dnagogl.blogg.se

BERT and its variants help to reduce the burden of complex annotation work in many interdisciplinary research areas, for example, legal argument mining in digital humanities. The contextual word embedding model, BERT, has proved its ability on downstream tasks with limited quantities of annotated data. Pedagogical implications and future research are discussed at the end of this paper. Through correlation analysis and stepwise regression analysis, the findings reveal that achievement goals could positively and negatively predict different types of argumentative discourse styles while the personality traits could positively predict three types of argumentative discourse styles. Students’ achievement goals and personality traits were obtained through questionnaires, and their argumentative discourse styles were characterized by the actual argumentative moves they made during the collaborative argumentation. Students were arranged into ten groups with four based on their standpoints of the topic, and each team had two supporters and two opponents. Therefore, the current study attempted to fill in this gap by conducting a self-designed collaborative scientific argumentation activity and 40 undergraduates participated.

However, the related empirical evidence revealing how the achievement goals and personality traits are related to discourse styles is limited. Some researchers proposed that two learners’ individual characteristics, including achievement goals and personality traits, could be potential factors that induce different argumentative discourse styles. Different argumentative discourse styles will have different effects on science learning.