Acta Informatica Pragensia - Forthcoming articles

Fairness-Aware Multimodal Machine Learning for Retail Stock Prediction from Sentiment and Market Data

Sanjay Rastogi, Kamal Upreti, Uma Shankar, Pravin Ramdas Kshirsagar, Tan Kuan Tak, Rituraj Jain, Ganesh Veluswwamy Radhakrishnan

Acta Informatica Pragensia X:X | DOI: 10.18267/j.aip.299384  

Background: The introduction of retail investors to AI-powered trading platforms and especially on emerging markets, has resulted in a new set of risks linked to algorithmic bias and financial forecasting fairness. Social media sentiment and structured data multimodal strategies have demonstrated a potential, but frequently do not have ethical considerations.Objective: This work proposes a multimodal model predictive control (MPC) framework grounded in fairness-based forecasting of next-day returns on stock in stock market settings, particularly ethical behaviour and transparency of the model on retail markets.Methods: We combine BERT-based sentiment...

SKR1: Benchmark for Testing Knowledge About Slovak Realia for Large Language Models

Marek Dobeš

Acta Informatica Pragensia X:X | DOI: 10.18267/j.aip.300298  

Background: To objectively evaluate the capabilities of large language models (LLMs), we need to develop tools that enable such assessment. While numerous benchmarks exist, the vast majority are in English and focus on general knowledge, often overlooking the cultural and factual specifics of smaller countries.Objective: Currently, there is no benchmark that tests LLMs΄ knowledge of Slovak realia. At the same time, LLM performance in this domain remains inadequate. To objectively measure and compare these capabilities, our goal is to develop and validate a specialized benchmark for assessing LLMs΄ knowledge of Slovak cultural and factual...

Artificial Intelligence Applications in Consumer Behaviour Analysis: A Systematic Review, Mapping Trends and Challenges

Adrián No-Pérez, Sandra Castro-González

Acta Informatica Pragensia X:X | DOI: 10.18267/j.aip.301322  

Background: The vast amounts of data generated by consumers require new forms of processing, in which artificial intelligence stands out for its ability to analyse them more quickly and deeply. However, although there is abundant literature on artificial intelligence (AI) and consumption, most of it focuses on its impact on consumer behaviour rather than its usefulness in enhancing understanding.Objective: The aim of this study is to conduct a thorough review of the existing literature on the use of AI to understand consumer behaviour.Methods: This study uses the PRISMA protocol for the selection of the studies. Then, it combines bibliometric methods...

Artificial Intelligence in Software Testing and Beyond: A Review of Current Practices and Emerging Challenges

Codrina-Victoria Lisaru, Claudiu-Vasile Kifor

Acta Informatica Pragensia X:X | DOI: 10.18267/j.aip.303183  

Background: Artificial intelligence (AI) is increasingly used both to test software (T1) and to assure AI-based systems (T2), with adjacent software-engineering work that shapes testing practice (T3). Prior reviews are mostly descriptive and rarely report comparable maturity or replicability signals.Objective: To provide a PRISMA-style systematic review (2015–2025, Web of Science) that maps T1–T2–T3 within a testing-centric frame, audits evidence maturity, threats reporting, and artefact openness per paper, and adds an explicit lens of large language models or generative AI (LLMs/GenAI).Methods: We queried the Web of Science Core...

Enhanced Diabetes Detection via a Privacy-Preserving Federated Learning Framework

Nouhaila Aasoum, Ismail Jellouli, Souad Amjad

Acta Informatica Pragensia X:X | DOI: 10.18267/j.aip.304118  

Background: The integration of artificial intelligence (AI) in healthcare depends on striking a balance between patient privacy and clinical utility. The standard methods often compromise one for the other, preventing the development of trustworthy healthcare AI.Objective: This paper aims to resolve the privacy-utility trade-off by developing an enhanced federated learning framework with adaptive differential privacy (DP) mechanisms that are optimized for clinical data.Methods: We implement and compare several different methods, from the most centralized deep learning to various federated configurations with formal DP guarantees. Our improved framework...

