Open Journal in Information Systems Engineering

ROISI - ISSN 2634-1468 - © ISTE Ltd

Journal issues

---

Recent articles

Editorial

Ce numéro spécial de la Revue ouverte d’ingénierie des systèmes d’information est consacré à une sélection d’articles étendus issus de la conférence INFORSID 2025.

---

Hybrid Approach Combining Markov, HMM, and RNN to Detect Learning Blockages in Programming Résumé

Understanding the learning process in programming poses a complex challenge due to the sequential and multidimensional nature of students’ interactions with digital environments. This study analyzes the activity logs of 70 beginner computer science students engaged in problem-solving programming tasks to identify encountered difficulties and propose tailored pedagogical interventions.We present a hybrid approach combining Markov Chains to model transitions between types of actions, Hidden Markov Models (HMM) to infer latent learning states (progress, hesitation, blockage), and Recurrent Neural Networks (RNN) enhanced with an attention mechanism to detect critical moments. This combination allows for the simultaneous exploitation of behavioral, cognitive, and sequential dimensions of learning.The methodology involves extracting temporal and structural features from the activity logs, modeling cycles of exploration, hesitation, and blockage, and integrating them into a unified framework to predict learning states. The data comes from several standardized practical work sessions, totaling over 80 MB of timestamped traces, collected with consent and stored in a NoSQL database. Each session is divided into sequences corresponding to coherent problem-solving phases, enabling a fine-grained analysis of learning trajectories.Experimental results show that the proposed hybrid model outperforms traditional approaches, achieving an accuracy of 93.5% and significantly reducing false positives in blockage detection.
The multidimensional analysis offers a richer understanding of learning trajectories, including their invisible dimensions such as unproductive engagement or phases of uncertainty.This research paves the way for intelligent educational platforms capable of providing personalized real-time feedback, sensitive to micro-indicators of activity, cognitive intensity, and individual context, thereby contributing to improved student success and enhanced engagement.

---

An integrative conceptual framework for data and information governance

Data and information governance is an important activity for organizations seeking to leverage data as a strategic asset. Its goal is to maximize value while minimizing costs and risks. In this article, we present a conceptual framework for data and information governance that offers a holistic view, enriching existing academic and professional frameworks and models. Using bibliometric techniques, we analyze the existing literature to identify the key elements of data and information governance, including its intellectual structure, research themes, and the most influential articles that form its backbone. We compare the common and specific spheres of data governance and information governance. In a second step, we propose an enriched conceptual framework based on systems theory. This framework encompasses five key dimensions: purpose, structure, activities, environment, and outcome. It also allows for consideration of the interaction between these dimensions. To illustrate this conceptual framework, we describe how it was used to structure the questions in a barometer designed to assess the maturity of data and information governance in organizations.

---

A study on the bridge between information system security and environmental responsibility: the case of optimising vulnerability management in a cloud-based organisation

This paper examines information system (IS) security as a foundational pillar of organisational continuity and resilience. In response to growing environmental responsibility, it becomes essential to adopt a vulnerability management approach that goes beyond purely technical considerations. The study proposes integrating business context and sectorspecific
priorities into the vulnerability prioritisation process, with the aim of optimising resource allocation and reducing the energy footprint of security remediation. We suggest extending the Common Vulnerability Scoring System (CVSS) by incorporating organisational criteria and analysing vulnerability chaining. This approach is illustrated through practical case
studies (banking, healthcare, and websites hosting), demonstrating that contextual factors significantly influence remediation priorities and promote more sustainable cybersecurity practices. The objective is to reconcile security, sustainability, and cost, positioning vulnerability management as a strategic lever for responsible IS governance.

---

Computational Characterization and Taxonomy of Patent Writing Styles: Towards Stylometric Automation of Technical Drafting

In the field of intellectual property, patents are essential technical and legal documents whose drafting requires expertise that combines technical, legal, and linguistic skills. Patent drafting styles vary considerably depending on technological domains, jurisdictions, and protection strategies. This article proposes the design of SCASB (System for Stylometric Characterization and Automation of Patents), an approach that, for the first time, unifies the technical, legal, and stylistic dimensions within a coherent computational framework. We propose a two-dimensional taxonomy of patent analysis approaches (automatic computational methods for document analysis × level of analytical granularity) and highlight current shortcomings. Our system builds upon the rapid advances in artificial intelligence technologies, particularly natural language processing (NLP). This work opens the path toward intelligent automation of technical drafting that accounts for the stylistic nuances specific to each jurisdiction and protection strategy.

