International Journal of Information Management Data Insights最新文献

{"title":"A multimodal framework for enhancing E-commerce information management using vision transformers and large language models","authors":"Anitha Balachandran ,&nbsp;Mohammad Masum","doi":"10.1016/j.jjimei.2025.100355","DOIUrl":"10.1016/j.jjimei.2025.100355","url":null,"abstract":"<div><div>In the rapidly advancing field of visual search technology, traditional methods that rely only on visual features often struggle with accuracy and relevance. This challenge is particularly evident in e-commerce, where precise product recommendations are critical, and is further complicated by keyword stuffing in product descriptions. To address these limitations, this study introduces BiLens, a multimodal recommendation framework that integrates both visual and textual information. BiLens leverages large language models (LLMs) to generate descriptive captions from image queries, which are transformed into word embeddings, and extracts visual features using Vision Transformers (ViT). The visual and textual representations are integrated using an early fusion strategy and compared using cosine similarity, enabling deeper contextual understanding and enhancing the accuracy and relevance of product recommendations in capturing customer intent. A comprehensive evaluation was conducted using Amazon product data across five categories, testing various image captioning models and embedding methods—including BLIP-2, ViT-GPT2, BLIP-Image-Captioning-Large, Florence-2-large, GIT (microsoft/git-base-coco), Word2Vec, GloVe, BERT, and ELMo. The combination of Florence-2-large and BERT emerged as the most effective, achieving a <span><math><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>c</mi><mi>i</mi><mi>s</mi><mi>i</mi><mi>o</mi><mi>n</mi></mrow></math></span> of <span><math><mrow><mn>0.81</mn><mspace></mspace><mo>±</mo><mspace></mspace><mn>0.14</mn></mrow></math></span> and <span><math><mrow><mi>F</mi><mn>1</mn></mrow></math></span> score of <span><math><mrow><mn>0.49</mn><mspace></mspace><mo>±</mo><mspace></mspace><mn>0.16</mn></mrow></math></span>. This setup was further validated on the Myntra dataset, showing generalizability with <span><math><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>c</mi><mi>i</mi><mi>s</mi><mi>i</mi><mi>o</mi><mi>n</mi></mrow></math></span> of <span><math><mrow><mn>0.59</mn><mspace></mspace><mo>±</mo><mspace></mspace><mn>0.27</mn></mrow></math></span>, <span><math><mrow><mi>r</mi><mi>e</mi><mi>c</mi><mi>a</mi><mi>l</mi><mi>l</mi></mrow></math></span> of <span><math><mrow><mn>0.47</mn><mspace></mspace><mo>±</mo><mspace></mspace><mn>0.25</mn></mrow></math></span>, and <span><math><mrow><mi>F</mi><mn>1</mn></mrow></math></span> score of <span><math><mrow><mn>0.52</mn><mspace></mspace><mo>±</mo><mspace></mspace><mn>0.24</mn></mrow></math></span>. Comparisons with image-only and text-only baselines confirmed the superiority of the fusion-based approach, with statistically significant improvements in F1 scores, underscoring BiLens’s ability to deliver more accurate, context-aware product recommendations.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 2","pages":"Article 100355"},"PeriodicalIF":0.0,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144580826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic review and future agenda on continuance intentions in mobile apps","authors":"Suryati Veronika ,&nbsp;Michael S.W. Lee ,&nbsp;Bodo Lang ,&nbsp;Pragea Putra","doi":"10.1016/j.jjimei.2025.100352","DOIUrl":"10.1016/j.jjimei.2025.100352","url":null,"abstract":"<div><div>Technology changes at ever increasing speeds. Therefore, it is crucial for practitioners and academics to understand why users’ intend to continue or discontinue their usage. This paper presents a current and comprehensive systematic literature review on continuance intentions for mobile applications. The review analyzes 119 studies from the Scopus database (January 2019–December 2023) using the PRISMA, SPAR, and TCCM frameworks. It identifies key theoretical models, determinants of mobile app continuance intention, research methods, existing gaps, and future research directions. Findings reveal that several well-recognised theoretical models are frequently applied in the literature on continuance intention. Consequently, the variables derived from these models are among the most commonly measured by researchers. Additionally, the majority of studies in this area employ quantitative methods, with structural equation modelling being most widely used. This review categorises the literature based on mobile application classifications and six distinct sets of factors influencing continuance intention: psychological, technical, social, behavioural, contextual, and barriers. Furthermore, it explores the outcomes associated with continuance intention. The paper identifies two primary areas for future research: the development of a conceptual framework and research design. It also highlights research opportunities related to emerging technologies and the gap between intentions and actual behaviours.