Detecting Online Risks and Supportive Interaction in Instant Messenger Conversations using Czech Transformers

Varování

Publikace nespadá pod Filozofickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.

Autoři	SOTOLÁŘ Ondřej PLHÁK Jaromír TKACZYK Michal LEBEDÍKOVÁ Michaela ŠMAHEL David
Rok publikování	2021
Druh	Článek ve sborníku
Konference	Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)
Fakulta / Pracoviště MU	Fakulta informatiky
Citace
www	Full text PDF Domovská stránka workshopu
Klíčová slova	Online Risks; Supportive Interaction; Facebook Messenger; Text Classification
Popis	We present a comparison of state-of-the-art models for text clas- sification of Online Risks and Supportive Interaction in anonymized In- stant Messenger conversations held in Czech. We compare the transformer models Czert, RobeCzech, and FERNET-C5 with the Fasttext classifier as a baseline. For the comparison, we build a novel dataset with five sub- categories for the Online Risks and five for the Supportive Interaction. We solve the balanced classification problem achieving 75.44 - 89.66 F1 score depending on the category. Our results show that the transformer models perform consistently better than the baseline.
Související projekty:	Modelling the future: Understanding the impact of technology on adolescent’s well-being