Scholars have applied automatic content analysis to study computer-mediated communication in computer-supported collaborative learning (CSCL). Since CSCL also takes place in face-to-face interactions, we studied the automatic coding accuracy of manually transcribed face-to-face communication. We conducted our study in an authentic higher-education physics context where computer-supported collaborative inquiry-based learning (CSCIL) is a popular pedagogical approach. Since learners’ needs for support in CSCIL vary in the different inquiry phases (orientation, conceptualization, investigation, conclusion, and discussion), we studied, first, how the coding accuracy of five computational models (based on word embeddings and deep neural networks with attention layers) differed in the various inquiry-based learning (IBL) phases when compared to human coding. Second, we investigated how the different features of the best performing computational model improved the coding accuracy. The study indicated that the accuracy of the best performing computational model (differentiated attention with pre-trained static embeddings) was slightly better than that of the human coder (58.9% vs. 54.3%). We also found that considering the previous and following utterances, as well as the relative position of the utterance, improved the model’s accuracy. Our method illustrates how computational models can be trained for specific purposes (e.g., to code IBL phases) with small data sets by using pre-trained models.
Artículo de publicación ISIOne important challenge in mathematics education is teaching modeling skills.
We analyze the logs from a game-based learning system used in a massively multiplayer
online tournament. Students had to detect an input–output pattern across 20 rounds. For each
round, they received an input and had 2 minutes to predict the output by selecting a binary
option (2 points if correct, −1 otherwise), or writing a model (4 points if model prediction
was correct, −4 otherwise), or refraining (1 point). Thousands of 3rd to 10th grade students
from hundreds of schools simultaneously played together on the web.We identified different
types of players using cluster analysis. From 5th grade onwards, we found a cluster of
students that wrote models with correct predictions. Half of the 7th to 10th grade students
that detected patterns were able to express them with models. The analysis also shows
diffusion within the teams of modeling strategies for simple patterns.Conicyt Project CIE-05 Center for Advanced Research on Education, BASAL-CMM
project Centro de Modelamiento Matemático U. de Chile and Fondef Grant TIC EDU TE10I001
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.