1. Transparent Persona Generation With LLMs : An Evidence-based and Traceable Method for User-centred DesignBojan Blažica, Manca Topole, Marko Debeljak, 2025, independent scientific component part or a chapter in a monograph Abstract: Personas are a cornerstone of user-centred design, but traditional methods for developing them are difficult to validate, prone to bias and labour-intensive. Data-driven approaches have improved scalability, but often lack the narrative richness and empathy that make personas effective. We present a methodology that uses large language models (LLMs) to accelerate the creation of personas while underpinning and constraining the results with contextual and empirical data. Our approach emphasises transparency and traceability: each generated persona attribute can be linked to its source material, including project documentation, workshop transcripts, survey results or other contextual corpora. By combining the narrative strengths of LLMs with the rigour of an evidence-based foundation, the method generates personas that are both descriptive and verifiable. We present a five-step workflow methodology: (1) generation of persona candidates from contextual data using LLMs, (2) iterative refinement to ensure representativeness of personas, (3) selection of the most relevant profiles through expert evaluation, (4) design of detailed persona profiles, and (5) enrichment with empirical evidence to ensure traceability and validation. The methodology is illustrated with a case study from the field of soil health, but can also be applied to other design contexts where alignment between different stakeholders is crucial. We argue that this approach positions LLMs not as a substitute for human expertise, but as an accelerator of persona work that improves accountability, reduces bias and facilitates communication in collaborative design processes.
Keywords: personas, large language model, traceability, user-centered design, decision support systems
Published in RUP: 30.01.2026; Views: 156; Downloads: 0
 Full text (275,89 KB) |
2. Optimizing Product Catalogue Design : A Comparative Study of Traditional Photography and 3D ModelingSimon Kolmanič, Jan Hrašar, Štefan Horvat, Domen Mongus, 2025, independent scientific component part or a chapter in a monograph Abstract: This study examines the replacement of traditional studio photography with a 3D modelling and rendering workflow in product catalogue production. Using the case of Urnes, a manufacturer of wooden urns, we compared the two approaches in terms of time, cost, and visual fidelity. The 3D pipeline, combining Blender, Substance 3D Painter, and InDesign, reduced preparation time per variation from 179 minutes to 36 minutes—a 4.9-fold improvement. After an initial 50-hour setup, subsequent catalogue updates achieved time savings of 97.6%. An informal interview with 38 professional users confirmed that 3D renderings matched or exceeded photographs in colour and texture accuracy. Results demonstrate that 3D workflows significantly lower production costs, accelerate updates, and support product personalisation, positioning them as a sustainable alternative to photography in catalogue design.
Keywords: Product Catalogue Design, Computer Generated Imagery, Visual Fidelity, Cost Reduction
Published in RUP: 30.01.2026; Views: 128; Downloads: 0
Full text (689,35 KB) |
3. Designing the ideal political identity questionnaire using machine learning and ideology scalesAna Nikolić, Uroš Sergaš, Marko Tkalčič, 2025, published scientific conference contribution (invited lecture) Abstract: 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 created using machine learning and psychometric methods. Sixty participants completed four ideological instruments (MFQ, SDO, RWA and 8values). Lasso regression and Random Forest with nested cross-validation identified predictive items, while psychometric evaluation included CFA and Cronbach’s alpha. Random Forest outperformed Lasso. Internal reliability was excellent and factor loadings supported a two-factor structure despite moderate model it. Findings show that ideology can be measured efficiently with reduced items, supporting applications in research, digital platforms and political psychology.
Keywords: political ideology, questionnaire design, machine learning, psychometrics
Published in RUP: 30.01.2026; Views: 132; Downloads: 2
Full text (189,01 KB) |
4. |
5. Banff designs: difference methods for coloring incidence graphsMarco Buratti, Francesca Merola, Anamari Nakić, Christian Rubio-Montiel, 2025, original scientific article Abstract: We present some results on the harmonious colourings of the Levi graph of a 2-design, focusing on Steiner 2-design. It is easily seen that the harmonious chromatic number of such a Levi graph is at least the number of points of the design: we study and construct Banff designs, that is designs such that this lower bound is attained.