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 2","pages":"Article 100352"},"PeriodicalIF":0.0,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144534885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-variate LSTM with attention mechanism for the Indian stock market","authors":"Ashy Sebastian,&nbsp;Dr. Veerta Tantia","doi":"10.1016/j.jjimei.2025.100350","DOIUrl":"10.1016/j.jjimei.2025.100350","url":null,"abstract":"<div><div>The advent of attention mechanism has surpassed numerous benchmarks and enabled widespread progress in the realm of natural language processing (NLP). Nevertheless, they have not been adequately leveraged in a time-series context. Accordingly, this paper aims to address this issue by proposing a hybrid, deep-learning model that integrates attention mechanisms and multi-variate long short-term memory (LSTM) for financial forecasting in the Indian stock market. Our model yields superior results as compared to baseline and state-of-the-art models evaluated using MAE and RMSE. Moreover, we employed a modern evaluation criterion based on the methodology advocated by Diebold–Mariano, known as the Diebold–Mariano test (DM test), as a new criterion for evaluation based on statistical hypothesis tests. DM test has been applied in this study to distinguish the significant differences in forecasting accuracy between LSTM with attention and other models. From the results and according to DM-test it is observed that the differences between the forecasting performances of models are significant and that attention mechanism could enhance the accuracy in predicting stock prices by allowing the model to prioritize and concentrate on the most important features and patterns in the data while avoiding overfitting and noise.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 2","pages":"Article 100350"},"PeriodicalIF":0.0,"publicationDate":"2025-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144330579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transformer-based model for moroccan Arabizi-to-Arabic transliteration using a semi-automatic annotated dataset","authors":"Soufiane Hajbi ,&nbsp;Omayma Amezian ,&nbsp;Mouhssine Ziyad ,&nbsp;Issame El Kaime ,&nbsp;Redouan Korchyine ,&nbsp;Younes Chihab","doi":"10.1016/j.jjimei.2025.100351","DOIUrl":"10.1016/j.jjimei.2025.100351","url":null,"abstract":"<div><div>Language models have recently achieved state-of-the-art results in tasks such as translation, sentiment analysis, and text classification for high-resource languages. However, dedicated models for low-resource languages remain scarce, largely due to a lack of annotated data and linguistic resources. Most efforts focus on fine-tuning models trained on high-resource languages using limited data, resulting in a substantial performance gap. Moroccan Darija (MD), widely spoken in Morocco, lacks language resources and dedicated models. Additionally, MD texts often employ the Arabizi writing form, which combines Latin characters and numbers with Arabic script, further complicating Natural Language Processing (NLP) tasks. This work presents the first transformer-based model designed specifically for transliterating Moroccan Arabizi to Arabic. The approach leverages a character-level modeling architecture and a semi-automatically generated dataset containing over 33k word pairs, capturing significant linguistic diversity. The model achieves a state-of-the-art word transliteration accuracy (WTA) of 93 % and a character error rate (CER) of 4.73 % on unseen Moroccan Arabizi data, highlighting the potential of transformer models to improve transliteration accuracy for low-resource languages, particularly MD.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 2","pages":"Article 100351"},"PeriodicalIF":0.0,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MultiBanFakeDetect: Integrating advanced fusion techniques for multimodal detection of Bangla fake news in under-resourced contexts","authors":"Fatema Tuj Johora Faria ,&nbsp;Mukaffi Bin Moin ,&nbsp;Zayeed Hasan ,&nbsp;Md. Arafat Alam Khandaker ,&nbsp;Niful Islam ,&nbsp;Khan Md Hasib ,&nbsp;M.F. Mridha","doi":"10.1016/j.jjimei.2025.100347","DOIUrl":"10.1016/j.jjimei.2025.100347","url":null,"abstract":"<div><div>The rise of false news in recent years poses significant risks to society. As misinformation spreads rapidly, automated detection systems are essential to mitigate its impact. However, most existing methods rely solely on textual analysis, limiting their effectiveness. The challenge is further compounded by the lack of a large-scale, multimodal dataset for Bangla fake news detection, as existing datasets are either small or unimodal. To address this, we introduce <strong>MultiBanFakeDetect</strong>, a novel multimodal dataset integrating both textual and visual information. This dataset comprises manually curated real and fake news samples from various online sources. Additionally, we propose <strong>MultiFusionFake</strong>, a hybrid multimodal fake news detection framework that fuses text and image modalities using an Early Fusion approach while also comparing Late and Intermediate fusion techniques. Our experiments show that MultiFusionFake, combining DenseNet-169 and mBERT, achieves 79.69% accuracy, outperforming the text-only mBERT model’s 73.13%, reflecting a 6.56 percentage point improvement. These results underscore the advantages of multimodal over unimodal methods. To the best of our knowledge, this is the first study on multimodal fake news detection in the under-resourced Bangla context, offering a promising approach to combating online misinformation.