Liudmila Zavolokina
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Liudmila Zavolokina has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Gerhard Schwabe
University of Zurich, Zurich, Switzerland
11 shared publications - Kilian Sprenkamp
University of Zürich
9 shared publications - Helmut Krcmar
Technical University of Munich
5 shared publications Gerhard Schwabe
University of Zürich
4 shared publications- Andreas Hein
University of St. Gallen
3 shared publications - Arthur Carvalho
Miami University
3 shared publications
Latest Publications
- Open Access
- 4 November 2026
- Published by Elsevier in Information & Management
- Vol. 64 (1)
Guidelines for employing large language models in information systems research
- 4 November 2026
- Published by Elsevier in Information & Management
- Vol. 64 (1)
Open AccessGuidelines for employing large language models in information systems research
- Open Access
- 18 December 2025
- Published by Association for Computing Machinery (ACM) in Digital Government: Research and Practice
- Vol. 6 (4) , 1-21
From Information-Seeking to Information-Asking: Designing RefuGPT, a Chatbot for Ukrainian Refugees in Switzerland
A key challenge for refugees is accessing relevant information about their host country. However, refugees often face disorientation during their information-seeking process. Disorientation is driven by language barriers, a digital divide, high urgency, and an evolving situation, which hinders the refugees’ ability to access information. Addressing the issue of disorientation, we propose an IT artifact, i.e., a chatbot called RefuGPT , designed through a rigorous Design Science Research Methodology. RefuGPT leverages the power of a large language model (LLM), GPT-4 while accessing two distinct sources of information, i.e., official and community-based information utilizing retrieval augmented generation and prompt-based learning (Figure 1 ). We assess RefuGPT's usefulness and usability through an ex-post evaluation in a naturalistic setting with Ukrainian refugees. Hence, we show that our bi-layered LLM-based chatbot can effectively assist refugees. They thus move from information-seeking to a more effortless information-asking. Based on those insights, we propose design principles as well as practical recommendations for refugee chatbots.
- 18 December 2025
- Published by Association for Computing Machinery (ACM) in Digital Government: Research and Practice
- Vol. 6 (4) , 1-21
Open AccessFrom Information-Seeking to Information-Asking: Designing RefuGPT, a Chatbot for Ukrainian Refugees in Switzerland
A key challenge for refugees is accessing relevant information about their host country. However, refugees often face disorientation during their information-seeking process. Disorientation is driven by language barriers, a digital divide, high urgency, and an evolving situation, which hinders the refugees’ ability to access information. Addressing the issue of disorientation, we propose an IT artifact, i.e., a chatbot called RefuGPT , designed through a rigorous Design Science Research Methodology. RefuGPT leverages the power of a large language model (LLM), GPT-4 while accessing two distinct sources of information, i.e., official and community-based information utilizing retrieval augmented generation and prompt-based learning (Figure 1 ). We assess RefuGPT's usefulness and usability through an ex-post evaluation in a naturalistic setting with Ukrainian refugees. Hence, we show that our bi-layered LLM-based chatbot can effectively assist refugees. They thus move from information-seeking to a more effortless information-asking. Based on those insights, we propose design principles as well as practical recommendations for refugee chatbots.
