Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 9
Uvajanje in uporaba elektronskih dokumentov
Uroš Sergaš, Cene Bavec
Diplomsko delo
Oznake: e-dokumenti;e-dokumentiranje;e-poslovanje;digitalni podpisi;
Leto: 2018 Vir: Univerza na Primorskem (UP)
Tribalizem in lažne novice: opisni in napovedni modeli vpliva prepričanj na zaupanje novicam
Uroš Sergaš, Marko Tkalčič, Habil Kalkan
Magistrsko delo
Oznake: tribalizem;lažne novice;zaupanje novicam;napovedni modeli;
Leto: 2022 Vir: Fakulteta za matematiko, naravoslovje in informacijske tehnologije Koper (UP FAMNIT)
Analiza vpliva tehnologije na kakovost spanja
Tamara Mikač, Marko Tkalčič, Uroš Sergaš
Diplomsko delo
Oznake: kakovost spanja;modra svetloba;tehnologija;spalna rutina;življenski slog;napovedni modeli;stres;diplomske naloge;
Leto: 2025 Vir: Fakulteta za matematiko, naravoslovje in informacijske tehnologije Koper (UP FAMNIT)
Designing the ideal political identity questionnaire using machine learning and ideology scales
Ana Nikolić, Uroš Sergaš, Marko Tkalčič
Objavljeni znanstveni prispevek na konferenci (vabljeno predavanje)
Oznake: political ideology;questionnaire design;machine learning;psychometrics;
Political ideology shapes beliefs, behavior and attitudes toward society. Many existing questionnaires for measuring ideology are lengthy, repetitive, and misaligned with self-perception. This paper investigates whether a shorter, reliable, two-dimensional political identity questionnaire can be cre ...
Leto: 2025 Vir: Repozitorij Univerze na Primorskem (RUP)
Evaluating depolarization-oriented news ranking strategies using LLM-generated articles
Uroš Sergaš, Marko Tkalčič, Bruce Ferwerda
Objavljeni znanstveni prispevek na konferenci
Oznake: news recommendation;political polarization;affective polarization;ranking strategies;large language models;
Algorithmic news ranking and large language models (LLMs) increasingly mediate how citizens receive political information. While personalization is often criticized for reinforcing echo chambers, ranking has also been proposed as a lever for depolarization by shaping exposure to cross-cutting viewpo ...
Leto: 2026 Vir: Fakulteta za matematiko, naravoslovje in informacijske tehnologije Koper (UP FAMNIT)
Designing the ideal political identity questionnaire using machine learning and ideology scales
Ana Nikolić, Ana Nikolić, Marko Tkalčič, Uroš Sergaš
Diplomsko delo
Oznake: political ideology;questionnaire shortening;machine learning;lasso regression;random forest;psychometric;
Leto: 2025 Vir: Fakulteta za matematiko, naravoslovje in informacijske tehnologije Koper (UP FAMNIT)
Game on for news
Caroline Frössling, Uroš Sergaš, Marko Tkalčič, Bruce Ferwerda
Objavljeni znanstveni prispevek na konferenci
Oznake: information systems;recommender systems;personalization;human-centered computing;user studies;
Personalized news systems often adapt ranking to user preferences, which can reinforce selective exposure. We investigate an alterna- tive personalization strategy: stance-aware incentive shaping. In- stead of modifying content ranking, we use a minimal per-topic stance user model to adapt reward gr ...
Leto: 2026 Vir: Fakulteta za matematiko, naravoslovje in informacijske tehnologije Koper (UP FAMNIT)
Progress feedback for countering selective exposure
Janine Riemann, Jasmin Alt, Uroš Sergaš, Marko Tkalčič, Bruce Ferwerda
Objavljeni znanstveni prispevek na konferenci
Oznake: human-centered computing;human computer interaction;information systems;recommender systems;
Selective exposure in online news is often attributed to person- alization mechanisms and user modeling. Recent work proposes interface-level interventions that visualize reading balance or frame cross-cutting exposure as progress. However, we lack empirical evidence on whether alternative represent ...
Leto: 2026 Vir: Fakulteta za matematiko, naravoslovje in informacijske tehnologije Koper (UP FAMNIT)
Prompt to press
Uroš Sergaš, Ahmadou Wagne, Thomas Elmar Kolb, Julia Neidhardt, Bruce Ferwerda, Marko Tkalčič
Objavljeni znanstveni prispevek na konferenci
Oznake: AI-generated news;prompt specificity;human vs. AI detection;media perception;assisted suicide;
Large language models (LLMs) are becoming a common feature in content creation tools, prompting important questions about how design choices influence user trust and engagement in AI- assisted journalism. Beyond output quality, factors such as prompt specificity, model choice, and authorship disclos ...
Leto: 2026 Vir: Fakulteta za matematiko, naravoslovje in informacijske tehnologije Koper (UP FAMNIT)
Št. zadetkov: 9
Ključne besede:
Leto izdaje:
Avtorji:
Repozitorij:
Tipologija:
Jezik: