementing Human-Centered Learning Analytics Indicators", available in LAK24 Companion Proceedings here.

In our new paper "ConceptGCN: Knowledge concept recommendation in MOOCs based on knowledge graph convolutional networks and SBERT", recently published in Computers and Education: Artificial Intelligence, we propose ConceptGCN, an end-to-end framework that combines knowledge graphs, graph convolutional networks, and transformer sentence encoders to enhance the representations of knowledge concepts and learner models and provide personalized and explainable recommendation of concepts in our MOOC platform CourseMapper. The paper is available as open access here.

2023

On December 1, 2023, Shoeb Joarder attended the Lehrkräftefortbildung Informatik 2023. He presented our ongoing work on Human-Centered Learning Analytics (HCLA) with Open Learning Analytics Platform (OpenLAP), our platform for self-service learning analytics. He showed a demo of OpenLAP in action, with a focus on the Indicator Specification Card (ISC) Creator and the Indicator Editor in OpenLAP.

Our paper "Interactive Explanation with Varying Level of Details in an Explainable Scientific Literature Recommender System" has been published in the International Journal of Human-Computer Interaction (IJHCI). In this work, we show how to design explanations with different levels of detail, in a systematic and theoretically-sound manner. Further, we highlight the positive impact of user-controlled, interactive explanation with varying level of details on the perception of explainable recommendation. A preprint version of the paper is available here.

Our paper "Automatic Construction of Educational Knowledge Graphs: A Word Embedding-Based Approach" has been published in the Information Journal.  In this work, we aimed at improving the concept extraction and weighting mechanisms in educational knowledge graphs (EduKGs) by leveraging state-of-the-art word and sentence embedding techniques. The paper is available as open access here.

Our paper "Semantic Interest Modeling and Content-Based Scientific Publication Recommendation Using Word Embeddings and Sentence Encoders" has been published in the Multimodal Technologies and Interaction Journal. In this work, we combine word embedding-based keyphrase extraction techniques with knowledge bases to generate semantically-enriched user interest models, and we leverage pretrained transformer sentence encoders to represent user models and papers and compute their similarities.  The paper is available as open access here.  

On August 28 & 29, 2023, Shoeb Joarder attended the 2nd Learning AID at the Ruhr-University of Bochum. The conference and workshop was organized by the state funded project KI:edu.nrw – a project to promote Didactics, Ethics and Technology of Learning Analytics and AI in Higher Education.  The event focused on the practical use of learning analytics, artificial intelligence, and data mining in higher education. Shoeb presented our ongoing research on Human-Centered Learning Analytics (HCLA) and gave a demo on the ISC Creator module in our Open Learning Analytics Platform (OpenLAP). The ISC Creator provides an intuitive user interface that allows the low-cost design of low-fidelity Learning Analytics indicators using Indicator Specification Cards. A demo can be found here.

You might be interested in understanding the difference between Transparency and Justification in explainable recommender systems. Check out our contribution "Justification vs. Transparency: Why and How Visual Explanations in a Scientific Literature Recommender System" which is published in the Information Journal  as part of the Special Issue "Information Visualization Theory and Applications". The paper is available as open access here.

Interested to learn more about visual explanation in recommender systems? Check out our paper "Visualization for Recommendation Explainability: A Survey and New Perspectives" at the following link.

Our paper "Validation of the EDUSS Framework for Self-Actualization Based on Transparent User Models: A Qualitative Study" got accepted as a full research paper at the workshop on Explainable User Models and Personalized System (ExUM 2023) in conjunction with the conference on User Modeling, Adaptation and Personalization (ACM UMAP 2023). A preprint version of the paper is available here.

On April 28^th and 29^th, 2023, Clara Siepmann attended the Human-Centered Explainable AI Workshop at the CHI'23 conference. She presented our paper "Trust and Transparency in Recommender Systems". In this work, we argue that exploration and explanation can be seen as two ends of a spectrum, with both having the potential to help the user achieve transparency and therefore trust. We referred to the combination of both approaches as exploranation.  The paper can be found here.

On March 13, 2023, we co-organized the Fourth International Workshop on Human-Centered Learning Analytics (HCLA) at the LAK’23 conference. Shoeb Joarder co-moderated the table discussion on “How can we create trustworthy LA systems?”. Furthermore, he presented our paper "Towards a Flexible User Interface for ‘Quick and Dirty’ Learning Analytics Indicator Design". In this work, we present the development details of an intuitive and theoretically-sound Indicator Specification Cards (ISC) user interface that allows the low-cost design of learning analytics indicators. The paper can be found here. A demo of the ISC user interface in OpenLAP can be found here.