---

Edito – Special Issue

Ce numéro spécial de la Revue Ouverte de l’Ingénierie des Systèmes d’Information se consacre à la thématique « L’industrie culturelle face à la transformation numérique », un sujet central pour comprendre les évolutions récentes des pratiques, des organisations et des usages culturels à l’ère du numérique. La culture, qui englobe croyances, pratiques, normes, valeurs, traditions et connaissances partagées, façonne les interactions sociales et les modes de production et de consommation. La transformation numérique modifie profondément ces processus, en offrant de nouvelles formes d’accès, de consommation et de création culturelle

---

The advent of AI in the cultural and creative industries: from the mythology of progress to the collective reappropriation of technology

This article questions the dominant narratives on generative artificial intelligence (GAI) in the cultural and creative industries, comparing it with the social and economic dynamics that accompany its integration into work processes and collectives. Three myths are analyzed: the disappearance of professions and jobs, the obsolescence of skills, and productivity gains. Using a multidisciplinary approach combining expertise in AI, a sociotechnical approach, and field approach, we show that the situation reveals structural imbalances rather than producing them: the gradual deterioration of processes, value capture, and deskilling are telling illustrations of this. We highlight real uses that tend to reconfigure these technologies and propose concrete avenues for collective reappropriation through the empowerment of actors, usage labs, and technological social dialogue.

---

Netflix: A Black Box Within a Black Box

This article focuses on the recommendation system of the subscription video-on-demand (SVOD) platform Netflix®, specifically exploring what can be understood from an end-user perspective. To this end, we investigate how viewing choices influence the recommendations displayed during the subsequent platform visit. To conduct this analysis, we designed two experiments comparing two user profiles: one long-standing profile active for 7 years, and another newly created profile. We concentrated on elements observable directly by the user: categories, recommended titles within personalized categories, and the « top banners » displayed prominently on the homepage. Our findings revealed the following: first, recommendations for a recent profile are more quickly and strongly influenced by the content viewed on that profile, whereas an older profile shows little change. Second, the new profile receives recommendations spanning a wide variety of genres, including popular content as well as some personalized suggestions. Finally, over time, while the older profile initially received increasing numbers of documentary recommendations based on its viewing history, only a few days of inactivity were enough for these recommendations to disappear entirely. Conversely, the recent profile continued to receive documentary suggestions. These experiments also allowed us to observe the evolution of suggested categories for each profile. The significant diversity of categories and the variability in how films are ranked within them emerged as important factors. This observation raises further questions about how the recommendation system creates and uses categories to encourage user engagement.

---

Risks and benefits of conversational agents for naive access to scientific knowledge

This article examines the risks associated with using generative conversational agents such as ChatGPT to access scientific knowledge (and, more broadly, technical and medical knowledge). The evolution of the Web has been accompanied by a shift in gatekeeping towards algorithmic forms, of which generative artificial intelligences are the latest manifestation. Their limitations, most notably hallucinations and various biases, are, however, well documented. Are these conversational agents therefore suitable for tasks of scientific mediation? Their performance depends not only on the properties of their algorithms but also on the availability of training data in sufficient quantity and quality. Access to content on news websites is, moreover, frequently hindered by publishers. What, then, of scientific content managed by commercial academic publishers? Must developers of generative chatbots rely on lower-quality material, with harmful consequences for the reliability of responses? We therefore analyse the risks of scientific misinformation stemming from constraints on data access. We then discuss these risks more broadly, when such agents are used as scientific mediators, across different usage scenarios.

---

International cultural law to the test of synthetic media

Synthetic media produced by generative artificial intelligence (GAI) tools are flooding the Web, causing risks of cultural harm that should be addressed. Yet, the question of cultural harm resulting from the dissemination of synthetic media has only been partially addressed in the legal literature. This article aims to fill this gap, by exploring the legal implications of culturally harmful synthetic media. To that end, this article analyzes the key concept of cultural harm and the role played by cultural rights and the principle of cultural diversity in its characterization. The ways in which synthetic media can cause cultural harm and the potential legal consequences are then discussed. It will be shown that, while international law provides mechanisms for preventing cultural harm, there are few means to really take into account the specificities of culturally harmful synthetic media.