Journal of Systems and Information Technology

Ali, Omar; Zaidi, Syed Faizan Hussain; Thanasi-Boçe, Marsela

2024 Journal of Systems and Information Technology

doi: 10.1108/jsit-09-2021-0188

The main purpose of this research study is to investigate and examine the factors that might influence the intention to adopt and use mobile payment and their relationships during the COVID-19 pandemic.Design/methodology/approachThis research study used both mobile payment adoption literature, The Technology Adoption Model and Unified Theory of Acceptance and Use of Technology, to propose a conceptual framework for mobile payment adoption. Quantitative method is used in which 306 participants responded to an online survey to validate the proposed conceptual framework.FindingsThe introduced integrated model embraced perceived risk, transaction transparency, mobile payment usefulness, social influence, performance expectation as independent variables and usage continuation intention to adopt mobile payment as the dependent variable. The results from data analysis have statistically revealed significant relationships and a positive impact of perceived risk, mobile payment usefulness, social influence and performance expectation. Also, the results identified a negative impact for the transaction transparency factor. As this research study is conducted at a later stage of the COVID-19 pandemic, it adds value to the existing literature by providing insights to business managers on the factors influencing mobile payment usage and other implications related to increasing the market potential for businesses in the new normality of the coronavirus pandemic.Originality/valueThis paper offers a combination conceptual framework of mobile payment adoption based on a literature review on mobile payment adoption from information systems perspective. It adapts integrated model to establish a more comprehensive innovation adoption framework for mobile payment.

Bhattacharjee, Biplab; Unni, Kavya; Pratap, Maheshwar

2024 Journal of Systems and Information Technology

doi: 10.1108/jsit-06-2020-0120

Product returns are a major challenge for e-businesses as they involve huge logistical and operational costs. Therefore, it becomes crucial to predict returns in advance. This study aims to evaluate different genres of classifiers for product return chance prediction, and further optimizes the best performing model.Design/methodology/approachAn e-commerce data set having categorical type attributes has been used for this study. Feature selection based on chi-square provides a selective features-set which is used as inputs for model building. Predictive models are attempted using individual classifiers, ensemble models and deep neural networks. For performance evaluation, 75:25 train/test split and 10-fold cross-validation strategies are used. To improve the predictability of the best performing classifier, hyperparameter tuning is performed using different optimization methods such as, random search, grid search, Bayesian approach and evolutionary models (genetic algorithm, differential evolution and particle swarm optimization).FindingsA comparison of F1-scores revealed that the Bayesian approach outperformed all other optimization approaches in terms of accuracy. The predictability of the Bayesian-optimized model is further compared with that of other classifiers using experimental analysis. The Bayesian-optimized XGBoost model possessed superior performance, with accuracies of 77.80% and 70.35% for holdout and 10-fold cross-validation methods, respectively.Research limitations/implicationsGiven the anonymized data, the effects of individual attributes on outcomes could not be investigated in detail. The Bayesian-optimized predictive model may be used in decision support systems, enabling real-time prediction of returns and the implementation of preventive measures.Originality/valueThere are very few reported studies on predicting the chance of order return in e-businesses. To the best of the authors’ knowledge, this study is the first to compare different optimization methods and classifiers, demonstrating the superiority of the Bayesian-optimized XGBoost classification model for returns prediction.

