Papers by Gayane Sedrakyan
Artificial intelligence (AI) has been recognized by the World Health Organization for its transfo... more Artificial intelligence (AI) has been recognized by the World Health Organization for its transformative potential in addressing global reproductive healthcare challenges, including inequitable access to monitoring and treatment and limited diagnostic precision. AI offers significant promise in enhancing diagnostic accuracy enabling data-driven decision-making for personalized preventive and therapeutic interventions. However, its deployment also raises ethical and operational concerns, such as data privacy risks, algorithmic bias, legal complexities, cultural sensitivity, overreliance on AI-generated recommendations, and the potential deskilling of clinicians. Addressing these challenges requires inclusive frameworks for responsible integration. Moreover, AI-driven digital transformation must align with the broader call for sustainable innovation outlined in the United Nations' 2030 Agenda and European Union regulations defining the requirement for safe and secure integration standards. This research explores pathways for responsible and sustainable AI adoption in reproductive healthcare while mitigating associated risks. It introduces the (H)iCARE framework, which advocates for (1) human-centric hybrid models that integrate AI-driven innovations with clinical expertise to ensure balanced innovations. The framework also (2) embraces a broader, humanity-oriented perspective to ensure inclusivity beyond a limited subset of stakeholders, and (3) fosters a learning-driven approach that prioritizes continuous skill development to prevent cognitive complacency. While developed in the context of reproductive healthcare, its principles extend across the healthcare sector, providing a foundation
Design Implications Towards Human-Centric Semantic Recommenders for Sustainable Food Consumption
Lecture Notes in Computer Science, Dec 31, 2022
Measuring Learning Progress for Serving Immediate Feedback Needs: Learning Process Quantification Framework (LPQF)
Lecture Notes in Computer Science, 2020
Our earlier research attempts to close the gap between learning behavior analytics based dashboar... more Our earlier research attempts to close the gap between learning behavior analytics based dashboard feedback and learning theories by grounding the idea of dashboard feedback onto learning science concepts such as feedback, learning goals, (socio-/meta-) cognitive mechanisms underlying learning processes. This work extends the earlier research by proposing mechanisms for making those concepts and relationships measurable. The outcome is a complementary framework that allows identifying feedback needs and timing for their provision in a generic context that can be applied to a certain subject in a given LMS. The research serves as general guidelines for educators in designing educational dashboards, as well as a starting research platform in the direction of systematically matching learning sciences concepts with data and analytics concepts.
Communications in computer and information science, 2017
State-of-the-art technologies have made it possible to provide a learner with immediate computer-... more State-of-the-art technologies have made it possible to provide a learner with immediate computer-assisted feedback by delivering a feedback targeting cognitive aspects of learning, (e.g. reflecting on a result, explaining a concept, i.e. improving understanding). Fast advancement of technology has recently generated increased interest for previously non-feasible approaches for providing feedback based on learning behavior observations by exploiting different traces of learning processes stored in information systems. Such learner behavior data makes it possible to observe different aspects of learning processes in which feedback needs of learners (e.g. difficulties, engagement issues, inefficient learning processes, etc.) based on individual learning trajectories can be traced. By identifying problems earlier in a learning process it is possible to deliver individualized feedback helping learners to take control of their own learning, i.e. to become self-regulated learners, and teachers to understand individual feedback needs and/or adapt their teaching strategies. In this work we (i) propose cognitive computer-assisted feedback mechanisms using a combination of MDE based simulation augmented with automated feedback, and (ii) discuss perspectives for behavioral feedback, i.e. feedforward, that can be based on learning process analytics in the context of learning conceptual modeling. Aggregated results of our previous studies assessing the effectiveness of the proposed cognitive feedback method with respect to improved understanding on different dimensions of knowledge, as well as feasibility of behavioral feedforward automation based on learners behavior patterns, are presented. Despite our focus on conceptual modeling and specific diagrams, the principles of the approach presented in this work can be used to support educational feedback automation for a broader spectrum of diagram types beyond the scope of conceptual modeling.
It is commonly accepted that quality testing is the integral part of system engineering. Recent r... more It is commonly accepted that quality testing is the integral part of system engineering. Recent research highlights the need of shifting testing of a system to the earliest phases of engineering in order to reduce the number of errors resulting from miscommunicated and/or wrongly specified requirements. Information and Computer Science education might need to adapt to such needs. This paper explores the perspectives and benefits of testing-based teaching of requirements engineering. Model Driven Engineering (MDE) is known to promote the early testing perspective through fast prototyping of a prospective system contributing in this way to semantic validation of requirements. Our previous research presents empirically validated positive results on the learning effectiveness of modelbased requirements engineering in combination with adapted MDE-prototyping method within an educational context to test the requirements and to test the requirements testability. Despite these positive results, our observation of the prototype testing patterns of novice analysts suggest that combining this prototypebased learning with the teaching of testing skills, such combined approach can result in even better learning outcomes.