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 2","pages":"Article 100347"},"PeriodicalIF":0.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI literacy and e-entrepreneurial intention: A serial mediation model of e-entrepreneurial self-efficacy and e-entrepreneurial identity aspiration","authors":"Cong Doanh Duong","doi":"10.1016/j.jjimei.2025.100349","DOIUrl":"10.1016/j.jjimei.2025.100349","url":null,"abstract":"<div><div>The rapid integration of artificial intelligence in education and entrepreneurship highlights the importance of artificial intelligence literacy as a foundational skill for fostering entrepreneurial intentions in the digital economy. This study applies the stimulus-organism-response framework to examine how artificial intelligence literacy influences e-entrepreneurial intention through the mediating roles of e-entrepreneurial self-efficacy and e-entrepreneurial identity aspiration. Data were collected from 504 undergraduate students at leading universities in Vietnam, using a stratified sampling approach. The results demonstrate that artificial intelligence literacy significantly enhances e-entrepreneurial self-efficacy and e-entrepreneurial identity aspiration, which are essential psychological mechanisms for driving entrepreneurial intention. Notably, the direct relationship between artificial intelligence literacy and e-entrepreneurial intention was not significant, emphasizing the importance of psychological pathways. The findings also reveal a serial mediation effect, where artificial intelligence literacy influences e-entrepreneurial intention sequentially through e-entrepreneurial self-efficacy and e-entrepreneurial identity aspiration. This research advances the theoretical understanding of the link between technological literacy and entrepreneurial behavior, particularly in the context of e-entrepreneurship. It expands the application of the stimulus-organism-response framework to entrepreneurial studies, offering a robust explanation of the mechanisms underlying the formation of entrepreneurial intention. Practically, educational institutions and policymakers should focus on enhancing artificial intelligence literacy while fostering self-efficacy and identity aspiration to promote entrepreneurial engagement among students.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 2","pages":"Article 100349"},"PeriodicalIF":0.0,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144296877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Media and information literacy among pre-service teachers: A systematic review of key trends and gaps (2013–2024)","authors":"Shi Chen ,&nbsp;Sabariah Mohamed Salleh ,&nbsp;Mohd Azul Mohamad Salleh","doi":"10.1016/j.jjimei.2025.100348","DOIUrl":"10.1016/j.jjimei.2025.100348","url":null,"abstract":"<div><div>Media and information literacy (MIL) is gaining academic attention due to media technology advancements and evolving communication, with pre-service teachers (PTs) playing a crucial role in preparing future citizens. This systematic review examined 40 articles focusing on PTs to identify their theoretical characteristics and methodological patterns. The methodology follows the PRISMA statement and covers research from 2013 to 2024. All of these selected papers are evaluated using a quality assessment tool, Quality Assessment Tool for papers with Diverse Designs (QATSDD). The review identifies a regional concentration of PTs’ MIL research in Europe and Asia. This demonstrates how regional settings and national policies have a significant impact on MIL research, as do differences in terminology usage and conceptual understanding. However, aspects of PTs’ MIL that support teaching practices remain underexplored in the existing literature, indicating a critical gap in preparing PTs for their roles as educators. Concerns regarding the credibility of results are further raised by the extensive use of self-reported assessments. Furthermore, because they have a big impact on PTs' MIL abilities, demographic factors including gender and regional discrepancies need constant monitoring. The findings highlight the need to integrate MIL into teacher education to enhance teaching competencies and address regional and demographic disparities, ensuring preservice teachers are equipped for modern educational demands.