Tukamuhabwa, Benjamin R.; Mutebi, Henry; Mbatsi, Anne

2024 Journal of Systems and Information Technology

doi: 10.1108/jsit-11-2020-0242

The purpose of this paper is to propose and validate a theoretical model to investigate the relationship between self-organisation, information integration, adaptability and supply chain agility in humanitarian organisations.Design/methodology/approachA theoretical model was developed from extant studies and assessed through a structured questionnaire survey of 86 humanitarian organisations operating in South Sudan. The data were analysed using partial least square structural equation modelling.FindingsThe study found that self-organisation has a discernible positive influence on supply chain agility not only directly but also indirectly through adaptability. Further, information integration does not significantly influence supply chain agility directly but is fully mediated by adaptability. Together, the antecedent variables account for 53.9% variance in supply chain agility.Research limitations/implicationsThis study contributes to providing an empirical understanding of a humanitarian supply chain as a complex adaptive system and hence the need to incorporate self-organising and adaptive dimensions in supply chain management practice. Furthermore, it confirms the centrality of the complex adaptive system feature of adaptability when building supply chain agility through self-organisation and information integration.Practical implicationsThe findings provide a firm ground for managerial decisions on investment in self-organisation and information integration dimensions so as to enhance adaptability and improve supply chain agility in humanitarian organisations.Originality/valueThis study is distinctive in the sense that it uses the complex adaptive system variables to empirically validate the relationships between self-organisation, information integration, adaptability and supply chain agility in humanitarian organisations in the world’s youngest developing economy with a long history of conflict and humanitarian intervention. The mediating influence of adaptability examined in this study is also novel.

Tewari, Shuchita Pant; Misra, Richa; Nagdev, Kritika; Sharma, Himani

2024 Journal of Systems and Information Technology

doi: 10.1108/jsit-12-2023-0329

Online health communities (OHC) can transform the healthcare industry, particularly in developing economies. Technology advancement and increased health literacy pave the way for these communities to become powerful tools for empowering patients. The purpose of this study was to empirically validate the linkages between social support and how it overarchingly influences patient compliance. Following social support theory, this study delineates how support from the community affects the patient–physician relationship (PERP) and consequently patient compliance regarding the treatment plan. This study also invents the role of patient trust in an OHC in moderating the relationship between PERP and engagement.Design/methodology/approachThis paper is based on social support and empowerment theories to investigate the importance of social support in improving patients’ health behaviours and health outcomes via patient empowerment, patient engagement and patient compliance. The authors surveyed users from three Facebook cancer communities in India to collect data. The authors used partial least squares structured equation modelling and necessary condition analysis (NCA) with 265 participants to support the proposed model.FindingsThe result demonstrates that PERP is a crucial factor for patient engagement in OHC, and patient engagement has a significant effect on patient compliance. The results also showed that trust was a significant moderator between PERP and engagement. The NCA analysis shows all the relationships are significant; however, emotional support is not a necessary condition for PERP.Research limitations/implicationsBy empowering cancer patients and enabling them to meet their emotional and informational needs through OHCs, the study model can aid in the development of solutions that will improve compliance with their treatment in an emerging economic context. The findings indicate the potential chain reaction of social support and PERP in online cancer health communities. This study also contributes to quantifying the social impacts of online healthcare services and how to enhance the healthcare compliance framework.Originality/valueThis study combines social support and empowerment theory with patient, physician, and technology to provide a fine-grained picture of PERP in OHC. It explains how social support in OHC promotes self-care behaviour. This linkage validation enables readers and the community at large to gain a more nuanced understanding of how social support – through PERP, engagement and trust – enables patient compliance using primary data.

Dakiche, Narimene; Benatchba, Karima; Benbouzid-Si Tayeb, Fatima; Slimani, Yahya; Brahmi, Mehdi Anis

