Semantic Scholar Open Access 2022 4 sitasi

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

J. Eronen M. Ptaszynski Fumito Masui Gniewosz Leliwa Michal +1 lainnya

Abstrak

In this research, we analyze the potential of Feature Density (FD) 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 training of ML models which is becoming a serious issue due to continuously increasing dataset sizes and the ever rising popularity of Deep Neural Networks (DNN). The issue of constantly increasing demands for more powerful computational resources is also af- fecting the environment, as training large-scale ML models are causing alarmingly-growing amounts of COz emissions. Our approach is to optimize the resource-intensive training of ML models for Nat-ural Language Processing to reduce the number of required experiments iterations. We expand on previous attempts on improving classifier training ef-ficiency with FD while also providing an insight to the effectiveness of various linguistically-backed feature preprocessing methods for dialog classifica- tion, specifically cyberbullying detection.

Topik & Kata Kunci

Penulis (6)

J

J. Eronen

M

M. Ptaszynski

F

Fumito Masui

G

Gniewosz Leliwa

M

Michal

W

Wroczynski

Format Sitasi

Eronen, J., Ptaszynski, M., Masui, F., Leliwa, G., Michal, Wroczynski (2022). Exploring the Potential of Feature Density in Estimating Machine Learning Classifier Performance with Application to Cyberbullying Detection. https://doi.org/10.48550/arXiv.2206.01949

Akses Cepat

Lihat di Sumber doi.org/10.48550/arXiv.2206.01949
Informasi Jurnal
Tahun Terbit
2022
Bahasa
en
Total Sitasi
Sumber Database
Semantic Scholar
DOI
10.48550/arXiv.2206.01949
Akses
Open Access ✓