Barbara Probierz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Barbara Probierz has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Jan Kozak
University of Economics in Katowice
18 shared publications - Przemysław Juszczuk
University of Economics in Katowice
8 shared publications - Grzegorz Dziczkowski
Department of Machine Learning, University of Economics in Katowice, 1 Maja 50, 40-287 Katowice, Poland
6 shared publications - Tomasz Jach
Department of Machine Learning, University of Economics in Katowice, 1 Maja 50, 40-287 Katowice, Poland
6 shared publications - Anita Hrabia
Department of Machine Learning, University of Economics in Katowice, 1 Maja 50, 40-287 Katowice, Poland
4 shared publications - Piotr Stefański
University of Economics in Katowice
4 shared publications
Latest Publications
- 18 September 2026
- Published by Springer Nature
- p. 437-450
Graph-Based Representation and Weighted Clique Cover Strategy for Disinformation Detection
- 18 September 2026
- Published by Springer Nature
- p. 437-450
Graph-Based Representation and Weighted Clique Cover Strategy for Disinformation Detection
- 1 June 2026
- Published by Springer Nature
- p. 110-123
Fine-Tuning of Multilingual Language Models for Low-Resource Smishing Detection Using LoRA
- 1 June 2026
- Published by Springer Nature
- p. 110-123
Fine-Tuning of Multilingual Language Models for Low-Resource Smishing Detection Using LoRA
- 1 January 2026
- Published by Springer Nature
- p. 484-495
Stylometric and Embedding Synergy for Smishing Detection
- 1 January 2026
- Published by Springer Nature
- p. 484-495
Stylometric and Embedding Synergy for Smishing Detection
- Open Access
- 18 February 2025
- Published by World Scientific Pub Co Pte Ltd in Vietnam Journal of Computer Science
- Vol. 13 (01) , 29-55
Machine Learning-Based Approach for the Gambling Problem Identification
Watching sports matches is a beloved pastime for every fan, and predicting the results and betting on which team will win adds to the excitement. Unfortunately, for some users, a lack of self-control can turn initially innocent play into a long-term problem. For this reason, problem gambling is among the crucial issues facing modern societies. Bookmaker companies, therefore, put considerable effort into implementing responsible gambling practices; however, identifying at-risk individuals remains a major challenge. Our paper focuses on identifying users who may currently have, or soon develop, potential issues with gambling. To achieve this, we introduce a set of machine learning methods combined with preprocessing tools that allow us to initially acquire and anonymize user data. This anonymized database is then used to identify high-risk groups. We tested our approach on a large dataset that was obtained and preprocessed specifically for this study. The experiments were conducted on actual data and verified by specialists responsible for identifying gambling problems. Using our method, we successfully identified and detected the early signs of potential gambling problems in multiple users.
- 18 February 2025
- Published by World Scientific Pub Co Pte Ltd in Vietnam Journal of Computer Science
- Vol. 13 (01) , 29-55
Open AccessMachine Learning-Based Approach for the Gambling Problem Identification
Watching sports matches is a beloved pastime for every fan, and predicting the results and betting on which team will win adds to the excitement. Unfortunately, for some users, a lack of self-control can turn initially innocent play into a long-term problem. For this reason, problem gambling is among the crucial issues facing modern societies. Bookmaker companies, therefore, put considerable effort into implementing responsible gambling practices; however, identifying at-risk individuals remains a major challenge. Our paper focuses on identifying users who may currently have, or soon develop, potential issues with gambling. To achieve this, we introduce a set of machine learning methods combined with preprocessing tools that allow us to initially acquire and anonymize user data. This anonymized database is then used to identify high-risk groups. We tested our approach on a large dataset that was obtained and preprocessed specifically for this study. The experiments were conducted on actual data and verified by specialists responsible for identifying gambling problems. Using our method, we successfully identified and detected the early signs of potential gambling problems in multiple users.
- Open Access
- 16 February 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (4) , 2067
Exploration-Driven Genetic Algorithms for Hyperparameter Optimisation in Deep Reinforcement Learning
This paper investigates the application of genetic algorithms (GAs) for hyperparameter optimisation in deep reinforcement learning (RL), focusing on the Deep Q-Learning (DQN) algorithm. This study aims to identify approaches that enhance RL model performance through the effective exploration of the configuration space. By comparing different GA methods for selection, crossover, and mutation, this study focuses on deep RL models. The results indicate that GA techniques emphasising the exploration of the configuration space yield significant improvements in optimisation efficiency, reducing training time and enhancing convergence. The most effective GA improved the fitness function value from 68.26 (initial best chromosome) to 979.16 after 200 iterations, demonstrating the efficacy of the proposed approach. Furthermore, variations in specific hyperparameters, such as learning rate, gamma, and update frequency, were shown to substantially affect the DQN model’s learning ability. These findings suggest that exploration-driven GA strategies outperform GA approaches with limited exploration, underscoring the critical role of selection and crossover methods in enhancing DQN model efficiency and performance. Moreover, a mini case study on the CartPole environment revealed that even a 5% sensor dropout impaired the performance of a GA-optimised RL agent, while a 20% dropout almost entirely halted improvements.
