Automatized visualization methods for the qualitative analysis of teachers' collegial discussions

In this paper, we discuss a set of procedures for the visualization conversation data, based on machine learning and text mining algorithms. The methodological function these methods is to support (rather than substitute) humanistic interpretive qualitative data analysis. context our discussion study teachers’ communities. Enabling collegial among teachers has been argued play pivotal role in both professional development students’ learning. problem that discussions teachers, which are typically considered fruitful teachers' learning, time-consuming cognitively demanding. Several scholars have discussed potential including toolbox analysis as way analyze large sets solve time demand problem. However, literature discussing use research conceives algorithms substitutes work researcher. These automatized approaches introduced categorize substituting researcher process. contrast, rewards using discussions. We introduce semi-supervised topic modeling supervised classification how visualizations can provide additional elements useful Whereas do not substitute analysis, argue they researchers’ interpretations by reducing identifying patterns interactions, possibly, visualizing group-level