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Effective Yet Ephemeral Propaganda Defense: There Needs to Be More than One-Shot Inoculation to Enhance Critical Thinking
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Open AccessEffective Yet Ephemeral Propaganda Defense: There Needs to Be More than One-Shot Inoculation to Enhance Critical Thinking
- 22 March 2025
- Published by Springer Nature
- p. 339-354
Toward Government as a Platform: An Analysis Method for Public Sector Infrastructure
- 22 March 2025
- Published by Springer Nature
- p. 339-354
Toward Government as a Platform: An Analysis Method for Public Sector Infrastructure
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-24
Think Fast, Think Slow, Think Critical: Designing an Automated Propaganda Detection Tool
In today's digital age, characterized by rapid news consumption and increasing vulnerability to propaganda, fostering citizens' critical thinking is crucial for stable democracies. This paper introduces the design of ClarifAI, a novel automated propaganda detection tool designed to nudge readers towards more critical news consumption by activating the analytical mode of thinking, following Kahneman's dual-system theory of cognition. Using Large Language Models, ClarifAI detects propaganda in news articles and provides context-rich explanations, enhancing users' understanding and critical thinking. Our contribution is threefold: first, we propose the design of ClarifAI; second, in an online experiment, we demonstrate that this design effectively encourages news readers to engage in more critical reading; and third, we emphasize the value of explanations for fostering critical thinking. The study thus offers both a practical tool and useful design knowledge for mitigating propaganda in digital news.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-24
Open AccessThink Fast, Think Slow, Think Critical: Designing an Automated Propaganda Detection Tool
In today's digital age, characterized by rapid news consumption and increasing vulnerability to propaganda, fostering citizens' critical thinking is crucial for stable democracies. This paper introduces the design of ClarifAI, a novel automated propaganda detection tool designed to nudge readers towards more critical news consumption by activating the analytical mode of thinking, following Kahneman's dual-system theory of cognition. Using Large Language Models, ClarifAI detects propaganda in news articles and provides context-rich explanations, enhancing users' understanding and critical thinking. Our contribution is threefold: first, we propose the design of ClarifAI; second, in an online experiment, we demonstrate that this design effectively encourages news readers to engage in more critical reading; and third, we emphasize the value of explanations for fostering critical thinking. The study thus offers both a practical tool and useful design knowledge for mitigating propaganda in digital news.
- Open Access
- 8 January 2024
- Published by Springer Nature in Electronic Markets
- Vol. 34 (1) , 1-5
Preface to the special issue on “Enterprise and organizational applications of distributed ledger technologies”
- 8 January 2024
- Published by Springer Nature in Electronic Markets
- Vol. 34 (1) , 1-5
Open AccessPreface to the special issue on “Enterprise and organizational applications of distributed ledger technologies”
- Open Access
- 1 January 2024
- Published by HICSS Conference Office
Formative Archetypes in Enterprise Blockchain Governance: Exploring the Dynamics of Participant Dominance and Platform Openness
It is widely assumed that blockchain should, in principle, lead to decentralization. Yet, in practice, many enterprise blockchains are highly centralized. To explain this conundrum, we conduct a multi-case study of four enterprise blockchains: Walmart DL Freight, Contour, Chronicled MediLedger, and Cardossier. Exploring the dynamics of participant dominance and platform openness during their formative stages, we theorize that these blockchains correspond to the distinct archetypes of Chief, Clan, Custodian, and Consortium, respectively. Importantly, these archetypes shape the subsequent evolution of the governance approach, thus explaining why and how enterprise blockchains with dominant participants and limited openness later exhibit more centralized governance.
- 1 January 2024
- Published by HICSS Conference Office
Open AccessFormative Archetypes in Enterprise Blockchain Governance: Exploring the Dynamics of Participant Dominance and Platform Openness
It is widely assumed that blockchain should, in principle, lead to decentralization. Yet, in practice, many enterprise blockchains are highly centralized. To explain this conundrum, we conduct a multi-case study of four enterprise blockchains: Walmart DL Freight, Contour, Chronicled MediLedger, and Cardossier. Exploring the dynamics of participant dominance and platform openness during their formative stages, we theorize that these blockchains correspond to the distinct archetypes of Chief, Clan, Custodian, and Consortium, respectively. Importantly, these archetypes shape the subsequent evolution of the governance approach, thus explaining why and how enterprise blockchains with dominant participants and limited openness later exhibit more centralized governance.
