@phdthesis{oai:kitami-it.repo.nii.ac.jp:02000332,
 author = {Eronen Juuso Kalevi Kristian},
 month = {Sep},
 note = {In this thesis, I study two different methods for improving multilingual automatic cyberbullying
detection. First, I study the effectiveness of Feature Density (FD) using different linguisticallybacked
feature preprocessing methods in order to estimate dataset complexity, which in turn is
used to comparatively estimate the potential performance of machine learning (ML) classifiers
prior to any training. I hypothesize that estimating dataset complexity allows for the reduction
of the number of required experiments iterations, making it possible to optimize the resourceintensive
training of ML models which is becoming a serious issue due to the increases in available
dataset sizes and the ever rising popularity of models based on Deep Neural Networks (DNN).
The problem of constantly increasing needs for more powerful computational resources is also
affecting the environment due to alarmingly-growing amount of CO2 emissions caused by training
of large-scale ML models. I use cyberbullying datasets collected for multiple languages, namely
English, Japanese and Polish. The difference in linguistic complexity of datasets allows me to
additionally discuss the efficacy of linguistically-backed word preprocessing.
Second, I study the selection of transfer languages for automatic abusive language detection.
I demonstrate the effectiveness of cross-lingual transfer learning for zero-shot abusive language
detection. This way it is possible to use existing data from higher-resource languages to build
better detection systems for languages lacking data. The datasets are from eight different languages
from three language families. I measure the distance between the languages using several language
similarity measures, especially by quantifying the World Atlas of Language Structures. I show
that there is a correlation between linguistic similarity and classifier performance, making it
possible to choose an optimal transfer language for zero shot abusive language detection.
Next, I demonstrate that this method is also generally applicable to multiple Natural Language
Processing tasks, specifically sentiment analysis, named entity recognition and dependency parsing.
I show that there is also a correlation between linguistic similarity and zero-shot cross-lingual
transfer performance for these tasks, allowing me to select an ideal transfer language in order to
aid with the problem of dealing with languages that do not currently have a sufficient amount
of data. Lastly, I show that the World Atlas of Language Structures can be quantified into an
effective linguistic similarity method.},
 school = {北見工業大学},
 title = {素性密度及びクロスリンガルゼロショット転移学習による多言語のネットいじめ自動検出の改良に関する研究},
 year = {2022}
}