Logo des Repositoriums

Auflistung nach Autor:in "Riazy, Shirin"

1 - 4 von 4
  • Conference Paper 
    Code of Practice for Sensor-Based Learning
    (DELFI 2019, 2019) Yun, Haeseon; Riazy, Shirin; Fortenbacher, Albrecht; Simbeck, Katharina
    Sensor-based learning refers to utilizing physiological sensor data from learners and information from a learning environment to promote learning. Sensor data enclose learner’s personal information so ethical practice of adopting sensor data in learning analytics needs to be explored thoroughly. In this positional paper, we examine current ethical practices in learning analytics to derive a code of practice for sensor-based learning. Furthermore, we critically validate a wearable sensor device developed as a learning support against the derived code of practice.
  • Zeitschriftenartikel
    Highly Accurate, But Still Discriminatory
    (Business & Information Systems Engineering: Vol. 63, No. 1, 2021) Köchling, Alina; Riazy, Shirin; Wehner, Marius Claus; Simbeck, Katharina
    The study aims to identify whether algorithmic decision making leads to unfair (i.e., unequal) treatment of certain protected groups in the recruitment context. Firms increasingly implement algorithmic decision making to save costs and increase efficiency. Moreover, algorithmic decision making is considered to be fairer than human decisions due to social prejudices. Recent publications, however, imply that the fairness of algorithmic decision making is not necessarily given. Therefore, to investigate this further, highly accurate algorithms were used to analyze a pre-existing data set of 10,000 video clips of individuals in self-presentation settings. The analysis shows that the under-representation concerning gender and ethnicity in the training data set leads to an unpredictable overestimation and/or underestimation of the likelihood of inviting representatives of these groups to a job interview. Furthermore, algorithms replicate the existing inequalities in the data set. Firms have to be careful when implementing algorithmic video analysis during recruitment as biases occur if the underlying training data set is unbalanced.
  • Konferenzbeitrag
    Mobile First: Trends in Virtual Learning Environments
    (DELFI 2020 – Die 18. Fachtagung Bildungstechnologien der Gesellschaft für Informatik e.V., 2020) Riazy, Shirin; Simbeck, Katharina; Träger, Marco; Wöstenfeld, Robert
    Although mobile learning has long been predicted to become a vital part of the educational reality, schools often seem reluctant to implement mobile teaching solutions. In order to assess the current preferences of learning modalities for school students (ages 9-15) and teachers, an e-learning environments traffic data was analyzed. We have detected two trends: The first is a total rise of mobile usage, especially in comparison to the usage of desktop PCs in the past four years. Second, we have detected that especially students aged 12-15 mostly prefer mobile devices. Hence platform design should be adapted for better use with mobile devices to meet the learners’ needs.
  • Conference Paper 
    Predictive Algorithms in Learning Analytics and their Fairness
    (DELFI 2019, 2019) Riazy, Shirin; Simbeck, Katharina
    Predictions in learning analytics are made to improve tailored educational interventions. However, it has been pointed out that machine learning algorithms might discriminate, depending on different measures of fairness. In this paper, we will demonstrate that predictive models, even given a satisfactory level of accuracy, perform differently across student subgroups, especially for different genders or for students with disabilities.