2022

Join us for the Fourth International Workshop on "Human-Centred Learning Analytics (HCLA)" that we are co-organizing at the 13th International Learning Analytics and Knowledge (LAK'23) conference in Arlington, Texas, USA (March 13-17, 2023). The workshop will be fully online.

Human-centred learning analytics (HCLA) is an emerging subcommunity of learning analytics (LA) researchers and practitioners interested in creating reliable and trustworthy LA systems that amplify and augment the abilities of educational stakeholders and which are aligned to intentions, revealed preferences, ideal preferences, interests and values.

More details and call for short papers can be found on the workshop website.

Qurat Ul Ain has been selected as the "Best Presenter" from all the presentations in the 14th International Conference on Education Technology and Computers ICETC'22 which was held hybrid (in Barcelona and online) from October 28th to 30th, 2022. She presented a paper related to our CourseMapper project, titled: "Learning Channels to Support Interaction and Collaboration in CourseMapper". A preprint version of the paper is available here.

Our team continues to grow! We warmly welcome a new research assistant and Ph.D. student to our group. Clara Siepmann holds a master's degree in Applied Cognitive and Media Science from the University of Duisburg-Essen. Clara is especially interested in human factors in computing systems and AI/machine learning. She will strengthen our group's research on trustworthy human-AI interaction.

Our paper "What if Interactive Explanation in a Scientific Literature Recommender System" has been accepted at the ACM RecSys 22 Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS 2022). The paper can be found here.

On July 5th, 2022 Shoeb Joarder attended the DataCampus Conference in Essen. The event was organized by the DataCampus UDE - an interdisciplinary association to promote data skills at the UDE. During the conference, impressions of the development of the field of data literacy and data science were given, practical examples for the promotion of data skills in the subjects were presented, and perspectives for the development and expansion of data literacy and data science offered at the UDE were jointly developed. Shoeb presented the results of our Interactive Data Exploration and Analytics (IDEA)lab course and Exploratory Learning Analytics Toolkit for Students (ELAS) project - a collection of Learning Analytics applications developed by students for students.

Mouadh Guesmi attended the 30th ACM Conference on User Modeling, Adaptation, and Personalization (UMAP'22) which was held hybrid (in Barcelona and online) from July 4th to 7th, 2022. He presented two papers on our ongoing work on explainable recommender systems and explanation design choices. One in the main conference entitled: "Is More Always Better? The Effects of Personal Characteristics and Level of Detail on the Perception of Explanations in a Recommender System" (link to the paper), and the second was in the ExUM workshop entitled "Explaining User Models with Different Levels of Detail for Transparent Recommendation: A User Study" (link to the paper).

We currently have one open position for a Research Assistant and PhD Student in trustworthy data science. Please send your application as one PDF file to Prof. Mohamed Chatti. Application deadline is July 7th 2022.

You might be interested in our Explore - Develop - Understand - Scrutinize - Socialize (EDUSS) framework for self-actualization goals of transparent user modeling. Check out our contribution "Interactive Visualizations of Transparent User Models for Self-Actualization: A Human-Centered Design Approach" which is published in the Multimodal Technologies and Interaction Journal  as part of the Special Issue "Explainable User Models". The paper is available as open access here.  

Our paper "Explaining User Models with Different Levels of Detail for Transparent Recommendation: A User Study" got accepted as a full research paper at the workshop on Explainable User Models and Personalized System (ExUM 2022) in conjunction with the conference on User Modeling, Adaptation and Personalization (ACM UMAP 2022). A preprint version of the paper is available here.

Our team is growing. We are happy to welcome a new research assistant and Ph.D. student to our group! Rawaa Alatrash holds a master's degree in Computer Science and Engineering from India with a scholarship. Rawaa is interested in Human-Centered AI and NLP. She will support our group's research on knowledge graphs for recommendation and explanation.

Our paper "Is More Always Better? The Effects of Personal Characteristics and Level of Detail on the Perception of Explanations in a Recommender System" got accepted as a full research paper at the conference on User Modeling, Adaptation and Personalization (ACM UMAP 2022). A preprint version of the paper is available here.

The results of the student projects developed in the Human-Computer Interaction (HCI) and Learning Analytics lecture course in the winter semester of 2021/22 are now available, including open-source codes, demos, and advertisement videos. 

Teams of students in HCI participated in a two-months project to design and build a prototype around a set of user needs. The teams are tasked with milestones to move them towards a high-fidelity prototype as 
proof-of-concept that is presented in slides and demos at the end of the course. We were impressed with the quality of their projects.

