1. Inferring a Mobile User’s Valence and Arousal through On-Screen Text AnalysisEdita Džubur, Veljko Pejović, 2025, samostojni znanstveni sestavek ali poglavje v monografski publikaciji Opis: Understanding a user’s emotional state is critical for building adaptive and intelligent mobile applications. In this paper we investigate the feasibility of inferring valence and arousal from the text displayed on smartphone screens. We developed AV-Sense, a mobile application that combines the Experience Sampling Method, a technique that prompts users to report their feelings in the moment, with passive screentext logging. In a two-week study with 12 participants, we collected 787 ESM responses and over 650,000 screentext entries. Data analysis revealed meaningful temporal and individual patterns in reported affect. We then explored the use of large language models to predict valence and arousal from screentext, but results indicated limited predictive power in this setting. Our findings highlight both the potential and current challenges of screentext-based affect inference, laying the groundwork for future research on emotion-aware applications and naturalistic psychological studies.
Ključne besede: text analysis, experience sampling method, screentext sensing, valence, arousal, large language models
Objavljeno v RUP: 30.01.2026; Ogledov: 277; Prenosov: 1
 Celotno besedilo (350,11 KB) |
2. Reducing Food Waste and Boosting Profits through Inventory Management : The Case of Small Slovenian BakeriesŠpela Lipnik, Žiga Čepar, 2025, izvirni znanstveni članek Opis: This article explores the role of inventory management in reducing food waste and improving economic performance in selected Slovenian bakeries, contributing to a more efficient, environmentally responsible and sustainable economy. Using semi-structured interviews with key bakery personnel and an in-depth analysis of business documentation, our study applies the Economic Order Quantity (EOQ) model and News vendor model to test the following two hypotheses: (H1) improving inventory management at Bakery 1 can reduce total annual procurement costs by more than 15% without causing spoilage or raw material waste, and (H2) minimizing food waste at Bakery 2 may not necessarily align with maximizing profit. The findings confirm that applying these models can enhance production and procurement planning, demonstrating that while cost reductions and waste minimization are achievable, they may not always be fully aligned. The study underscores the importance of strategic inventory management in balancing financial and environmental objectives in small bakeries.
Ključne besede: EOQ and Newsvendor inventory management models, inventory optimization, food waste minimization, sustainable economy
Objavljeno v RUP: 18.12.2025; Ogledov: 254; Prenosov: 0
Celotno besedilo (527,29 KB)
Gradivo ima več datotek! Več... |
3. Is open source the future of AI? : a data-driven approachDomen Vake, Bogdan Šinik, Jernej Vičič, Aleksandar Tošić, 2025, izvirni znanstveni članek Opis: Large language models (LLMs) have become central to both academic research and industrial applications, fueling debates on their accuracy, usability, privacy, and potential misuse. While proprietary models benefit from substantial investments in data and computing resources, open-sourcing is often suggested as a means to enhance trust and transparency. Yet, open-sourcing comes with its own challenges, such as risks of illicit applications, limited financial incentives, and intellectual property concerns. Positioned between these extremes are hybrid approaches—including partially open models and licensing restrictions—that aim to balance openness with control. In this paper, we adopt a data-driven approach to examine the open-source development of LLMs. By analyzing contributions in model improvements, modifications, and methodologies, we assess how community efforts impact model performance. Our findings indicate that the open-source community can significantly enhance models, demonstrating that community-driven modifications can yield efficiency gains without compromising performance. Moreover, our analysis reveals distinct trends in community growth and highlights which architectures benefit disproportionately from open-source engagement. These insights provide an empirical foundation to inform balanced discussions among industry experts and policymakers on the future direction of AI development.
Ključne besede: large language models, artificial intelligence, open source, data science, HuggingFace
Objavljeno v RUP: 25.09.2025; Ogledov: 681; Prenosov: 4
Celotno besedilo (606,12 KB)
Gradivo ima več datotek! Več... |
4. |
5. Exploring the drivers of farm sustained participation in agri‑environmental programmesŠtefan Bojnec, Imre Fertő, 2025, izvirni znanstveni članek Opis: This paper examines the socioeconomic and institutional determinants influencing sustained participation in Agri-Environmental Climate Schemes (AECS), drawing on comprehensive panel data from Slovenian farms covering the period 2014–2021. Using discrete-time hazard models and nonparametric duration analysis, we identify economic resilience—characterised by larger farm size, income diversification, and prior participation—as a significant driver of prolonged AECS engagement. Conversely, greater dependence on market-based income is negatively correlated with long-term participation, highlighting inherent trade-offs between short-term economic gains and sustained ecological commitments. Additionally, educational attainment exhibits a modest yet positive association, emphasising the importance of knowledge dissemination and capacity building in facilitating the responsible use and sustained environmental protection. Our findings underscore the necessity for context-specific policy designs, advocating diversified financial incentives, robust extension services, and market-aligned strategies to effectively integrate agricultural productivity with environmental sustainability.
Ključne besede: agri-environmental climate scheme management, farm corporate social responsibility, sustainable farm production adoption, selection model, duration analysis, discrete-time models
Objavljeno v RUP: 28.08.2025; Ogledov: 533; Prenosov: 7
Celotno besedilo (1,16 MB)
Gradivo ima več datotek! Več... |
6. |
7. |
8. |
9. |
10. |