International Journal of Information and Education Technology
After some time of lockdown experiences, limited attention for feedback and the absence of feedba... more After some time of lockdown experiences, limited attention for feedback and the absence of feedback digitalization frameworks suggests rethinking traditional feedback practices toward post-pandemics digital/hybrid education. This research surveyed feedback digitalization needs in the context of online education in high education institutions in the Netherlands and Germany during the COVID-19 pandemic. The dimensions surveyed included preferences for feedback such as typology of feedback (e.g., cognitive, behavioral, etc.), formats (e.g., written, audio, video), online instruments, and features for communicating feedback. The results suggest that online instruments supporting features for effortless interactivity are among the highly preferred digital options for giving/receiving feedback. When given online, inclusive formats of feedback that inform learners not only about their own but also peer performance were also found to be among highly rated options. The increased need for inc...
Soft Computing
Student feedback analysis is time-consuming and laborious work if it is handled manually. This st... more Student feedback analysis is time-consuming and laborious work if it is handled manually. This study explores the use of a new deep learning-based method to design a more accurate automated system for analysing students’ feedback (called DTLP: deep learning and teaching process). The DTLP employs convolutional neural networks (CNNs), bidirectional LSTM (BiLSTM), and attention mechanism.To the best of our knowledge, a deep learning-based method using a unified feature set, which is representative of word embedding, sentiment knowledge, sentiment shifter rules, linguistic and statistical knowledge, has not been thoroughly studied with regard to sentiment analysis of student feedback. Furthermore, DTLP uses multiple strategies to overcome the following drawbacks: contextual polarity; sentence types; words with similar semantic context but opposite sentiment polarity; word coverage limit of an individual lexicon; and word sense variations. To evaluate the DTLP, we conducted an experimen...
Measuring Learning Progress for Serving Immediate Feedback Needs: Learning Process Quantification Framework (LPQF)
Our earlier research attempts to close the gap between learning behavior analytics based dashboar... more Our earlier research attempts to close the gap between learning behavior analytics based dashboard feedback and learning theories by grounding the idea of dashboard feedback onto learning science concepts such as feedback, learning goals, (socio-/meta-) cognitive mechanisms underlying learning processes. This work extends the earlier research by proposing mechanisms for making those concepts and relationships measurable. The outcome is a complementary framework that allows identifying feedback needs and timing for their provision in a generic context that can be applied to a certain subject in a given LMS. The research serves as general guidelines for educators in designing educational dashboards, as well as a starting research platform in the direction of systematically matching learning sciences concepts with data and analytics concepts.
It is commonly accepted that quality testing is the integral part of system engineering. Recent r... more It is commonly accepted that quality testing is the integral part of system engineering. Recent research highlights the need of shifting testing of a system to the earliest phases of engineering in order to reduce the number of errors resulting from miscommunicated and/or wrongly specified requirements. Information and Computer Science education might need to adapt to such needs. This paper explores the perspectives and benefits of testing-based teaching of requirements engineering. Model Driven Engineering (MDE) is known to promote the early testing perspective through fast prototyping of a prospective system contributing in this way to semantic validation of requirements. Our previous research presents empirically validated positive results on the learning effectiveness of modelbased requirements engineering in combination with adapted MDE-prototyping method within an educational context to test the requirements and to test the requirements testability. Despite these positive resu...
Communications in Computer and Information Science, 2017
State-of-the-art technologies have made it possible to provide a learner with immediate computer-... more State-of-the-art technologies have made it possible to provide a learner with immediate computer-assisted feedback by delivering a feedback targeting cognitive aspects of learning, (e.g. reflecting on a result, explaining a concept, i.e. improving understanding). Fast advancement of technology has recently generated increased interest for previously non-feasible approaches for providing feedback based on learning behavior observations by exploiting different traces of learning processes stored in information systems. Such learner behavior data makes it possible to observe different aspects of learning processes in which feedback needs of learners (e.g. difficulties, engagement issues, inefficient learning processes, etc.) based on individual learning trajectories can be traced. By identifying problems earlier in a learning process it is possible to deliver individualized feedback helping learners to take control of their own learning, i.e. to become self-regulated learners, and teachers to understand individual feedback needs and/or adapt their teaching strategies. In this work we (i) propose cognitive computer-assisted feedback mechanisms using a combination of MDE based simulation augmented with automated feedback, and (ii) discuss perspectives for behavioral feedback, i.e. feedforward, that can be based on learning process analytics in the context of learning conceptual modeling. Aggregated results of our previous studies assessing the effectiveness of the proposed cognitive feedback method with respect to improved understanding on different dimensions of knowledge, as well as feasibility of behavioral feedforward automation based on learners behavior patterns, are presented. Despite our focus on conceptual modeling and specific diagrams, the principles of the approach presented in this work can be used to support educational feedback automation for a broader spectrum of diagram types beyond the scope of conceptual modeling.
