Małgorzata Lucińska

Dr. Małgorzata Lucińska


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
28 October 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MPMirosław Płaza
Mirosław Płaza
RKRobert Kazala
Robert Kazala
ZKZbigniew Koruba
Zbigniew Koruba
MKMarcin Jan Kozłowski
Marcin Jan Kozłowski
MLMałgorzata Lucińska
Małgorzata Lucińska
JSJarosław Spyrka
Jarosław Spyrka
Nowadays, one of the important aspects of research on call/contact centre (CC) systems is how to automate their operations. Process automation is influenced by the continuous development in the implementation of virtual assistants. The effectiveness of virtual assistants depends on numerous factors. One of the most important is correctly recognizing the intent of clients conversing with the machine. Recognizing intentions is not an easy process, as often the client’s actual intentions can only be correctly identified after considering the client’s emotional state. When it comes to human–machine communication, the ability of a virtual assistant to recognize the client’s emotional state would greatly improve its effectiveness. This paper proposes a new method for recognizing interlocutors’ emotions dedicated directly to contact centre systems. The developed method provides opportunities to determine emotional states in text and voice channels. It provides opportunities to explore both the client’s and the agent’s emotional states. Information about agents’ emotions can be used to build their behavioural profiles, which is also applicable in contact centres. In addition, the paper explored the possibility of emotion assessment based on automatic transcriptions of recordings, which also positively affected emotion recognition performance in the voice channel. The research used actual conversations that took place during the operation of a large, commercial contact centre. The proposed solution makes it possible to recognize the emotions of customers contacting the hotline and agents handling these calls. Using this information in practical applications can increase the efficiency of agents’ work, efficiency of bots used in CC and increase customer satisfaction.

1 December 2018 in International Journal of Applied Mathematics and Computer Science
Verified
Journal Article
Open access
PDF file
MLMałgorzata Lucińska
Małgorzata Lucińska
SWSlawomir T. Wierzchon
Slawomir T. Wierzchon
The paper presents a novel spectral algorithm EVSA (eigenvector structure analysis), which uses eigenvalues and eigenvectors of the adjacency matrix in order to discover clusters. Based on matrix perturbation theory and properties of graph spectra we show that the adjacency matrix can be more suitable for partitioning than other Laplacian matrices. The main problem concerning the use of the adjacency matrix is the selection of the appropriate eigenvectors. We thus propose an approach based on analysis of the adjacency matrix spectrum and eigenvector pairwise correlations. Formulated rules and heuristics allow choosing the right eigenvectors representing clusters, i.e., automatically establishing the number of groups. The algorithm requires only one parameter-the number of nearest neighbors. Unlike many other spectral methods, our solution does not need an additional clustering algorithm for final partitioning. We evaluate the proposed approach using real-world datasets of different sizes. Its performance is competitive to other both standard and new solutions, which require the number of clusters to be given as an input parameter.

10 March 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MLMałgorzata Lucińska
Małgorzata Lucińska
MPMałgorzata Płaza
Małgorzata Płaza
JKJustyna Keczkowska
Justyna Keczkowska
KKKacper Kurek
Kacper Kurek
KWKarol Wykrota
Karol Wykrota
MPMirosław Płaza
Mirosław Płaza
Multi-class and multi-label classification of medical dialogues remains a challenging task due to high linguistic variability and transcription noise. This study proposes an ensemble approach based on three fine-tuned Polish T5 (Text-to-Text Transfer Transformer) models trained on partially overlapping clinical dialogue datasets. The models are evaluated exclusively on low-quality, highly noisy, automatically transcribed conversations to assess real-world robustness. The results demonstrate that the ensemble of models improves classification stability and outperforms the best single model, increasing the F1-score by 21.8% for internal medicine dialogues and by 44.9% for paediatric interviews. The proposed method shows potential for practical deployment in clinical decision support and automated medical documentation systems.

9 September 2016
Verified
Book Chapter
Open access
PDF file
MLMałgorzata Lucińska
Małgorzata Lucińska
SWSlawomir T. Wierzchon
Slawomir T. Wierzchon
Very fast growth of empirical graphs demands clustering algorithms with nearly-linear time complexity. We propose a novel approach to clustering, based on random walks. The idea is to relax the standard spectral method and replace eigenvectors with vectors obtained by running early-stopped random walks. We abandoned iterating the random walk algorithm to convergence but instead stopped it after the time that is short compared with the mixing time. The computed vectors constitute a local approximation of the leading eigenvectors. The algorithm performance is competitive to the traditional spectral solutions in terms of computational complexity. We empirically evaluate the proposed approach against other exact and approximate methods. Experimental results show that the use of the early stop procedure does not influence the quality of the clustering on the tested real world data sets.