skip to main content


Title: The TalkMoves dataset: K-12 mathematics lesson transcripts annotated for teacher and student discursive moves.
Transcripts of teaching episodes can be effective tools to understand discourse patterns in classroom instruction. According to most educational experts, sustained classroom discourse is a critical component of equitable, engaging, and rich learning environments for students. This paper describes the TalkMoves dataset, composed of 567 human annotated K-12 mathematics lesson transcripts (including entire lessons or portions of lessons) derived from video recordings. The set of transcripts primarily includes in-person lessons with whole-class discussions and/or small group work, as well as some online lessons. All of the transcripts are human-transcribed, segmented by the speaker (teacher or student), and annotated at the sentence level for ten discursive moves based on accountable talk theory. In addition, the transcripts include utterance-level information in the form of dialogue act labels based on the Switchboard Dialog Act Corpus. The dataset can be used by educators, policymakers, and researchers to understand the nature of teacher and student discourse in K-12 math classrooms. Portions of this dataset have been used to develop the TalkMoves application, which provides teachers with automated, immediate, and actionable feedback about their mathematics instruction.  more » « less
Award ID(s):
1837986
NSF-PAR ID:
10387284
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Proceedings of the 13th Conference on Language Resources and Evaluation
Page Range / eLocation ID:
4654-4662
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Inclusion in mathematics education is strongly tied to discourse rich classrooms, where students ideas play a central role. Talk moves are specific discursive practices that promote inclusive and equitable participation in classroom discussions. This paper describes the development of the TalkMoves application, which provides teachers with detailed feedback on their usage of talk moves based on accountable talk theory. Building on our recent work to automate the classification of teacher talk moves, we have expanded the application to also include feedback on a set of student talk moves. We present results from several deep learning models trained to classify student sentences into student talk moves with performance up to 73% F1. The classroom data used for training these models were collected from multiple sources that were pre-processed and annotated by highly reliable experts. We validated the performance of the model on an out-of-sample dataset which included 166 classroom transcripts collected from teachers piloting the application. 
    more » « less
  2. null (Ed.)
    TalkMoves is an innovative application designed to support K-12 mathematics teachers to reflect on, and continuously improve their instructional practices. This application combines state-of-the-art natural language processing capabilities with automated speech recognition to automatically analyze classroom recordings and provide teachers with personalized feedback on their use of specific types of discourse aimed at broadening and deepening classroom conversations about mathematics. These specific discourse strategies are referred to as “talk moves” within the mathematics education community and prior research has documented the ways in which systematic use of these discourse strategies can positively impact student engagement and learning. In this article, we describe the TalkMoves application’s cloud-based infrastructure for managing and processing classroom recordings, and its interface for providing teachers with feedback on their use of talk moves during individual teaching episodes. We present the series of model architectures we developed, and the studies we conducted, to develop our best-performing, transformer-based model (F1 = 79.3%). We also discuss several technical challenges that need to be addressed when working with real-world speech and language data from noisy K-12 classrooms. 
    more » « less
  3. null (Ed.)
    TalkMoves is an innovative application designed to support K-12 mathematics teachers to reflect on, and continuously improve their instructional practices. This application com- bines state-of-the-art natural language processing capabilities with automated speech recognition to automatically analyze classroom recordings and provide teachers with personalized feedback on their use of specific types of discourse aimed at broadening and deepening classroom conversations about mathematics. These specific discourse strategies are referred to as “talk moves” within the mathematics education com- munity and prior research has documented the ways in which systematic use of these discourse strategies can positively impact student engagement and learning. In this article, we describe the TalkMoves application’s cloud-based infrastruc- ture for managing and processing classroom recordings, and its interface for providing teachers with feedback on their use of talk moves during individual teaching episodes. We present the series of model architectures we developed, and the studies we conducted, to develop our best-performing, transformer-based model (F1 = 79.3%). We also discuss sev- eral technical challenges that need to be addressed when working with real-world speech and language data from noisy K-12 classrooms. 
