Agata Filipowska
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
Research Subjects
Agata Filipowska has a total of 74 co-authors. Here are the top co-authors by number of shared publications:
- Monika Kaczmarek
University of Duisburg-Essen
11 shared publications - Witold Abramowicz
Department of Information Systems, Poznan University of Economics and Business, 61-875 Poznan, Poland
7 shared publications - Dominik Filipiak
AI Clearing Inc., Austin, TX, USA
5 shared publications Andrzej Bassara
The Poznan University of Economics, Poland
3 shared publications- Krzysztof Węcel
Poznań University of Economics and Business, Poznań, Poland
3 shared publications - Marek Kowalkiewicz
Queensland University of Technology
3 shared publications
Latest Publications
- Open Access
Explorative Insights into Local Immune Response to BK Virus—A Cross-Sectional Study in Urine Samples Between Transplant Recipients and Non-Immunocompromised Hosts
Background and Objectives: BK virus (BKPyV) is a common latent pathogen in humans, but it becomes particularly insidious in kidney transplant recipients, where reactivation may contribute to allograft loss. The immune mechanisms controlling BKPyV latency in immunocompromised hosts remain incompletely understood. We assume the urinary immune proteome reflects local immune response in the kidney and the urinary tract. Thus, this study aimed to determine whether the presence of BKPyV alters the urinary immune-related proteomic profile of kidney transplant recipients and shifts it away to that observed in healthy individuals. Materials and Methods: 137 urine samples were collected from kidney recipients, both BKPyV-positive and BKPyV-negative, patients with stage 5 chronic kidney disease, and healthy controls. Targeted proteomic analysis was performed using the proximity extension assay, followed by heatmapping, principal component analysis, random forest, and linear regression modeling. Results: The urinary proteome of BKPyV-positive recipients remained more distinct from healthy controls than that of BKPyV-negative ones. Among the 33 proteins detected across all samples, 17 showed significant intergroup differences, with KLRD1 (CD94) uniquely upregulated in all transplant recipients, but downregulated in BKPyV-positive samples. Conclusions: We conclude that the presence of BKPyV in the urinary tract of kidney recipients notably interplays with the local immune response even in the absence of clinical disease.
Open AccessExplorative Insights into Local Immune Response to BK Virus—A Cross-Sectional Study in Urine Samples Between Transplant Recipients and Non-Immunocompromised Hosts
Background and Objectives: BK virus (BKPyV) is a common latent pathogen in humans, but it becomes particularly insidious in kidney transplant recipients, where reactivation may contribute to allograft loss. The immune mechanisms controlling BKPyV latency in immunocompromised hosts remain incompletely understood. We assume the urinary immune proteome reflects local immune response in the kidney and the urinary tract. Thus, this study aimed to determine whether the presence of BKPyV alters the urinary immune-related proteomic profile of kidney transplant recipients and shifts it away to that observed in healthy individuals. Materials and Methods: 137 urine samples were collected from kidney recipients, both BKPyV-positive and BKPyV-negative, patients with stage 5 chronic kidney disease, and healthy controls. Targeted proteomic analysis was performed using the proximity extension assay, followed by heatmapping, principal component analysis, random forest, and linear regression modeling. Results: The urinary proteome of BKPyV-positive recipients remained more distinct from healthy controls than that of BKPyV-negative ones. Among the 33 proteins detected across all samples, 17 showed significant intergroup differences, with KLRD1 (CD94) uniquely upregulated in all transplant recipients, but downregulated in BKPyV-positive samples. Conclusions: We conclude that the presence of BKPyV in the urinary tract of kidney recipients notably interplays with the local immune response even in the absence of clinical disease.
- 2 January 2026
- Published by Springer Nature
- p. 16-27
Supporting the Mental Health Care with Artificial Intelligence Chatbots
- 2 January 2026
- Published by Springer Nature
- p. 16-27
Supporting the Mental Health Care with Artificial Intelligence Chatbots
- Open Access
- 1 August 2024
- Published by MDPI AG in Electronics
- Vol. 13 (15) , 3049
Job Recommendations: Benchmarking of Collaborative Filtering Methods for Classifieds
Classifieds pose numerous challenges for recommendation methods, including the temporary visibility of ads, the anonymity of most users, and the fact that typically only one user can consume an advertised item. In this work, we address these challenges by choosing models and evaluation procedures that are considered accurate, diverse, and efficient (in terms of memory and time consumption during training and prediction). This paper aims to benchmark various recommendation methods for job classifieds, using OLX Jobs as an example, to enhance the conversion rate of advertisements and user satisfaction. In our research, we implement scalable methods and represent different approaches to the recommendations: Alternating Least Square (ALS), LightFM, Prod2Vec, RP3Beta, and Sparse Linear Methods (SLIM). We conducted A/B tests by sending millions of messages with recommendations to perform online evaluations of selected methods. In addition, we have published the dataset created for our research. To the best of our knowledge, this is the first dataset of its kind. It contains 65,502,201 events performed on OLX Jobs by 3,295,942 users who interacted with (displayed, replied to, or bookmarked) 185,395 job ads over two weeks in 2020. We demonstrate that RP3Beta, SLIM, and ALS perform significantly better than Prod2Vec and LightFM when tested in a laboratory setting. Online A/B tests also show that sending messages with recommendations generated by the ALS and RP3Beta models increases the number of users contacting advertisers. Additionally, RP3Beta had a 20% more significant impact on this metric than ALS.
