RT Book, Section
T1 On the design and tuning of machine learning models for language toxicity classification in online platforms
A1 Rybinski, Maciej
A1 Miller, William
A1 Del Ser, Javier
A1 Bilbao, Miren Nekane
A1 Aldana-Montes, José F.
AB One of the most concerning drawbacks derived from the lack of supervision in online platforms is their exploitation by misbehaving users to deliver offending (toxic) messages while remaining unknown themselves. Given the huge volumes of data handled by these platforms, the detection of toxicity in exchanged comments and messages has naturally called for the adoption of machine learning models to automate this task. In the last few years Deep Learning models and related techniques have played a major role in this regard due to their superior modeling capabilities, which have made them stand out as the prevailing choice in the related literature. By addressing a toxicity classification problem over a real dataset, this work aims at throwing light on two aspects of this noted dominance of Deep Learning models: (1) an empirical assessment of their predictive gains with respect to traditional Shallow Learning models; and (2) the impact of using different text embedding methods and data augmentation techniques in this classification task. Our findings reveal that in our case study the application of non-optimized Shallow and Deep Learning models attains very competitive accuracy scores, thus leaving a narrow improvement margin for the fine-grained refinement of the models or the addition of data augmentation techniques.
PB Springer Verlag
SN 1860-949X
YR 2018
FD 2018
LK https://hdl.handle.net/11556/1625
UL https://hdl.handle.net/11556/1625
LA eng
NO Rybinski , M , Miller , W , Del Ser , J , Bilbao , M N & Aldana-Montes , J F 2018 , On the design and tuning of machine learning models for language toxicity classification in online platforms . in Studies in Computational Intelligence . Studies in Computational Intelligence , vol. 798 , Springer Verlag , pp. 329-343 . https://doi.org/10.1007/978-3-319-99626-4_29
NO Publisher Copyright: © 2018, Springer Nature Switzerland AG.
NO Acknowledgements. The work of Maciej Rybinski has been partially funded by grant TIN2017-86049-R (Ministerio de Economa, Industria y Competitividad, Spain). Javier Del Ser also thanks the Basque Government for its funding support through the EMAITEK program. The work of Maciej Rybinski has been partially funded by grant TIN2017-86049-R (Ministerio de Economa, Industria y Competitividad, Spain). Javier Del Ser also thanks the Basque Government for its funding support through the EMAITEK program.
DS TECNALIA Publications
RD 29 jul 2024