Publications

Conversational agents (CAs) are getting smarter thanks to advances in artificial intelligence, which opens the potential to use them in educational contexts to support (working) students. In addition, CAs are turning toward relationship-oriented virtual companions (e.g., Replika). Synthesizing these trends, we derive the virtual learning companion (VLC), which aims to support working students in their time management and motivation. In addition, we propose design knowledge, which was developed as part of a design science research project. We derive nine design principles, 28 meta-requirements, and 33 categories of design features based on interviews with students and experts, the results of an interdisciplinary workshop, and a user test. We aim to demonstrate how to design VLCs to unfold their potential for individual student support.

Basierend auf einer theoretisch fundierten Grundlage zu Motivationstheorien präsentiert diese Arbeit die Ergebnisse gestaltungsorientierter Forschung entlang des Design Science Research Paradigmas mit dem Ziel, Gestaltungsanforderungen für motivationale LCs abzuleiten. Der Prozess basiert dabei auf einer systematischen Literaturanalyse, problemzentrierten Interviews mit potentiellen, zukünftigen Nutzern sowie der exemplarischen Gestaltung eines konzeptionellen Prototyps, welcher eine erste Instanziierung von Designwissen verkörpert und mithilfe eines Design Thinking Workshops evaluiert wird. Als Ergebnis der Arbeit werden sieben Design-Prinzipien identifiziert, welche bei der Umsetzung eines LCs zur Erhöhung der Lernmotivation beachtet werden sollten. Dazu zählen spielerische Elemente (DP1), personalisierte und adaptive Avatare (DP2), individualisiertes Feedback und Statistiken (DP3), eine benutzerfreundliche Oberfläche mit Benachrichtigungsfunktionen (DP4), multimediale und interaktive Lerninhalte (DP5), Kommunikation und Kollaboration mit der Peer-Group (DP6) sowie an den Kenntnisstand des Lernenden angepasste Inhalte (DP7). Die gewonnenen Erkenntnisse leisten einen ersten Beitrag, um Praktikern konkrete Umsetzungsimpulse bei der Gestaltung motivationaler LCs bereitzustellen. Zeitgleich bieten sie der Forschung ein Grundgerüst für weitere gestaltungsorientierte Studien und moderne Ansätze zur digitalen Motivationsunterstützung, welche langfristig Abbruchquoten in der Weiterbildung senken und die Motivation beim Lernen steigern sollen.

Conversational agents (CAs)-software systems emulating conversations with humans through natural language-have been widely used to communicate and collaborate with humans in various settings. A rising application domain is education since so-called Pedagogical Conversational Agents (PCAs) hold the potential for individualized learning and thus the long-term improvement of learning success. However, existing research on CA adaptation is scattered across different application domains and user groups, so researchers face difficulty in understanding the current state of the art on the adaptation design of PCAs as an independent field of interest. To address this gap, we systematically analyze existing scientific literature and discuss identified adaptation aspects of PCAs in scientific publications. Our literature review contributes to IS research by providing an overview of existing adaptive and adaptable PCA designs, identified gaps, and future research streams with the rising potential thereupon.

Learners are faced with the challenge of processing a large amount of knowledge. However, they often lack individual support, and teaching is not tailored to their learning styles. Conversational Agents (CAs) could be a way to identify personal learning styles through a dialog between the CA and the learner, and to support him/her accordingly. This paper investigates whether learning styles can be determined through a dialog with a CA and how the conversation is perceived by users. For this purpose, a CA called Vicky was developed using the platform Rasa and the intent classifier DIET. Vicky determines the user’s learning styles through a questionnaire as well as a quiz and acts human-like to be perceived as a virtual companion. The prototype was evaluated in an experiment with 25 participants. They predominantly perceived themselves to be correctly classified and treated kindly by the CA. Overall, we contribute to science and practice by showing that CAs acting as virtual companions can be used to better understand learner preferences.