Our paper "A Multi-Dimensional Conceptualization Framework for Personalized Explanations in Recommender Systems" got accepted at the workshop on Adaptive and Personalized Explainable User Interfaces (APEx-UI) in conjunction with the conference on Intelligent User Interfaces (ACM IUI 2022). In this work, we present a multi-dimensional conceptualization framework for personalized explanations in recommender systems, based on five dimensions: WHAT to personalize?, TO WHOM to personalize?, WHO does the personalization?, WHY personalize?, and HOW to personalize?. The paper can be found here.

You might be interested in how to effectively bring together theories and models from self-regulated learning, learning analytics, human-centered design, and information visualization. Check out our contribution "Designing Theory-Driven Analytics-Enhanced Self-Regulated Learning Applications" recently published as a chapter in the book "Visualizations and Dashboards for Learning Analytics. Advances in Analytics for Learning and Teaching" by Springer . In this chapter, we present the Student-Centered Learning Analytics-enhanced Self-Regulated Learning (SCLA-SRL) methodology for building theory-driven LA-enhanced SRL applications for and with learners. A preprint version of the chapter can be found here.

2021

The results of the student projects developed in theAdvanced Web Technologies (AWT)lecture course andInteractive Data Exploration and Analytics (IDEA)lab in summer semester 2021 are now available, including open-source codes, demos, and advertisement videos. Our students managed again to provide excellent projects and we are proud of them!

Our paper "Input or Output: Effects of Explanation Focus on the Perception of Explainable Recommendation with Varying Level of Details" has been accepted at theACM RecSys21 Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS 2021). The paper can be foundhere.

We are happy to welcome a new research assistant and Ph.D. student to our group. Qurat Ul Ain holds a master's degree in Computer Science from the National University of Computer & Emerging Sciences, Islamabad, Pakistan. Qurat Ul Ain is especially interested in Human-Computer Interaction and User Experience Engineering. She will strengthen our group's research on explainable learning analytics.

In the UMAP poster/demo session on Thursday, June 24, 2021, 15:30-16:15 CEST, we will present the Semantic Interest Modeling Toolkit (SIMT) and show how it has been leveraged in the transparent Recommendation and Interest Modeling Application (RIMA) to infer interest models of researchers based on their publications extracted from Semantic Scholar and use the inferred interest models to provide personalized recommendations of tweets. Here are links to the paper, the poster, and the video presentation of the demo.

We are happy to welcome a new research associate and Ph.D. student to our group. Shoeb Joarder holds a master's degree in Computer Engineering from the University of Duisburg-Essen. Shoeb is especially interested in the application of HCI, big data analytics, and visual analytics in education and social media. He will strengthen our group's research on scalable human-centered learning analytics.

Our paper "On-demand Personalized Explanation for Transparent Recommendation" got accepted as a full research paper at the workshop on Explainable User Models and Personalized System (ExUM 2021) in conjunction with the conference on User Modeling, Adaptation and Personalization (ACM UMAP 2021). The paper can be foundhere.

Our paper "SIMT: A Semantic Interest Modeling Toolkit" got accepted as a demo paper at the conference on User Modeling, Adaptation and Personalization (ACM UMAP 2021). The paper can be found here.

Starting summer semester 2021, we are offering a new lab course onInteractive Data Exploration and Analytics (IDEA)for Bachelor students in Applied Computer Science and Komedia. The aim of this semester's IDEA lab is to provide the foundation for an Exploratory Learning Analytics Toolkit for Students (ELAS) to support UDE students in their learning activities.

Our paper "Open, Scrutable and Explainable Interest Models for Transparent Recommendation" got accepted at the workshop on Transparency and Explanations in Smart Systems (TExSS) in conjunction with the conference on Intelligent User Interfaces (ACM IUI 2021). The paper can be found here.

2020

Mouadh Guesmi presented our paper "How to Design Effective Learning Analytics Indicators? A Human-Centered Design Approach" at the European Conference on Technology Enhanced Learning (ECTEL 2020). We propose in this work Human-Centered Indicator Design (HCID) as a transparent learning analytics approach that targets learners and teachers as end-users by involving them in the systematic design of learning analytics indicators that fit their needs, based on well-established design practices from the HCI and information visualization fields. A preprint version of the paper is available here.

Our chapter entitled "The LAVA Model: Learning Analytics Meets Visual Analytics" has been published in the book "Adoption of Data Analytics in Higher Education Learning and Teaching" by Springer. A preprint version of the chapter can be found here.

Our chapter entitled "Open Learning Analytics: A Systematic Literature Review and Future Perspectives" has been published in the book "Artificial Intelligence Supported Educational Technologies" by Springer. A preprint version of the chapter can be found here.

To support our online teaching in the summer semester 2020, we will use CourseMapper; a mind map-based collaborative course annotation and analytics platform that fosters collaboration and interaction around pdf/video learning materials, supported by visual learning analytics.