ponedeljek, 30. junij 2025 Una VULETIĆ: Computational Analysis and Visualization of Viewing Behavior: Interactive vs. Non-Interactive Documentary / Zala ŽUŽEK: Prediction of Eudaimonic and Hedonic Movie characteristics using User reviews

V ponedeljek, 30. junija 2025, bosta ob 16:00 uri izvedeni dve
predavanji v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 30. junij 2025 ob 16.00 v FAMNIT-VP2.

1. predavanje:
============

------------------------------------------
PREDAVATELJICA: Una VULETIĆ
------------------------------------------

Una Vuletić is 2nd year Data Science master's student at UP FAMNIT, writing her master thesis under supervision of Associate Professors Matjaž Kljun and Klen Čopič Pucihar. She is also working at HICUP Lab at UP FAMNIT, as part of the pilot project GDI UP.

---------------------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Computational Analysis and Visualization of Viewing Behavior: Interactive vs. Non-Interactive Documentary
---------------------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

In this seminar, we explore how interactivity in digital documentaries influences viewer experience, both visually and emotionally. While traditional documentaries rely on passive, linear storytelling, which can limit emotional engagement and attention, interactive documentaries allow viewers to shape their own experience while navigating through content. To investigate effect of interactivity, we analyzed eye-tracking and facial expression data from two participant groups who watched interactive and non-interactive versions of the iIsland documentary, which focuses on the lives of the last residents of Biševo, a small Croatian island.

Seminar bo potekal v angleškem jeziku.

=============================================================================================================

2. predavanje:
============

---------------------------------------
PREDAVATELJICA: Zala ŽUŽEK
---------------------------------------

Zala Žužek is currently completing her master’s studies in Data Science at UP FAMNIT. Her interests include data analytics, machine learning, and recommender systems, which she explores in depth through her master’s thesis on the prediction of psychological content in user-generated movie reviews. She currently works as a data analyst in the Data Intelligence and Delivery Assurance department, where she applies and deepens her expertise in data analytics, process automation, and data-driven assurance. Her work involves automating audit processes, improving data quality, and supporting digital transformation by integrating advanced analytics into assurance workflows. She is passionate about using data to enhance efficiency, uncover meaningful insights, and enable smarter decision-making in complex business environments.

-------------------------------------------------------------------------------------------------------------------------
NASLOV: Prediction of Eudaimonic and Hedonic Movie characteristics using User reviews
-------------------------------------------------------------------------------------------------------------------------

POVZETEK:

This thesis explores the use of machine learning to predict eudaimonic and hedonic movie characteristics based on user reviews. Using natural language processing (NLP) techniques, we extracted relevant features from full-text reviews scraped from an online movie database and trained several regression and classification models. The results indicate that user reviews contain sufficient emotional and semantic information that can predict user preferences more effectively than baseline models. These findings suggest that integrating text-based insights with traditional features can provide a deeper understanding of user behavior and improve the performance of recommendation systems.

Seminar bo potekal v angleškem jeziku.

 

Vabljeni.

---

ponedeljek, 23. junij 2025 Valentina PUCER: Razložljiva umetna inteligenca pri napovedovanju verjetnosti neplačila v bančništvu

---

nedelja, 15. junij 2025 Bogdan ŠINIK: Application of Benfords Law on Enviormental Data

V ponedeljek, 16. junija 2025, bo ob 16:00 uri izvedeno 
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE 
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 16. junij 2025 ob 16.00 v FAMNIT-VP2.

---------------------------------------
PREDAVATELJ: Bogdan ŠINIK
---------------------------------------

Bogdan Šinik is doing his Masters in Data Science at UP FAMNIT under the supervision of Associate Professor Jernej Vičič and Assistant Professor Aleksandar Tošić. He is also working at DLT^2 lab at UP FAMNIT, as part of the pilot project GDI UP.