- 1 August 2024
- Published by MDPI AG in Electronics
- Vol. 13 (15) , 3049
Open AccessJob Recommendations: Benchmarking of Collaborative Filtering Methods for Classifieds
Classifieds pose numerous challenges for recommendation methods, including the temporary visibility of ads, the anonymity of most users, and the fact that typically only one user can consume an advertised item. In this work, we address these challenges by choosing models and evaluation procedures that are considered accurate, diverse, and efficient (in terms of memory and time consumption during training and prediction). This paper aims to benchmark various recommendation methods for job classifieds, using OLX Jobs as an example, to enhance the conversion rate of advertisements and user satisfaction. In our research, we implement scalable methods and represent different approaches to the recommendations: Alternating Least Square (ALS), LightFM, Prod2Vec, RP3Beta, and Sparse Linear Methods (SLIM). We conducted A/B tests by sending millions of messages with recommendations to perform online evaluations of selected methods. In addition, we have published the dataset created for our research. To the best of our knowledge, this is the first dataset of its kind. It contains 65,502,201 events performed on OLX Jobs by 3,295,942 users who interacted with (displayed, replied to, or bookmarked) 185,395 job ads over two weeks in 2020. We demonstrate that RP3Beta, SLIM, and ALS perform significantly better than Prod2Vec and LightFM when tested in a laboratory setting. Online A/B tests also show that sending messages with recommendations generated by the ALS and RP3Beta models increases the number of users contacting advertisers. Additionally, RP3Beta had a 20% more significant impact on this metric than ALS.
- Open Access
- 25 January 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 54 (2) , 1893-1908
KGTN-ens: few-shot image classification with knowledge graph ensembles
- 25 January 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 54 (2) , 1893-1908
Open AccessKGTN-ens: few-shot image classification with knowledge graph ensembles
- Open Access
- 22 July 2023
- Published by Narxoz University - Non-profit joint stock company in Central Asian Economic Review
- No. 2,p. 105-117
Impact of ESG on the investment attractiveness of business
Purpose. The main goal in initiating this study was to explore the impact and exposure of these factors, through a review of significant research works by leading world scientists in this field.Methodology. To conduct the study, there was used a scientometric methodology with a selection of the most cited studies in the ESG field in Science Direct, Scopus, and Web of Science databases, which provided the information basis for the research. General scientific methods (synthesis, induction, grouping) formed the basis of the research methodology carried out in the format of a literature review.Originality / value of the research. The value of the research results is determined by the formulation of key research areas on ESG issues in the context of the application in the investment analysis methodology. In particular, questions were raised about the importance of ESG principles in evaluating companies for their investment attractiveness.Findings. As a result of the study, there were established groups of scientific research areas concerning the ESG impact on the development of corporate governance and assessment of companies' investment attractiveness. These recommendations are addressed both to analysts when developing reports for investors to make investment decisions, and to the companies themselves, which will be able to adjust their actions in achieving sustainable development goals, understanding the significance of the non-financial information they provide in investment analysis.
- 22 July 2023
- Published by Narxoz University - Non-profit joint stock company in Central Asian Economic Review
- No. 2,p. 105-117
Open AccessImpact of ESG on the investment attractiveness of business
Purpose. The main goal in initiating this study was to explore the impact and exposure of these factors, through a review of significant research works by leading world scientists in this field.Methodology. To conduct the study, there was used a scientometric methodology with a selection of the most cited studies in the ESG field in Science Direct, Scopus, and Web of Science databases, which provided the information basis for the research. General scientific methods (synthesis, induction, grouping) formed the basis of the research methodology carried out in the format of a literature review.Originality / value of the research. The value of the research results is determined by the formulation of key research areas on ESG issues in the context of the application in the investment analysis methodology. In particular, questions were raised about the importance of ESG principles in evaluating companies for their investment attractiveness.Findings. As a result of the study, there were established groups of scientific research areas concerning the ESG impact on the development of corporate governance and assessment of companies' investment attractiveness. These recommendations are addressed both to analysts when developing reports for investors to make investment decisions, and to the companies themselves, which will be able to adjust their actions in achieving sustainable development goals, understanding the significance of the non-financial information they provide in investment analysis.