New tutorial to be presented at ER'15 conference in Stockholm, Sweden (October 19-22, 2015) L... more New tutorial to be presented at ER'15 conference in Stockholm, Sweden (October 19-22, 2015) Learning requirements analysis and validation through conceptual modeling is very hard. Experienced analysts manage to mentally picture (i.e. simulate) the future information system in their mind while analyzing and validation requirements. This skill is very hard to transfer to junior requirements engineers. Not surprisingly, computer-based simulation has been proven to be an excellent technique in assisting juniors in understanding complex systems. However, the practical use of computer-based simulation is hampered by the difficulty of swiftly generating simulations out of conceptual models and the difficulty of interpreting simulation results. This tutorial reviews the challenges in teaching conceptual modeling and model simulation, and the gains that can be obtained when using feedback-enabled simulation. The tutorial is based on a novel, award winning and scientifically proven method...
Technology-enhanced learning of conceptual modeling
This paper is an extended abstract that describes the challenges of teaching conceptual modeling ... more This paper is an extended abstract that describes the challenges of teaching conceptual modeling and proposes an MDE-based simulation and automation technique to deliver feedbacks that guide throughout the entire modeling cycle starting from early modeling phases up to the increased transparency between a model and its simulated prototype.
Proceedings of the 10th International Conference on Model-Driven Engineering and Software Development
Requirements analysis and modeling is a challenging task involving complex knowledge of the domai... more Requirements analysis and modeling is a challenging task involving complex knowledge of the domain to be engineered, modeling notation, modelling knowledge, etc. When constructing architectural artefacts experts rely largely on the tacit knowledge that they have built based on previous experiences. Such implicit knowledge is difficult to teach to novices, and the cost of the gap between classroom knowledge and real business situations is thus reflected in further needs for postgraduate extensive trainings for novice and junior analysts. This research aims to explore the state-of-the art natural language processing techniques that can be adopted in the domain of requirements engineering to assist novices in their task of knowledge construction when learning requirements analysis and modeling. The outcome includes a method called Text-To-Model (TeToMo) that combines the state-of-the-art natural language processing approaches and techniques for identifying potential architecture element candidates out of textual descriptions (business requirements). A subsequent prototype is implemented that can assist a knowledge construction process through (semi-) automatic generation and validation of Unified Modeling Lnaguage (UML) models. In addition, to the best of our knowledge, a method that integrates machine learning based method has not been thoroughly studied for solving requirements analysis and modeling problem. The results of this study suggest that integrating machine learning methods, word embedding, heuristic rules, statistical and linguistic knowledge can result in increased number of automated detection of model constructs and thus also better semantic quality of outcome models.
Lecture Notes in Computer Science, 2018
The road to publishing public streaming data on the Web is paved with trade-offs that determine i... more The road to publishing public streaming data on the Web is paved with trade-offs that determine its viability. The cost of unrestricted query answering on top of data streams, may not be affordable for all data publishers. Therefore, public streams need to be funded in a sustainable fashion to remain online. In this paper we present an overview of possible query answering features for live time series in the form of multidimensional interfaces. For example, from a live parking availability data stream, pre-calculated time constrained statistical indicators or geographically classified data can be provided to clients on demand. Furthermore, we demonstrate the initial developments of a Linked Time Series server that supports such features through an extensible modular architecture. Benchmarking the costs associated to each of these features allows to weigh the trade-offs inherent to publishing live time series and establishes the foundations to create a decentralized and sustainable ecosystem for live data streams on the Web.