----------------------------------------------------------------------------------
NASLOV: Application of Benfords Law on Enviormental Data
----------------------------------------------------------------------------------

POVZETEK: 

This presentation provides an overview of the application of Benford's Law as a novel approach to assess data quality and integrity within Life-Cycle Assessment (LCA). LCA is a critical methodology for evaluating environmental impacts, yet its reliability is highly dependent on the quality of the underlying data, which can often be subject to inconsistencies or potential biases. This study explores the utility of Benford's Law by applying conformity tests to numerical data found in several Life Cycle Inventory (LCI) databases. The work demonstrates how this statistical tool can reveal patterns indicative of potential data anomalies. The research highlights Benford's Law as a simple, computationally efficient, and robust method for enhancing data quality assessment in LCA. Its application offers a valuable means to identify potential issues and improve the overall reliability of environmental impact evaluations.

Seminar bo potekal v živo, s pričetkom ob 16:00 uri v učilnici FAMNIT-VP2.

Vabljeni. 

---

ponedeljek, 9. junij 2025 2 predavanji: Špela ČUČKO & Anastasiia DZIUBA: Sofisticiranost ocenjevanja glasbe in vpliv razlage na priporočila & Graphlet-based Network Analysis

V ponedeljek, 9. junija 2025, bosta ob 16:00 uri izvedeni dve
predavanji v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 9. junij 2025 ob 16.00 v FAMNIT-VP2.

1. predavanje:

------------------------------------------
PREDAVATELJICA: Špela ČUČKO
------------------------------------------

Špela Čučko zaključuje študijski program Podatkovna znanost in trenutno deluje kot podatkovna znanstvenica, kjer se osredotoča na področje zavarovalništva. Njeno delo vključuje razvoj naprednih analitičnih rešitev, ki temeljijo na podatkovnem modeliranju, strojnem učenju ter uporabi statističnih metod za podporo poslovnim odločitvam v zavarovalni industriji.

---------------------------------------------------------------------------------------------------
NASLOV: Sofisticiranost ocenjevanja glasbe in vpliv razlage na priporočila
---------------------------------------------------------------------------------------------------

POVZETEK:

Glasba je univerzalni jezik, ki zajema vse kulture in generacije, hkrati pa predstavlja eno najpomembnejših področij za uporabo priporočilnih sistemov. Večina obstoječih sistemov pri glasbi se pretežno zanašajo na podatke o zgodovini poslušanja, priljubljenosti, žanrskih oznakah ali vedenjske vzorce uporabnikov. Razvili smo priporočilni sistem, ki temelji na analizi glasbene kvalitete s poudarkom na ritmu, melodiji, harmoniji in lastnostih besedila. Raziskali smo, kako glasbena izobrazba vpliva na percepcijo teh lastnosti in ali prisotnost razlage pri priporočilih vpliva na uporabnikov okus in zaupanje v model. Ugotovitve potrjujejo subjektivnost dojemanja glasbe, ter nakazujejo potencialen vpliv vsebinskih razlag pri priporočanju skladb z izrazitimi.

Seminar bo potekal v slovenskem jeziku.

---

2. predavanje:

-------------------------------------------------
PREDAVATELJICA: Anastasiia DZIUBA
-------------------------------------------------

Anastasiia Dziuba is a second-year Data Science master’s student at UP FAMNIT.

-----------------------------------------------------------
NASLOV: Graphlet-based Network Analysis
-----------------------------------------------------------

POVZETEK:

This research addresses the challenge of capturing local structure in complex networks by applying graphlet-based analysis. While traditional global metrics provide limited insight into detailed connectivity patterns, graphlets (small, connected subgraphs) can offer a more nuanced understanding of how nodes interact within their local neighbourhoods. Although graphlets have been successfully applied in biological and social networks, their potential remains unexplored in other dynamic fields. In this study, we propose an approach to apply graphlet-based analysis to stock market data. The focus is to investigate whether the use of graphlet-based methods can extend traditional approaches by capturing complex topological features. In particular, we will investigate whether graph local and global parameters can improve the detection and interpretation of market shifts and improve portfolio diversification.

Seminar bo potekal v angleškem jeziku.

Vabljeni.

---