Orsolya Ring

Dr. Orsolya Ring

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
2 February 2022 in Language Resources and Evaluation
Verified
Journal Article
Open access
PDF file
TETomaž Erjavec
Tomaž Erjavec
MOMaciej Ogrodniczuk
Maciej Ogrodniczuk
POPetya Osenova
Petya Osenova
NLNikola Ljubešić
Nikola Ljubešić
KSKiril Simov
Kiril Simov
DFDarja Fišer
Darja Fišer
This paper presents the ParlaMint corpora containing transcriptions of the sessions of the 17 European national parliaments with half a billion words. The corpora are uniformly encoded, contain rich meta-data about 11 thousand speakers, and are linguistically annotated following the Universal Dependencies formalism and with named entities. Samples of the corpora and conversion scripts are available from the project’s GitHub repository, and the complete corpora are openly available via the CLARIN.SI repository for download, as well as through the NoSketch Engine and KonText concordancers and the Parlameter interface for on-line exploration and analysis.

13 June 2023 in IEEE Access
Verified
Journal Article
Open access
IÜIstván Üveges
István Üveges
OROrsolya Ring
Orsolya Ring
The growing number of digitally accessible text corpora and the accelerating development of NLP tools and methods (particularly the emergence of powerful large-scale language models) have allowed their widespread use in various classification tasks, including the vast field of sentiment analysis. However, these models must often be fine-tuned to perform this task efficiently. Therefore, we aimed to create a transformer-based fine-tuned model for the emotion and sentiment analysis of Hungarian political texts. The training data for the model were the manually annotated parliamentary speech texts from 2014 to 2018, which have the advantage of being rich in various emotions. The compiled corpus can be freely used for research purposes. In our work, we describe in detail the process of fine-tuning the Hungarian BERT model for sentiment and emotion classification, the performance achieved, and the typical classification errors, mainly due to a lack of recognition of pragmatic and other language use features by the fine-tuned models.

23 March 2024 in Language Resources and Evaluation
Verified
Journal Article
Open access
PDF file
OROrsolya Ring
Orsolya Ring
MSMartina Katalin Szabó
Martina Katalin Szabó
CGCsenge Guba
Csenge Guba
BVBendegúz Váradi
Bendegúz Váradi
IÜIstván Üveges
István Üveges
Automated sentiment analysis of textual data is one of the central and most challenging tasks in political communication studies. However, the toolkits available are primarily for English texts and require contextual adaptation to produce valid results—especially concerning morphologically rich languages such as Hungarian. This study introduces (1) a new sentiment and emotion annotation framework that uses inductive approaches to identify emotions in the corpus and aggregate these emotions into positive, negative, and mixed sentiment categories, (2) a manually annotated sentiment data set with 5700 political news sentences, (3) a new Hungarian sentiment dictionary for political text analysis created via word embeddings, whose performance was compared with other available sentiment dictionaries. (4) Because of the limitations of sentiment analysis using dictionaries we have also applied various machine learning algorithms to analyze our dataset, (5) Last but not least to move towards state-of-the-art approaches, we have fine-tuned the Hungarian BERT-base model for sentiment analysis. Meanwhile, we have also tested how different pre-processing steps could affect the performance of machine-learning algorithms in the case of Hungarian texts.