A PIM-to-Code Requirements Engineering Framework
Proceedings of the 1st International Conference on Model-Driven Engineering and Software Development, 2013
The complexity of model-driven engineering leads to a limited adoption of MDE in practice. In thi... more The complexity of model-driven engineering leads to a limited adoption of MDE in practice. In this paper we argue that MDE offers "low hanging fruit" if creating executable UML models is targeted rather than developing full-fledged information systems. This paper describes an environment for designing and validating conceptual models using the model-driven architecture (MDA). The deliverable of the proposed modeling environment is an executable platform independent model (EPIM) that is further tested and validated through an MDA-based simulation feature. The proposed environment addresses a set of challenges associated with 1. shortcomings of the UML for being technically too complex for conceptual modeling goals as well as for being not precise enough for rapid prototyping; 2. difficulties of MDE adoption due to the large set of required skills to adopt the key MDA standards such as the UML, MOF and XMI. The paper aims to introduce the current work and identify the needs for future research.
Journal of computer languages, Feb 1, 2019
This is a PDF file of an unedited manuscript that has been accepted for publication. As a service... more This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. Highlights little is known theoretically on the dashboard design principles earlier research links design and educational science concepts to design feedback we extend earlier research by linking dashboard design and visualization concepts general recommendations are derived to guide the choice of visual representations a case example is given showing visualizations per intended feedback / goal
International journal of human-computer studies, 2019
In this paper, we advent a novel approach to foster exploration of recommendations: Inter-section... more In this paper, we advent a novel approach to foster exploration of recommendations: Inter-sectionExplorer, a scalable visualization that interleaves the output of several recommender engines with human-generated data, such as user bookmarks and tags, as a basis to increase exploration and thereby enhance the potential to find relevant items. We evaluated the viability of IntersectionExplorer in the context of conference paper recommendation, through three user studies performed in different settings to understand the usefulness of the tool for diverse audiences and scenarios. We analyzed several dimensions of user experience and other, more objective, measures of performance. Results indicate that users found Intersec-tionExplorer to be a relatively fast and effortless tool to navigate through conference papers. Objective measures of performance linked to interaction showed that users were not only interested in exploring combinations of machine-produced recommendations with bookmarks of users and tags, but also that this "augmentation" actually resulted in increased likelihood of finding relevant papers in explorations. Overall, the findings suggest the viability of In-tersectionExplorer as an effective tool, and indicate that its multi-perspective approach to exploring recommendations has great promise as a way of addressing the complex humanrecommender system interaction problem.
Evaluating Student-Facing Learning Dashboards of Affective States
Lecture Notes in Computer Science, 2017
Detection and visualizations of affective states of students in computer based learning environme... more Detection and visualizations of affective states of students in computer based learning environments have been proposed to support student awareness and improve learning. However, the evaluation of such visualizations with students in real life settings is an open issue. This research reports on our experiences from the use of four different types of dashboard visualizations in two user studies (n = 115). Students who participated in the studies were bachelor and master level students from two different study programs at two universities. The results indicate that usability, measured by interpretability, perceived usefulness and insight, is overall acceptable. However, the findings also suggest that interpretability of some visualizations, in terms of the capability to support emotion awareness, still needs to be improved. The level of students awareness about their emotions during learning activities based on the visualization interpretation varied depending on previous knowledge on visualization techniques. Furthermore, simpler visualizations resulted in better outcomes than more complex techniques.
Journal of research in innovative teaching & learning, Jul 3, 2017
Purpose-The purpose of this paper is to evaluate four visualizations that represent affective sta... more Purpose-The purpose of this paper is to evaluate four visualizations that represent affective states of students. Design/methodology/approach-An empirical-experimental study approach was used to assess the usability of affective state visualizations in a learning context. The first study was conducted with students who had knowledge of visualization techniques (n ¼ 10). The insights from this pilot study were used to improve the interpretability and ease of use of the visualizations. The second study was conducted with the improved visualizations with students who had no or limited knowledge of visualization techniques (n ¼ 105). Findings-The results indicate that usability, measured by perceived usefulness and insight, is overall acceptable. However, the findings also suggest that interpretability of some visualizations, in terms of the capability to support emotional awareness, still needs to be improved. The level of students' awareness of their emotions during learning activities based on the visualization interpretation varied depending on previous knowledge of information visualization techniques. Awareness was found to be high for the most frequently experienced emotions and activities that were the most frustrating, but lower for more complex insights such as interpreting differences with peers. Furthermore, simpler visualizations resulted in better outcomes than more complex techniques. Originality/value-Detection of affective states of students and visualizations of these states in computerbased learning environments have been proposed to support student awareness and improve learning. However, the evaluation of visualizations of these affective states with students to support awareness in real life settings is an open issue.
Uploads
Papers by Gayane Sedrakyan