2024 Journal of Systems and Information Technology

doi: 10.1108/jsit-02-2021-0024

This paper aims to introduce a novel modularity-based framework, Com_Tracker, designed to detect and track community structures in dynamic social networks without recomputing them from scratch at each snapshot. Despite extensive research in this area, existing approaches either require repetitive computations or fail to capture key community behavioral events, both of which limit the ability to generate timely and actionable insights. Efficiently tracking community structures is crucial for real-time decision-making in rapidly evolving networks, while capturing behavioral events is necessary for understanding deeper community dynamics. This study addresses these limitations by proposing a more efficient and adaptive solution. It aims to answer the following questions: How can we efficiently track community structures without recomputation? How can we detect significant community events over time?Design/methodology/approachCom_Tracker models dynamic social networks as a sequence of snapshots. First, it detects the community structure of the initial snapshot using a static community detection algorithm. Then, for each subsequent time step, Com_Tracker updates the community structure based on the previous snapshot, allowing it to track communities and detect their changes over time. The locus-based adjacency encoding scheme is adopted, and Pearson’s correlation guides the construction of neighboring solutions.FindingsExperiments conducted on various networks demonstrate that Com_Tracker effectively detects community structures and tracks their evolution in dynamic social networks. The results highlight its potential for real-time tracking and provide promising performance outcomes.Practical implicationsCom_Tracker offers valuable insights into community evolution, helping practitioners across fields such as resource management, public security, marketing and public health. By understanding how communities evolve, decision-makers can better allocate resources, enhance targeted strategies and predict future community behaviors, improving overall responsiveness to changes in network dynamics.Originality/valueCom_Tracker addresses critical gaps in existing research by combining the strengths of modularity maximization with efficient tracking of community changes. Unlike previous methods that either recompute structures or fail to capture behavioral events, Com_Tracker provides an incremental, adaptive framework capable of detecting both community evolution and behavioral changes, enhancing real-world applicability in dynamic environments.

Purusottama, Ambara; Simatupang, Togar Mangihut; Sunitiyoso, Yos

2024 Journal of Systems and Information Technology

doi: 10.1108/jsit-09-2023-0212

The growing discussion on blockchain and business models often falls short of demonstrating and evaluating systems consistently exposed to settings of dynamic complexity. Therefore, in practicing systems thinking, this study aims to provide a depiction of dynamic complexity in blockchain business models and develop policy-based scenarios to enhance blockchain-based systems behavior.Design/methodology/approachThis study integrated the soft system dynamic (SD) methodology approach, which focuses on a situation analysis and SDs in policy design. This single case study chose a firm engaged in the content industry, where the adoption of blockchains is a solution to tackle the industry’s significant challenges. Data were collected using a qualitative approach and then adapted into a simulation model.FindingsThe study pinpointed key parameters significantly affecting the system through a sensitivity analysis. Then, this experimental study found that all improvement initiatives delivered better system performance. At the same time, the study also identified counterintuitive findings, where the interventions using multiple value subsystems had insignificant effects on the system compared to a single advent.Originality/valueThis study illuminates the growing field of blockchain and business models through system modeling and experimentation, using an integrative approach like soft system dynamics methodology. It also identifies and demonstrates value distribution and the dynamic complexity inherent in the blockchain business model.

Bao, Zheshi

2024 Journal of Systems and Information Technology

doi: 10.1108/jsit-08-2022-0201

The phenomenon of nonposting behavior, known as lurking, has become increasingly prevalent on social networking sites (SNS). This study aims to understand why certain users are inclined to lurk on SNS by proposing a theoretical framework that integrates self-presentational concerns, SNS fatigue and social presence.Design/methodology/approachBuilding upon the theoretical framework, a moderated mediation model is established to illustrate the mechanisms of lurking on SNS. Survey data were collected from 616 SNS users through an online survey and analyzed using the SPSS macro PROCESS.FindingsThe findings show that self-presentational concerns have positive and direct effects on lurking. Moreover, the relationship between self-presentational concerns and lurking is partially mediated by SNS fatigue. Furthermore, both the direct effect and the mediating effect are moderated by social presence.Originality/valueThis study offers a novel theoretical perspective on lurking behavior by introducing a moderated mediation model. The findings reveal intricate mechanisms underlying this specific SNS usage behavior and its connections to both self-presentational concerns and SNS fatigue, thereby enriching the existing literature on user engagement and inactivity on SNS. Furthermore, this research highlights the pivotal role of social presence in moderating the effects of self-presentational concerns, offering new insights into the dynamics of online social interactions.