21 April 2025 in Information
Verified
Journal Article
Open access
PDF file
IÜIstván Üveges
István Üveges
OROrsolya Ring
Orsolya Ring
Emotion classification in natural language processing (NLP) has recently witnessed significant advancements. However, class imbalance in emotion datasets remains a critical challenge, as dominant emotion categories tend to overshadow less frequent ones, leading to biased model predictions. Traditional techniques, such as undersampling and oversampling, offer partial solutions. More recently, synthetic data generation using large language models (LLMs) has emerged as a promising strategy for augmenting minority classes and improving model robustness. In this study, we investigate the impact of synthetic data augmentation on German-language emotion classification. Using an imbalanced dataset, we systematically evaluate multiple balancing strategies, including undersampling overrepresented classes and generating synthetic data for underrepresented emotions using a GPT-4–based model in a few-shot prompting setting. Beyond enhancing model performance, we conduct a detailed linguistic analysis of the synthetic samples, examining their lexical diversity, syntactic structures, and semantic coherence to determine their contribution to overall model generalization. Our results demonstrate that integrating synthetic data significantly improves classification performance, particularly for minority emotion categories, while maintaining overall model stability. However, our linguistic evaluation reveals that synthetic examples exhibit reduced lexical diversity and simplified syntactic structures, which may introduce limitations in certain real-world applications. These findings highlight both the potential and the challenges of synthetic data augmentation in emotion classification. By providing a comprehensive evaluation of balancing techniques and the linguistic properties of generated text, this study contributes to the ongoing discourse on improving NLP models for underrepresented linguistic phenomena.

26 September 2024 in Journal of Computational Social Science
Verified
Journal Article
Open access
PDF file
MSMiklós Sebők
Miklós Sebők
OROrsolya Ring
Orsolya Ring
MKMárk György Kis
Márk György Kis
MBMartin Balázs Bánóczy
Martin Balázs Bánóczy
ÁDÁgnes Dinnyés
Ágnes Dinnyés
Extant studies on the European media coverage of the COVID-19 pandemic generally posit a linear relationship between the severity of the public health emergency and the volume of media reports. However, domestic politics and geopolitics may also impact the saliency, distribution, and sentiment of coverage in different outlets. Under Viktor Orbán’s illiberal leadership, Hungary sought deals for ventilators and vaccines from China and Russia—a deviation from joint European procurements. In this article, we conduct a content analysis of pro-government and Orbán-critical media to examine differences in their treatment of Eastern and Western vaccines. We relied on state-of-the-art deep learning analysis (a branch of articifial intelligence) to investigate all COVID-19-related articles (N = 72,339) published on three major Hungarian news portals between March 2020 and March 2022. We used a new fine-tuned BERT model for emotion analysis, the categories of which have been aggregated into three sentiment labels (positive, negative, and neutral). Our sentiment analysis results show a positive correlation between the number of sentences mentioning at least one of the vaccines and the (first) shots administered for only one outlet out of three. The pro-government portal in the sample showed more positivity towards Western vaccines than a hard-right, anti-government one. This latter also produced more positive reports concerning the Russian vaccine. These results shed light on the complex geopolitics of vaccine narratives in Hungarian media. Our research contributes not only to our understanding of illiberal media systems but also by sharing a new public dataset and a fine-tuned large language model that is applicable to alternative research questions and designs.

7 June 2022 in SocArXiv
Verified
Preprint
Open access
GKGyörgy Márk Kis
György Márk Kis
OROrsolya Ring
Orsolya Ring
MSMiklós Sebők
Miklós Sebők
BERT is a state-of-the-art open-sourced NLP solution for a wide range of tasks, but even basic uses need extensive GPU resources, technical expertise, and a large and good quality corpus with wide domain coverage. This paper presents an alternative, cost-efficient approach for using the strength of BERT’s tokenizer and contextual embeddings for virtually free, with only nominal Python and Machine Learning expertise. This method of using traditional ML-modeling enhanced by BERT’s contextual embeddings extracted from the hidden layers gives worse but comparable results to fine-tuned full BERT models. On our novel, manually validated dataset of Hungarian online media texts, seven emotions, and a neutral class were classified with a 0.62 weighted F1-score. While two categories were underperforming due to small sample representation and size, the other six produced results that sit squarely between classical frequency-based methods (0.44-0.47) and the newer, fine-tuned BERT models (0.71-0.73). We outline several routes for improvements and conclude that while ’doodling’ around with BERT is a large undertaking for many researchers, our approach provides good results with a fraction of the effort needed. The gap between our approach and a fine-tuned BERT significantly narrows down on corpuses necessitating parameter degradation due to insufficient memory.