Abstract

Abstract
Digital Transformation Models (DTM) and Digital Maturity Models (DMM) are two artefacts that guide the planning and implementation of Digital Transformation (DT) initiatives. When used in a combined approach, a DTM-DMM pairing could support DT managers and practitioners, as DTs are holistic and complex initiatives with high failure rates. However, no study has yet systematically addressed the compatibility amongst artefacts. This paper, therefore, aims to analyse the compatibility between academic DTMs and DMMs. Based on architectural compatibility and conceptual similarity, we provide a structured and replicable mixed methods approach to assessing artefact compatibility. To achieve this, we start with a systematic literature review to identify existing academic DTMs and DMMs, analyse the models and group them according to their scope. After, we employ quantitative similarity analysis techniques (Term Frequency-Inverse Document Frequency and Bidirectional Encoder Representations from Transformers combined with Cosine Similarity) and perform a qualitative compatibility analysis to establish ground truth. Based on this analysis, we apply the Receiver Operating Characteristic Curve technique to define threshold values for compatibility assessment. The threshold values were used to suggest compatible DTM-DMM pairings, resulting in nine DTM-DMM binomials for Small and Medium-sized Enterprises. The findings support managers and practitioners in selecting DTM-DMM pairs to guide DT initiatives while offering academics a mixed-methods approach based on the similarity analysis field to evaluate artefact compatibility systematically. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

Abstract
Fighting the propagation of misinformation within a social media group or community by focusing on identifying dishonest members who deliberately try to quash any constructive social movement is very challenging because such people use advanced tactics to create division and doubt by manipulating information. The present research aims to develop a hybrid heuristic model to identify those who intentionally spread misleading information on social media to jeopardize a social movement. We frame this issue under the heading of Graph Semi-supervised Learning (GSSL), and we propose a hybrid model that falls under the heuristic approach, called Label Propagation-Gated Recurrent Unit (LP-GRU). LP-GRU can effectively identify perpetrators of disinformation within social communities by fusing community structure from the Label Propagation algorithm with behavioral patterns identified by GRU. Compared to previous heuristic approaches, we achieve up to 76% accuracy when using the LP-GRU model on augmented semi-synthetic social network data. © 2025 IEEE.

Abstract

Abstract

Abstract