Attention-based hierarchical recurrent neural networks for MOOC forum posts analysis

Massive open online courses (MOOCs) allow students and instructors to discuss through messages posted on a forum. However, the instructors should limit their interaction to the most critical tasks during MOOC delivery so, teacher-led scaffolding activities, such as forum-based support, can be very limited, even impossible in such environments. In addition, students who try to clarify the concepts through such collaborative tools could not receive useful answers, and the lack of interactivity may cause a permanent abandonment of the course. The purpose of this paper is to report the experimental findings obtained evaluating the performance of a text categorization tool capable of detecting the intent, the subject area, the domain topics, the sentiment polarity, and the level of confusion and urgency of a forum post, so that the result may be exploited by instructors to carefully plan their interventions. The proposed approach is based on the application of attention-based hierarchical recurrent neural networks, in which both a recurrent network for word encoding and an attention mechanism for word aggregation at sentence and document levels are used before classification. The integration of the developed classifier inside an existing tool for conversational agents, based on the academically productive talk framework, is also presented as well as the accuracy of the proposed method in the classification of forum posts.

Relocating Research on Teacher Learning: Toward Pedagogically Productive Talk

Most research and practice in teacher in-service learning focuses on formal professional development activities. This article calls for paying greater attention to the informal conversations that are embedded in teachers’ day-to-day work and through which they learn from one another what it means to be a teacher and how to perform their duties. The authors build on theory and research in teacher on-the-job discourse and learning in order to (a) argue that, as a field, we need to pay more focused and systematic attention to teacher on-the-job discourse; (b) offer a coherent conceptual framework for “pedagogically productive” teacher talk; and (c) highlight key research directions and challenges in investigating this and related phenomena.

Traditions, Research, and Practice Supporting Academically Productive Classroom Discourse

This article focuses on both research and practice relating to academically productive classroom discourse. We seek to “expand the conversation” to include newcomers to the field of classroom talk, as well as practitioners and youth researchers who want to contribute to knowledge building in this area. We first explore a variety of traditions, questions, and methods that have been prominent in work on classroom talk. We also summarize some key findings that have emerged over the past several decades: • Finding 1: Certain kinds of talk promote robust learning for ALL students. • Finding 2: The field lacks shared conceptualizations of what productive talk is and how best to characterize it. • Finding 3: Dialogic discourse is exceedingly rare in classrooms, at all grade levels and across all domains. • Finding 4: A helpful way forward: conceptualizing talk moves as tools. Following the presentation of each research finding we provide a set of commentaries—explicating and in some cases problematizing the findings. Finally, we provide some promising approaches that presume cultural and linguistic assets among both students and teachers, including curricular programs, teacher education, professional development programs, teacher research, and intergenerational communities of inquiry. In all of this, we try to make our own assumptions, traditions, and governing gazes explicit, as a multi-generational and multi-role group of authors, to encourage greater transparency among all who work in this important and potentially transformative field of study.