Aura Cristina Udrea

Mrs. Aura Cristina Udrea

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 September 2025 in Electronics
Verified
Journal Article
Open access
PDF file
AUAura Cristina Udrea
Aura Cristina Udrea
SRStefan Ruseti
Stefan Ruseti
LNLaurentiu Marian Neagu
Laurentiu Marian Neagu
OOOvio Olaru
Ovio Olaru
ATAndrei Terian
Andrei Terian
MDMihai Dascalu
Mihai Dascalu
The study of dramatic plays has long relied on qualitative methods to analyze character interactions, making little assumption about the structural patterns of communication involved. Our approach bridges NLP and literary studies, enabling scalable, data-driven analysis of interaction patterns and power structures in drama. We propose a novel method to supplement addressee identification in tragedies using Large Language Models (LLMs). Unlike conventional Social Network Analysis (SNA) approaches, which often diminish dialogue dynamics by relying on co-occurrence or adjacency heuristics, our LLM-based method accurately records directed speech acts, joint addresses, and listener interactions. In a preliminary evaluation of an annotated multilingual dataset of 14 scenes from nine plays in four languages, our top-performing LLM (i.e., Llama3.3-70B) achieved an F1-score of 88.75% (P = 94.81%, R = 84.72%), an exact match of 77.31%, and an 86.97% partial match with human annotations, where partial match indicates any overlap between predicted and annotated receiver lists. Through automatic extraction of speaker–addressee relations, our method provides preliminary evidence for the potential scalability of SNA for literary analyses, as well as insights into power relations, influence, and isolation of characters in tragedies, which we further visualize by rendering social network graphs.

30 August 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
AUAura Cristina Udrea
Aura Cristina Udrea
SRStefan Ruseti
Stefan Ruseti
VPVlad Pojoga
Vlad Pojoga
SBStefan Baghiu
Stefan Baghiu
ATAndrei Terian
Andrei Terian
MDMihai Dascalu
Mihai Dascalu
Recent developments in natural language processing, particularly large language models (LLMs), create new opportunities for literary analysis in underexplored languages like Romanian. This study investigates stylistic heterogeneity and genre blending in 175 late 19th- and early 20th-century Romanian novels, each classified by literary historians into one of 17 genres. Our findings reveal that most novels do not adhere to a single genre label but instead combine elements of multiple (micro)genres, challenging traditional single-label classification approaches. We employed a dual computational methodology combining an analysis with Romanian-tailored linguistic features with general-purpose LLMs. ReaderBench, a Romanian-specific framework, was utilized to extract surface, syntactic, semantic, and discourse features, capturing fine-grained linguistic patterns. Alternatively, we prompted two LLMs (Llama3.3 70B and DeepSeek-R1 70B) to predict genres at the paragraph level, leveraging their ability to detect contextual and thematic coherence across multiple narrative scales. Statistical analyses using Kruskal–Wallis and Mann–Whitney tests identified genre-defining features at both novel and chapter levels. The integration of these complementary approaches enhances microgenre detection beyond traditional classification capabilities. ReaderBench provides quantifiable linguistic evidence, while LLMs capture broader contextual patterns; together, they provide a multi-layered perspective on literary genre that reflects the complex and heterogeneous character of fictional texts. Our results argue that both language-specific and general-purpose computational tools can effectively detect stylistic diversity in Romanian fiction, opening new avenues for computational literary analysis in limited-resourced languages.

11 August 2026 in Electronics
Verified
Journal Article
Open access
PDF file
AUAura Cristina Udrea
Aura Cristina Udrea
SRStefan Ruseti
Stefan Ruseti
LNLaurentiu Marian Neagu
Laurentiu Marian Neagu
OOOvio Olaru
Ovio Olaru
ATAndrei Terian
Andrei Terian
MDMihai Dascalu
Mihai Dascalu
Character networks have become a standard tool for analyzing dramatic texts at scale, yet the dominant co-presence paradigm records only who shares the stage, not the directionality of speech that drives dramatic conflict and power. We address this limitation by employing Large Language Models (LLMs) to automatically identify the addressee for each utterance, thereby producing directed, weighted character networks that encode both the volume and directionality of speech. We illustrate the scalability of this approach through a large-scale cross-corpus analysis spanning 3327 plays across three Western European traditions (1931 French, 607 German, 789 English), examining diachronic trends in network density, character count, monologue frequency, and collective address from the 12th to the 21st century. Focused author-pair comparisons, such as Racine versus Corneille and Schiller versus Goethe, reveal distinct structural signatures that align with established literary-theoretical characterizations of these dramatists.