- 16 February 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (4) , 2067
Open AccessExploration-Driven Genetic Algorithms for Hyperparameter Optimisation in Deep Reinforcement Learning
This paper investigates the application of genetic algorithms (GAs) for hyperparameter optimisation in deep reinforcement learning (RL), focusing on the Deep Q-Learning (DQN) algorithm. This study aims to identify approaches that enhance RL model performance through the effective exploration of the configuration space. By comparing different GA methods for selection, crossover, and mutation, this study focuses on deep RL models. The results indicate that GA techniques emphasising the exploration of the configuration space yield significant improvements in optimisation efficiency, reducing training time and enhancing convergence. The most effective GA improved the fitness function value from 68.26 (initial best chromosome) to 979.16 after 200 iterations, demonstrating the efficacy of the proposed approach. Furthermore, variations in specific hyperparameters, such as learning rate, gamma, and update frequency, were shown to substantially affect the DQN model’s learning ability. These findings suggest that exploration-driven GA strategies outperform GA approaches with limited exploration, underscoring the critical role of selection and crossover methods in enhancing DQN model efficiency and performance. Moreover, a mini case study on the CartPole environment revealed that even a 5% sensor dropout impaired the performance of a GA-optimised RL agent, while a 20% dropout almost entirely halted improvements.
- Open Access
- 11 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (2) , 667
Automated Tree Detection Using Image Processing and Multisource Data
This paper presents a method for the automatic detection and assessment of trees and tree-covered areas in Katowice, the capital of the Upper Silesian Industrial Region in southern Poland. The proposed approach utilizes satellite imagery and height maps, employing image-processing techniques and integrating data from various sources. We developed a data pipeline for gathering and pre-processing information, including vegetation data and numerical land-cover models, which were used to derive a new method for tree detection. Our findings confirm that automatic tree detection can significantly enhance the efficiency of urban tree management processes, contributing to the creation of greener and more resident-friendly cities.
- 11 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (2) , 667
Open AccessAutomated Tree Detection Using Image Processing and Multisource Data
This paper presents a method for the automatic detection and assessment of trees and tree-covered areas in Katowice, the capital of the Upper Silesian Industrial Region in southern Poland. The proposed approach utilizes satellite imagery and height maps, employing image-processing techniques and integrating data from various sources. We developed a data pipeline for gathering and pre-processing information, including vegetation data and numerical land-cover models, which were used to derive a new method for tree detection. Our findings confirm that automatic tree detection can significantly enhance the efficiency of urban tree management processes, contributing to the creation of greener and more resident-friendly cities.
- Open Access
- 26 October 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (21) , 9795
Towards AI-Generated Essay Classification Using Numerical Text Representation
The detection of essays written by AI compared to those authored by students is increasingly becoming a significant issue in educational settings. This research examines various numerical text representation techniques to improve the classification of these essays. Utilizing a diverse dataset, we undertook several preprocessing steps, including data cleaning, tokenization, and lemmatization. Our system analyzes different text representation methods such as Bag of Words, TF-IDF, and fastText embeddings in conjunction with multiple classifiers. Our experiments showed that TF-IDF weights paired with logistic regression reached the highest accuracy of 99.82%. Methods like Bag of Words, TF-IDF, and fastText embeddings achieved accuracies exceeding 96.50% across all tested classifiers. Sentence embeddings, including MiniLM and distilBERT, yielded accuracies from 93.78% to 96.63%, indicating room for further refinement. Conversely, pre-trained fastText embeddings showed reduced performance, with a lowest accuracy of 89.88% in logistic regression. Remarkably, the XGBoost classifier delivered the highest minimum accuracy of 96.24%. Specificity and precision were above 99% for most methods, showcasing high capability in differentiating between student-created and AI-generated texts. This study underscores the vital role of choosing dataset-specific text representations to boost classification accuracy.
- 26 October 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (21) , 9795
Open AccessTowards AI-Generated Essay Classification Using Numerical Text Representation
The detection of essays written by AI compared to those authored by students is increasingly becoming a significant issue in educational settings. This research examines various numerical text representation techniques to improve the classification of these essays. Utilizing a diverse dataset, we undertook several preprocessing steps, including data cleaning, tokenization, and lemmatization. Our system analyzes different text representation methods such as Bag of Words, TF-IDF, and fastText embeddings in conjunction with multiple classifiers. Our experiments showed that TF-IDF weights paired with logistic regression reached the highest accuracy of 99.82%. Methods like Bag of Words, TF-IDF, and fastText embeddings achieved accuracies exceeding 96.50% across all tested classifiers. Sentence embeddings, including MiniLM and distilBERT, yielded accuracies from 93.78% to 96.63%, indicating room for further refinement. Conversely, pre-trained fastText embeddings showed reduced performance, with a lowest accuracy of 89.88% in logistic regression. Remarkably, the XGBoost classifier delivered the highest minimum accuracy of 96.24%. Specificity and precision were above 99% for most methods, showcasing high capability in differentiating between student-created and AI-generated texts. This study underscores the vital role of choosing dataset-specific text representations to boost classification accuracy.
- 28 August 2024
- Published by Springer Nature
- p. 318-331
Detection of Candidate Skills from Job Offers and Comparison with ESCO Database
- 28 August 2024
- Published by Springer Nature
- p. 318-331
Detection of Candidate Skills from Job Offers and Comparison with ESCO Database
- 16 July 2024
- Published by Springer Nature
- p. 263-274
Identification of Users in a Gambling Problem with the Use of Machine Learning
- 16 July 2024
- Published by Springer Nature
- p. 263-274
Identification of Users in a Gambling Problem with the Use of Machine Learning
- 16 July 2024
- Published by Springer Nature
- p. 120-131
Automation of the Analysis of Medical Interviews to Improve Diagnoses Using NLP for Medicine
- 16 July 2024
- Published by Springer Nature
- p. 120-131
Automation of the Analysis of Medical Interviews to Improve Diagnoses Using NLP for Medicine