Pedagogical Conversational Agents (PCAs) offer the potential to increase educational equity worldwide by making learning accessible to all as a service for good, often enabled by artificial intelligence (AI). Yet, there are ethical challenges to the design and use of PCAs that hinder the achievement of individual and social goals. However, in addition to a multitude of directives on the ethical design of information systems, concrete resulting design features for PCAs still fall short in scientific literature. Furthermore, a human-centered ethical discussion that integrates future users’ involvement in ethical PCA design is scarce to find. Based on a co-creation process embedded in Design Science Research with a total of 40 students, we derive requirements and concrete features for ethically responsible PCAs and reflect them along with the OECD principles for trustworthy AI. Initial conceptual prototypes visualize exemplary instantiations.

International students often have difficulties in getting connected with other students (from their host country), or in fully understanding the lectures due to barriers such as interacting in a foreign language or adjusting to a new campus. eLearning Companions (eLCs) act as virtual friends, accompany students with dialog-based support for learning and provide individual guidance. We contribute to the lack of prescriptive design knowledge for that specific use case by deriving 16 design principles for eLCs and transferring them into an expository instantiation along the Design Science Research paradigm. We build upon 14 identified literature requirements and 15 condensed user requirements resulting from an empirical study with 76 Chinese-speaking exchange students at a German university. Our objective is to extend the knowledge base and support scientists and practitioners in eLC design for non-native students to initiate further research and discussion.

Learners are faced with the challenge of processing a large amount of knowledge. However, they often lack individual support, and teaching is not tailored to their learning styles. Conversational Agents (CAs) could be a way to identify personal learning styles through a dialog between the CA and the learner, and to support him/her accordingly. This paper investigates whether learning styles can be determined through a dialog with a CA and how the conversation is perceived by users. For this purpose, a CA called Vicky was developed using the platform Rasa and the intent classifier DIET. Vicky determines the user’s learning styles through a questionnaire as well as a quiz and acts human-like to be perceived as a virtual companion. The prototype was evaluated in an experiment with 25 participants. They predominantly perceived themselves to be correctly classified and treated kindly by the CA. Overall, we contribute to science and practice by showing that CAs acting as virtual companions can be used to better understand learner preferences.

Due to significant technological progress in the field of artificial intelligence, conversational agents have the potential to become smarter, deepen the interaction with their users, and overcome a function of merely assisting. Since humans often treat computers as social actors, theories on interpersonal relationships can be applied to human-machine interaction. Taking these theories into account in designing conversational agents provides the basis for a collaborative and benevolent long-term relationship, which can result in virtual companionship. However, we lack prescriptive design knowledge for virtual companionship. We addressed this with a systematic and iterative design science research approach, deriving meta-requirements and five theoretically grounded design principles. We evaluated our prescriptive design knowledge by taking a two-way approach, first instantiating and evaluating the virtual classmate Sarah, and second analyzing Replika, an existing virtual companion. Our results show that with virtual companionship, conversational agents can incorporate the construct of companionship known from human-human relationships by addressing the need to belong, to build interpersonal trust, social exchange, and a reciprocal and benevolent interaction. The findings are summarized in a nascent design theory for virtual companionship, providing guidance on how our design prescriptions can be instantiated and adapted to different domains and applications of conversational agents.

Conversational Agents (CAs) are widely spread in a variety of domains, such as health and customer service. There is a recent trend of increasing publications and implementations of CAs in education. We conduct a systematic literature review to identify common methodologies, pedagogical CA roles, addressed target groups, the technologies and theories behind, as well as human-like design aspects. The initially found 3329 records were systematically reduced to 252 fully coded articles. Based on the analysis of the codings, we derive further research streams. Our results reveal a research gap for long-term studies on the use of CAs in education, and there is insufficient holistic design knowledge for pedagogical CAs. Moreover, target groups other than academic students are rarely considered. We condense our findings in a morphological box and conclude that pedagogical CAs have not yet reached their full potential of long-term practical application in education.