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 2","pages":"Article 100348"},"PeriodicalIF":0.0,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144254082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial: Artificial intelligence, digitization, sustainable development goals & global disruptions","authors":"Sonali Bhattacharya ,&nbsp;Manish Sinha ,&nbsp;Vincent Dutot ,&nbsp;Shahriar Akter ,&nbsp;V G Venkatesh","doi":"10.1016/j.jjimei.2025.100334","DOIUrl":"10.1016/j.jjimei.2025.100334","url":null,"abstract":"<div><div>This editorial summarizes the content of the special issue. It begins with the motivations behind the initiation of the special issue proposal and is followed by summarization of existing literature on the topic through a bibliometric analysis from a SCOPUS database. Finally, it shortly presents the special issue articles on the topical areas such as artificial intelligence, digitization, sustainable goals, and global disruptions. The deliberations will help both academics and professionals to expand their knowledge boundaries of these domains.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 1","pages":"Article 100334"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144231612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The interplay of virtualisation, work design, and business process management: A mixed-methods study","authors":"Luke Bartlett ,&nbsp;Muhammad Ashad Kabir ,&nbsp;Jun Han","doi":"10.1016/j.jjimei.2025.100345","DOIUrl":"10.1016/j.jjimei.2025.100345","url":null,"abstract":"<div><div>Business Process Management (BPM) has emerged as a fundamental aspect of modern business, revolutionising task execution and operational efficiency. This study explored the relationship between virtualisation and work design as well as their impact on BPM system design. An experiment was established where two simulated BPM systems were given to users to operate, one taking advantage of virtualisation and work design, the other not. A mixed method approach involving both quantitative and qualitative approaches was applied to system and usage data collected from these systems as well as a user survey. The analysis illustrates the potential significance of integrating virtualisation and work design in BPM systems. We provide a reflective discussion linking theoretical understanding with empirical evidence. We found that both components not only enhanced the performance and effectiveness of BPM systems, but also improved flexibility, scalability, and user experience. The data supports that a relationship between virtualised resources and work design exists when incorporated into BPM system design. Further, it provides valuable insights into how these elements interact and impact each other. The findings in this study contribute to building a case that establishes the effect of virtualisation and work design on the usability of BPM systems. These findings have very real practical applications that can be applied to existing BPM systems as well as the architecture of future systems. A number of the recommendations made as a result of this research have been applied to commercially available BPM systems.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 2","pages":"Article 100345"},"PeriodicalIF":0.0,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144168376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impacts of e-RLSQ on repurchase intention in Vietnam’s e-commerce market: The mediating role of customer satisfaction and trust","authors":"Anh Duc Do ,&nbsp;Dieu Linh Ha ,&nbsp;Minh Trang Pham ,&nbsp;Mai Anh Thi Khuat ,&nbsp;Van Anh Thi Le ,&nbsp;Dieu Ngoc Dieu Nguyen ,&nbsp;Toan Quoc La","doi":"10.1016/j.jjimei.2025.100346","DOIUrl":"10.1016/j.jjimei.2025.100346","url":null,"abstract":"<div><div>In the competitive e-commerce landscape, effective product returns management is crucial for customer retention. This study investigate the impact of electronic reverse logistics service quality (e-RLSQ) on repurchase intention, emphasizing the mediating roles of customer satisfaction and trust in Vietnam’s e-commerce market. Using Partial Least Squares Structural Equation Modeling (PLS-SEM), it explores the relationships between e-RLSQ dimensions, customer perceptions, and repurchase behavior. The findings reveal that Information Quality (INF) and Convenience (CON) significantly enhance customer satisfaction, while Remedies (REMD) and INF foster trust. Both satisfaction and trust mediate the relationship between e-RLSQ and repurchase intention, with satisfaction exerting a stronger influence. These insights highlight the importance of optimizing return processes and ensuring transparent communication to foster long-term customer loyalty. This study contributes to the limited literature on e-RLSQ in emerging markets and provide strategic implications for e-commerce platforms to enhance service quality and customer retention.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 2","pages":"Article 100346"},"PeriodicalIF":0.0,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144154950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}