Keywords: Harmonious chromatic number, Levi graph, combinatorial design
Published in RUP: 03.11.2025; Views: 292; Downloads: 4
Full text (426,74 KB) |
6. Transitive regular q-analogs of graphsDean Crnković, Vedrana Mikulić Crnković, Andrea Švob, Matea Zubović Žutolija, 2025, original scientific article Abstract: In 1976, Delsarte introduced the notion of q-analogs of designs, and q-analogs of graphs were introduced recently by M. Braun et al. In this paper, we extend that study by giving a method for constructing transitive regular q-analogs of graphs. Further, we illustrate the method by giving some examples. Additionally, we introduced the notion of q-analogs of quasi-strongly regular graphs and give examples of transitive q-analogs of quasi-strongly regular graphs coming from spreads.
Keywords: q-ary design, q-ary graph, regular graph, transitive group
Published in RUP: 03.11.2025; Views: 247; Downloads: 1
Full text (382,29 KB) |
7. |
8. Mutual-visibility problems in Kneser and Johnson graphsGülnaz Boruzanlı Ekinci, Csilla Bujtás, 2025, original scientific article Abstract: Let G be a connected graph and X ⊆ V(G). By definition, two vertices u and v are X-visible in G if there exists a shortest u, v-path with all internal vertices being outside of the set X. The largest size of X such that any two vertices of G (resp. any two vertices from X) are X-visible is the total mutual-visibility number (resp. the mutual-visibility number) of G.
In this paper, we determine the total mutual-visibility number of Kneser graphs, bipartite Kneser graphs, and Johnson graphs. The formulas proved for Kneser, and bipartite Kneser graphs are related to the size of transversal-critical uniform hypergraphs, while the total mutual-visibility number of Johnson graphs is equal to a hypergraph Turán number. Exact values or estimations for the mutual-visibility number over these graph classes are also established.
Keywords: mutual-visibility set, total mutual-visibility set, Kneser graph, bipartite Kneser graph, Johnson graph, Turán-type problem, covering design
Published in RUP: 22.10.2025; Views: 337; Downloads: 6
Full text (426,16 KB) |
9. Cubes of symmetric designsVedran Krčadinac, Mario Osvin Pavčević, Kristijan Tabak, 2025, original scientific article Abstract: We study n-dimensional matrices with {0, 1}-entries (n-cubes) such that all their 2-dimensional slices are incidence matrices of symmetric designs. A known construction of these objects obtained from difference sets is generalized so that the resulting n-cubes may have inequivalent slices. For suitable parameters, they can be transformed into n-dimensional Hadamard matrices with this property. In contrast, previously known constructions of n-dimensional designs all give examples with equivalent slices.
Keywords: symmetric design, difference set, Hadamard matrix
Published in RUP: 21.10.2025; Views: 273; Downloads: 0
Full text (121,51 KB) |
10. Distance-regular Cayley graphs over ℤpˢ ⊕ ℤpXiongfeng Zhan, Lu Lu, Xueyi Huang, 2025, original scientific article Abstract: In 2007, Miklavič and Potočnik proposed the problem of characterizing distance-regular Cayley graphs, which can be viewed as an extension of the problem of identifying strongly regular Cayley graphs, or equivalently, regular partial difference sets. Let p be an odd prime. In this paper, all distance-regular Cayley graphs over ℤps ⊕ ℤp are identified. It is shown that every such graph is isomorphic to a complete graph, a complete multipartite graph, or the line graph of a transversal design TD(r, p) with 2 ≤ r ≤ p − 1.
Keywords: distance-regular graph, Cayley graph, Schur ring, Fourier transformation, transversal design
Published in RUP: 21.10.2025; Views: 374; Downloads: 1
Full text (461,23 KB) |
