Samrat Gupta

• Gupta, Mukul; Gupta, Samrat & Tayi, Giri Kumar (2025). GASP: A Graph Augmentation-Based Approach for Sign Prediction of Ties in Social Networks. Journal of the AIS. 26(5), p. 1514–1546. doi: 10.17705/1jais.00941. Full text in Research Archive Show summary

  This paper proposes a method for the sign prediction of ties in social networks using a design science research process. The proposed method is grounded in social network analysis and leverages the tenets of graph augmentation and a graph regularized framework for information diffusion. To the best of our knowledge, this is the first study that develops a sign prediction method for social networks based on the principles of design science research. This study makes several contributions. We demonstrate the utility and applicability of the proposed method for predicting trust/distrust on a user-user network created from the IMDb platform, which represents ties between reviewers based on their movie evaluation preferences. We describe and discuss the novel aspects of graph augmentation, symmetric normalization of the affinity matrix, and graph regularized label propagation, and discuss their synergistic use to predict the signs of network ties. We also establish the effectiveness of the proposed method by comparing its performance with two different metrics for balanced networks and two metrics for unbalanced networks using four state-of-the-art methods. The benchmarking networks used for experiments originate from online platforms such as Slashdot, Epinions, Wikipedia, and the Yeast Genetic Interaction Network from the biology domain. Experiments show that the proposed method provides significant performance improvements in the sign prediction of ties in social networks. This study provides valuable insights for social media platform owners seeking to improve their platforms by building new features and business leaders seeking to target advertisements and personalized content to users. We also discuss the theoretical, practical, and societal implications of this research.

• Schoormann, Thorsten; Gupta, Samrat; Möller, Frederik & Kruse, Leona Chandra (2025). With Great Power Comes Great Responsibility: Responsible Management of Artificial Intelligence in Supporting Design Research Activities. Proceedings of the Annual Hawaii International Conference on System Sciences (HICSS). ISSN 1530-1605. 58, p. 5405–5414. doi: 10.24251/HICSS.2025.649. Full text in Research Archive Show summary

  Novel technologies are getting growing attention in our scholarly lives and are shifting the way traditional research practices are used. This paper explores how design research is affected by technological advancements and what potential risks can arise from that. By surveying information systems (IS) design literature, we observed a focus on enhancing the design outcome through computational, data-driven, and AIdriven approaches. Only a few papers in our sample provide insights into how the design process, from problem understanding through artifact building to evaluation, can be supported. We therefore explore the opportunities of delegating tasks between human designers and technology by presenting examples from the broader design research literature and borrowing illustrations from adjacent fields. Our work aims to open up the solution space of technology-aided design processes and creates awareness of the responsible handling of technology in design research.

• Sadhukhan, Payel & Gupta, Samrat (2025). A graph theoretic approach to assess quality of data for classification task. Data & Knowledge Engineering. ISSN 0169-023X. 158. doi: 10.1016/j.datak.2025.102421. Full text in Research Archive Show summary

  The correctness of predictions rendered by an AI/ML model is key to its acceptability. To foster researchers’ and practitioners’ confidence in the model, it is necessary to render an intuitive understanding of the workings of a model. In this work, we attempt to explain a model’s working by providing some insights into the quality of data. While doing this, it is essential to consider that revealing the training data to the users is not feasible for logistical and security reasons. However, sharing some interpretable parameters of the training data and correlating them with the model’s performance can be helpful in this regard. To this end, we propose a new measure based on Euclidean Minimum Spanning Tree (EMST) for quantifying the intrinsic separation (or overlaps) between the data classes. For experiments, we use datasets from diverse domains such as finance, medical, and marketing. We use state-of-the-art measure known as Davies Bouldin Index (DBI) to validate our approach on four different datasets from aforementioned domains. The experimental results of this study establish the viability of the proposed approach in explaining the working and efficiency of a classifier. Firstly, the proposed measure of class-overlap quantification has shown a better correlation with the classification performance as compared to DBI scores. Secondly, the results on multi-class datasets demonstrate that the proposed measure can be used to determine the feature importance so as to learn a better classification model.

• Schmager, Stefan; Gupta, Samrat; Pappas, Ilias & Vassilakopoulou, Polyxeni (2024). Designing for AI Transparency in Public Services: A User-Centred Study of Citizens’ Preferences. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 14720, p. 237–253. doi: 10.1007/978-3-031-61315-9_17. Full text in Research Archive
• Ødeskaug, Christian Aleksander Aamlid; Gjertsen, Tord Vetle; Gupta, Samrat & Pappas, Ilias (2023). Exploring Willingness to Adopt Contact Tracing Applications: A Study with Norwegian Citizens. International Journal of Business Science and Applied Management. 18(2), p. 1–16. Full text in Research Archive Show summary

  Amid discussions on the efficacy of digital contact tracing (DCT) during COVID-19, the Norwegian Institute of Public Health's application, Smittestopp, faced criticism for perceived privacy intrusions. Despite its relaunch without GPS-tracking, skepticism persisted due to initial issues. This study proposes a model to assess DCT adoption, focusing on Norwegian citizens' privacy concerns, trust, and risk beliefs, particularly towards Smittestopp. The moderating role of emotions is also examined. Findings indicate that privacy concerns inversely affect trust and enhance risk beliefs. Trust and perceived advantages bolster the intention to use the application, while risk beliefs reduce it. Negative emotions moderate the relationship between risk beliefs and intention to use, whereas positive emotions amplify the influence of perceived benefits on app usage intention. Intention to use led to actual utilization of the Smittestop app. These insights increase our understanding of how DCT apps are perceived in a country in which citizen trust in government is high, while offering significant implications for managing future crises and contagion spread.

View all works in NVA