Výsledky vyhledávání - "Leliwa, Gniewosz"

Report

Exploring the Potential of Feature Density in Estimating Machine Learning Classifier Performance with Application to Cyberbullying Detection

Autor: Eronen, Juuso, Ptaszynski, Michal, Masui, Fumito, Leliwa, Gniewosz, Wroczynski, Michal

Publikováno v: he 7th Workshop on Linguistic and Cognitive Approaches to Dialog Agents (LaCATODA 2021) collocated with IJCAI 2021,August 21--26th, 2021, Montreal, Canada. CEUR Workshop Proceedings 2935, 5-14

In this research. we analyze the potential of Feature Density (HD) as a way to comparatively estimate machine learning (ML) classifier performance prior to training. The goal of the study is to aid in solving the problem of resource-intensive trainin

Externí odkaz: http://arxiv.org/abs/2206.01949

Zobrazit plný text záznamu

Report

Initial Study into Application of Feature Density and Linguistically-backed Embedding to Improve Machine Learning-based Cyberbullying Detection

Autor: Eronen, Juuso, Ptaszynski, Michal, Masui, Fumito, Leliwa, Gniewosz, Wroczynski, Michal, Piech, Mateusz, Smywinski-Pohl, Aleksander

Publikováno v: Proceedings of The 6th Linguistic and Cognitive Approaches to Dialog Agents (LaCATODA 2020) IJCAI 2020 Workshop, Yokohama, Japan, January 2020

In this research, we study the change in the performance of machine learning (ML) classifiers when various linguistic preprocessing methods of a dataset were used, with the specific focus on linguistically-backed embeddings in Convolutional Neural Ne

Externí odkaz: http://arxiv.org/abs/2206.01889

Zobrazit plný text záznamu

Report

Transfer Language Selection for Zero-Shot Cross-Lingual Abusive Language Detection

Autor: Eronen, Juuso, Ptaszynski, Michal, Masui, Fumito, Arata, Masaki, Leliwa, Gniewosz, Wroczynski, Michal

Publikováno v: Information Processing & Management, Volume 59, Issue 4, July 2022, paper ID: 102981

We study the selection of transfer languages for automatic abusive language detection. Instead of preparing a dataset for every language, we demonstrate the effectiveness of cross-lingual transfer learning for zero-shot abusive language detection. Th

Externí odkaz: http://arxiv.org/abs/2206.00962

Zobrazit plný text záznamu

Report

Improving Classifier Training Efficiency for Automatic Cyberbullying Detection with Feature Density

Autor: Eronen, Juuso, Ptaszynski, Michal, Masui, Fumito, Smywiński-Pohl, Aleksander, Leliwa, Gniewosz, Wroczynski, Michal

Publikováno v: Information Processing and Management, Vol. 58, Issue 5, September 2021, paper ID: 102616

We study the effectiveness of Feature Density (FD) using different linguistically-backed feature preprocessing methods in order to estimate dataset complexity, which in turn is used to comparatively estimate the potential performance of machine learn

Externí odkaz: http://arxiv.org/abs/2111.01689

Zobrazit plný text záznamu

Report

Cyberbullying Detection -- Technical Report 2/2018, Department of Computer Science AGH, University of Science and Technology

Autor: Ptaszyński, Michał, Leliwa, Gniewosz, Piech, Mateusz, Smywiński-Pohl, Aleksander

The research described in this paper concerns automatic cyberbullying detection in social media. There are two goals to achieve: building a gold standard cyberbullying detection dataset and measuring the performance of the Samurai cyberbullying detec

Externí odkaz: http://arxiv.org/abs/1808.00926

Zobrazit plný text záznamu