- Open Access
Job recommendations: benchmarking of collaborative filtering methods for classifieds
Classifieds provide many challenges for recommendation methods, due to the limited information regarding users and items. In this paper, we explore recommendation methods for classifieds using the example of OLX Jobs. The goal of the paper is to benchmark different recommendation methods for jobs classifieds in order to improve advertisements' conversion rate and user satisfaction. In our research, we implemented methods that are scalable and represent different approaches to recommendation, namely ALS, LightFM, Prod2Vec, RP3beta, and SLIM. We performed a laboratory comparison of methods with regard to accuracy, diversity, and scalability (memory and time consumption during training and in prediction). Online A/B tests were also carried out by sending millions of messages with recommendations to evaluate models in a real-world setting. In addition, we have published the dataset that we created for the needs of our research. To the best of our knowledge, this is the first dataset of this kind. The dataset contains 65,502,201 events performed on OLX Jobs by 3,295,942 users, who interacted with (displayed, replied to, or bookmarked) 185,395 job ads in two weeks of 2020. We demonstrate that RP3beta, SLIM, and ALS perform significantly better than Prod2Vec and LightFM when tested in a laboratory setting. Online A/B tests also demonstrated that sending messages with recommendations generated by the ALS and RP3beta models increases the number of users contacting advertisers. Additionally, RP3beta had a 20% greater impact on this metric than ALS.
Open AccessJob recommendations: benchmarking of collaborative filtering methods for classifieds
Classifieds provide many challenges for recommendation methods, due to the limited information regarding users and items. In this paper, we explore recommendation methods for classifieds using the example of OLX Jobs. The goal of the paper is to benchmark different recommendation methods for jobs classifieds in order to improve advertisements' conversion rate and user satisfaction. In our research, we implemented methods that are scalable and represent different approaches to recommendation, namely ALS, LightFM, Prod2Vec, RP3beta, and SLIM. We performed a laboratory comparison of methods with regard to accuracy, diversity, and scalability (memory and time consumption during training and in prediction). Online A/B tests were also carried out by sending millions of messages with recommendations to evaluate models in a real-world setting. In addition, we have published the dataset that we created for the needs of our research. To the best of our knowledge, this is the first dataset of this kind. The dataset contains 65,502,201 events performed on OLX Jobs by 3,295,942 users, who interacted with (displayed, replied to, or bookmarked) 185,395 job ads in two weeks of 2020. We demonstrate that RP3beta, SLIM, and ALS perform significantly better than Prod2Vec and LightFM when tested in a laboratory setting. Online A/B tests also demonstrated that sending messages with recommendations generated by the ALS and RP3beta models increases the number of users contacting advertisers. Additionally, RP3beta had a 20% greater impact on this metric than ALS.
- Open Access
KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles
We propose KGTN-ens, a framework extending the recent Knowledge Graph Transfer Network (KGTN) in order to incorporate multiple knowledge graph embeddings at a small cost. We evaluate it with different combinations of embeddings in a few-shot image classification task. We also construct a new knowledge source - Wikidata embeddings - and evaluate it with KGTN and KGTN-ens. Our approach outperforms KGTN in terms of the top-5 accuracy on the ImageNet-FS dataset for the majority of tested settings.
Open AccessKGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles
We propose KGTN-ens, a framework extending the recent Knowledge Graph Transfer Network (KGTN) in order to incorporate multiple knowledge graph embeddings at a small cost. We evaluate it with different combinations of embeddings in a few-shot image classification task. We also construct a new knowledge source - Wikidata embeddings - and evaluate it with KGTN and KGTN-ens. Our approach outperforms KGTN in terms of the top-5 accuracy on the ImageNet-FS dataset for the majority of tested settings.
- 16 April 2021
- Published by Springer Nature
- p. 560-571
Project Comparison Method Supporting Participatory Budget Process - Poznan Case Study
- 16 April 2021
- Published by Springer Nature
- p. 560-571
Project Comparison Method Supporting Participatory Budget Process - Poznan Case Study
- 2 November 2020
- Published by Springer Nature
- p. 25-39
Introduction to Text Analytics
- 3 January 2019
- Published by Springer Nature
- p. 63-76
Profiling User Colour Preferences with BFI-44 Personality Traits
- 3 January 2019
- Published by Springer Nature
- p. 63-76
Profiling User Colour Preferences with BFI-44 Personality Traits