- Open Access
- 1 January 2024
- Published by HICSS Conference Office
Introduction to the Minitrack on Design, Implementation, and Management of Digital Government Policies and Strategies
- 1 January 2024
- Published by HICSS Conference Office
Open AccessIntroduction to the Minitrack on Design, Implementation, and Management of Digital Government Policies and Strategies
- 1 January 2024
- Published by Association for Information Systems in Communications of the Association for Information Systems
- Vol. 54, 1011-1021
Designing Incentives for Attracting Peer Reviewers to Information System Conferences
Information systems (IS) conferences, as venues for the introduction of new knowledge to the IS community, require effective peer review systems to evaluate submitted research for quality, validity, and originality. We argue in this paper that questionable practices and degrading review quality may arise without direct incentives beyond reviewer altruism to engage in the peer review process. In particular, we highlight potential issues with arguably common practices in some IS conferences, such as peer review invitations sent to researchers who have also submitted papers for publication consideration and the increasing number of reviews performed by graduate students. To address these issues, we suggest three solutions: 1) quid pro quo rules; 2) the use of incentive-compatible methods whose scores are linked to relevant rewards; and 3) the use of blockchain-based tokens in tandem with smart contracts and zero-knowledge proofs. We conclude by offering directions the IS community can take to further study the highlighted issues and implement the proposed solutions.
- 1 January 2024
- Published by Association for Information Systems in Communications of the Association for Information Systems
- Vol. 54, 1011-1021
Designing Incentives for Attracting Peer Reviewers to Information System Conferences
Information systems (IS) conferences, as venues for the introduction of new knowledge to the IS community, require effective peer review systems to evaluate submitted research for quality, validity, and originality. We argue in this paper that questionable practices and degrading review quality may arise without direct incentives beyond reviewer altruism to engage in the peer review process. In particular, we highlight potential issues with arguably common practices in some IS conferences, such as peer review invitations sent to researchers who have also submitted papers for publication consideration and the increasing number of reviews performed by graduate students. To address these issues, we suggest three solutions: 1) quid pro quo rules; 2) the use of incentive-compatible methods whose scores are linked to relevant rewards; and 3) the use of blockchain-based tokens in tandem with smart contracts and zero-knowledge proofs. We conclude by offering directions the IS community can take to further study the highlighted issues and implement the proposed solutions.
- Open Access
Large Language Models for Propaganda Detection
The prevalence of propaganda in our digital society poses a challenge to societal harmony and the dissemination of truth. Detecting propaganda through NLP in text is challenging due to subtle manipulation techniques and contextual dependencies. To address this issue, we investigate the effectiveness of modern Large Language Models (LLMs) such as GPT-3 and GPT-4 for propaganda detection. We conduct experiments using the SemEval-2020 task 11 dataset, which features news articles labeled with 14 propaganda techniques as a multi-label classification problem. Five variations of GPT-3 and GPT-4 are employed, incorporating various prompt engineering and fine-tuning strategies across the different models. We evaluate the models' performance by assessing metrics such as $F1$ score, $Precision$, and $Recall$, comparing the results with the current state-of-the-art approach using RoBERTa. Our findings demonstrate that GPT-4 achieves comparable results to the current state-of-the-art. Further, this study analyzes the potential and challenges of LLMs in complex tasks like propaganda detection.Open AccessLarge Language Models for Propaganda Detection
The prevalence of propaganda in our digital society poses a challenge to societal harmony and the dissemination of truth. Detecting propaganda through NLP in text is challenging due to subtle manipulation techniques and contextual dependencies. To address this issue, we investigate the effectiveness of modern Large Language Models (LLMs) such as GPT-3 and GPT-4 for propaganda detection. We conduct experiments using the SemEval-2020 task 11 dataset, which features news articles labeled with 14 propaganda techniques as a multi-label classification problem. Five variations of GPT-3 and GPT-4 are employed, incorporating various prompt engineering and fine-tuning strategies across the different models. We evaluate the models' performance by assessing metrics such as $F1$ score, $Precision$, and $Recall$, comparing the results with the current state-of-the-art approach using RoBERTa. Our findings demonstrate that GPT-4 achieves comparable results to the current state-of-the-art. Further, this study analyzes the potential and challenges of LLMs in complex tasks like propaganda detection.