    more » « less
  4. Effective K-12 integrated STEM education should reflect an intentional effort to adequately represent and facilitate each of its component disciplines in a meaningful way. However, most research in this space has been conducted within the context of science classrooms, ignoring mathematics. Also missing from the literature is research that examines the level of cognitive demand required from mathematical tasks present within integrated STEM lessons. In order to seek insight pertaining to this gap in the literature, we sought to better understand how science teachers use mathematics within K-12 integrated STEM instruction. We used an explanatory sequential mixed methods research design to explore the enactment of mathematics in integrated STEM lessons that focus on physical, earth, and life science content. We first examined 2030 sets of video-recorded classroom observation scores generated from the 10-item STEM Observation Protocol (STEM-OP) designed for observing integrated STEM education in K-12 classrooms. We compared the STEM-OP scores of classroom observations that included mathematics with those that did not. This quantitative analysis was followed by a closer, more in-depth qualitative examination of how mathematics was employed, focusing on the degree of cognitive demand. To do this, we coded and analyzed transcripts from video-recorded classroom observations in which mathematical content was present. Our study yielded two main findings about mathematics in integrated STEM lessons: (1) the presence of mathematical content resulted in higher STEM-OP scores on nearly all items, and (2) mathematical tasks within these lessons were categorized as requiring mainly low levels of cognitive demand from students. This study highlights the need for the increased inclusion of mathematical tasks in integrated STEM teaching. Implications for including higher-order mathematical thinking within integrated STEM teaching are discussed.

     
    more » « less
  5. Despite efforts to diversify the science, technology, engineering, and mathematics (STEM) workforce, engineering remains a White, male-dominated profession. Often, women and underrepresented students do not identify with STEM careers and many opt out of STEM pathways prior to entering high school or college. In order to broaden participation in engineering, new methods of engaging and retaining those who are traditionally underrepresented in engineering are needed. This work is based on a promising approach for encouraging and supporting diverse participation in engineering: disciplinary literacy instruction (DLI). Generally, teachers use DLI to provide K-12 students with a framework for interpreting, evaluating, and generating discipline-specific texts. This instruction provides students with an understanding of how experts in the discipline read, engage, and generate texts used to solve problems or communicate information. While models of disciplinary literacy have been developed and disseminated in several humanities and science fields, there is a lack of empirical and theoretical research that examines the use of DLI within the engineering domain. It is thought that DLI can be used to foster diverse student interest in engineering from a young age by removing literacy-based barriers that often discourage underrepresented students from entering and pursuing careers in STEM fields. This work-in-progress paper describes a new study underway to develop and disseminate a model of disciplinary literacy in engineering. During this project, researchers will observe, interview, and collect written artifacts from engineers working across four sub-disciplines of engineering: aerospace/mechanical, biological, civil/environmental, and electrical/computer. Data that will be collected include interview transcripts, observation field notes, engineer logs of literacy practices, and photographs of texts that the engineers read and write. Data will be analyzed using constant comparative analytic (CCA) methods. CCA will be used to generate theoretical codes from the data that will form the basis for a model of disciplinary literacy in engineering. As a primary outcome of this research, the engineering DLI model will promote the use of DLI practices within K-12 engineering instruction in order to assist and encourage diverse, underrepresented students to engage in engineering courses of study and pursue STEM careers. Thus far, the research team has begun collecting and analyzing data from two electrical engineers. This work in progress paper will report on preliminary findings, as well as implications for K-12 classroom instruction. For instance, this study has shed insights on how engineers use texts as part of the process of conducting failure analysis, and the research team has begun to conceptualize how these types of texts might be used with K-12 students to help them conduct failure analyses during design testing. Ultimately, this project will result in a list of grade-appropriate texts, evaluative frameworks, and activities (e.g., failure analysis in testing) that K-12 engineering teachers can use to prepare their diverse students to think, act, read, and write like engineers. 
    more » « less