FearTherapy: Assessing the Impact of Therapeutic Games in Virtual Environments through Physiological State Measurements

Zoltán Balogh, Kristián Fodor, Martin Magdin, Jaroslav Reichel, József Kopják, Štefan Koprda, Martin Polák

Acta Informatica Pragensia X:X | DOI: 10.18267/j.aip.305294  

Background: Virtual reality (VR) integrated with internet of things (IoT) wearable devices offers innovative approaches to mental health interventions by enabling real-time physiological monitoring during immersive therapeutic experiences.Objective: This study aims to evaluate the effectiveness of VR therapeutic games in identifying and measuring emotional responses through physiological signals (heart rate and galvanic skin response) and to classify these responses using machine learning.Methods: We conduct experiments with 103 participants (aged 6–57 years) using FearTherapy, a custom VR game featuring interactions with four animals (Hermit,...

Corr-SHAP: Correlation-Aware Sampling for Faithful SHAP Value Estimation

Ridha El Hamdi, Hana Charaabi, Ibtissam Hdhiri, Mohamed Njah

Acta Informatica Pragensia X:X | DOI: 10.18267/j.aip.306188  

Background: SHapley Additive exPlanations (SHAP) methods are widely used to interpret machine learning models, yet most implementations assume feature independence. This assumption rarely holds in practice, especially when features are correlated, leading to biased and unstable attributions.Objective: We introduce Corr-SHAP, a correlation-aware SHAP approach that produces more faithful and stable feature attributions by explicitly modeling feature dependencies. Our aim is to enhance the accuracy, robustness, and scalability of SHAP explanations for models trained on correlated data.Methods: Corr-SHAP models feature correlations via a multivariate Gaussian...

Exploring Design Principles for SME Complementor-Suitable Digital Platforms

Lukas Rudolf Germut Fitz, Jochen Scheeg

Acta Informatica Pragensia X:X | DOI: 10.18267/j.aip.307360  

Background: Some of the world’s most valuable platform businesses rely on products and services provided by small and medium-sized enterprises (SMEs). Though, the modern digital platform economy is increasingly shaped by uncertainties and power asymmetries benefitting dominant platform owners and threatening smaller players participating as complementors in those ecosystems. Negative consequences include lock-in effects and platform dependency, exploitative participation terms and eroded entrepreneurial autonomy on the SMEs’ side, which altogether harm the digital platforms’ long-term viability, too. Addressing these issues, this...

Ethical Application of Artificial Intelligence in the Contemporary Information Society: A Scoping Review

Marija Kuštelega, Renata Mekovec

Acta Informatica Pragensia X:X | DOI: 10.18267/j.aip.308117  

Background: Artificial intelligence (AI) has become a fundamental part of everyday life, making it crucial to integrate AI into the information society in ways that protect individual rights.Objective: This study explores the perspectives of different stakeholders on the ethical use of AI. The aim of this research is to identify practical measures that can help address ethical challenges associated with AI deployment.Methods: A scoping literature review approach was adopted, focusing on the most relevant articles addressing the ethical aspects of AI usage from Web of Science Core Collection and Scopus databases. The analysis was performed with focus...

Effect of Dimension Size and Window Size on Word Embedding in Classification Tasks

Dávid Držík, Jozef Kapusta

Acta Informatica Pragensia X:X | DOI: 10.18267/j.aip.309209  

Background: Static word embedding models such as Word2Vec and GloVe remain widely used in natural language processing, yet key hyperparameters are often selected heuristically rather than through systematic validation.Objective: This study provides an extrinsic evaluation of context window size and embedding dimensionality for Word2Vec (CBOW and Skip-gram) and GloVe embeddings in a downstream spam classification task.Methods: Embeddings were trained on a large external corpus and evaluated using a neural network and several classical machine learning classifiers.Results: The results show that context window size has a moderate influence on performance,...