Design Model for Pedagogical Content Knowledge Supports Based on Artificial Intelligence–Automated Scores (Poster 5)

• In Event: Artificial Intelligence–Augmented Assessment Tools to Support Instruction in STEM

Abstract

Objectives
This poster illustrates a design model for developing instructional strategies to support the development of pedagogical content knowledge (PCK) based on students’ performances on assessment tasks with consideration of social, cultural, and academic backgrounds. PCK – integration of content knowledge and pedagogy – provides teachers with instructional strategies to support student learning. The Next Generation Science Standards’ (NGSS Lead States, 2013) vision for science proficiency calls for teachers to use DCIs, SEPs, and CCCs to explain phenomena. This requires changing formative assessment practices in classrooms. Although AI can automatically score constructed responses to save teachers’ time to score the items, teachers need to use PCK to make sense of what those results mean to inform instructional decisions.
To support the growth of PCK, we developed 1) a design model, 2) instructional strategies through analyzing and interpreting students’ performances on assessments, and 3) teaching scenarios to use those strategies. We conducted teacher interviews to explore two questions: 1) In what ways and to what extent do teachers perceive that the instructional strategies could help students achieve learning goals? and 2) how would teachers adapt these instructional strategies to meet the learning needs of subgroups of students concerning their cultural differences?
Theoretical Background and Design Model
PCK promotes high-quality teaching and improvement of learning (Shulman, 1987). The literature proposes components of PCK, including teacher knowledge of students’ academic, social, and cultural backgrounds (Cochran, et al., 1993; Magnusson et al., 1999). Our design model uses five steps to support PCK development: (1) Clarification of learning goals, (2) assessment for characterizing student performances, (3) identification of student academic, social and cultural backgrounds, (4) culturally appropriate instructional strategies, and (5) supports for adapting instructional practices (Figure 2).
Procedures and participants
We developed a structured interview to elicit feedback on the design model and instructional strategies. Six lead teachers representing three low SES and three middle SES communities served as participants.
Findings and data analysis
Thematic analysis (Braun, & Clarke, 2006) found patterns across teachers’ responses. The teachers perceived that the PCK supports provided appropriate prompts and students’ performances on the assessment for teachers to make decisions in selecting and adapting instructional strategies to support the needs of each group. Five themes emerged from the analysis: 1) knowledge of scientific ideas was perceived to be necessary for using scientific practices, 2) contextualization was viewed as important and tied to relevant phenomena and familiar objects, 3) hands-on experiences were deemed as essential, 4) starting with simple and building to complex ideas using the same activity over an instructional period was thought to help gain proficiency, and 5) attending to language, learning modalities, and accessibility was perceived to foster fairness and equity.
Discussion and Implications
The results suggest that the model guides the process of instructional strategy development to support teachers’ PCK. We speculate that experienced teachers' content-specific strategies were similar despite different student academic, social, and cultural backgrounds. To support teacher PCK development, professional learning is needed to provide opportunities for formative assessment practices.

Authors

• Namsoo Shin, Michigan State University
  Presenting Author

• Peng He, Michigan State University
  Presenting Author

• Katherine Joy Nilsen, WestEd
  Presenting Author

• Holly Kennedy Amerman, University of Georgia
  Presenting Author

• Joseph S. Krajcik, Michigan State University
  Presenting Author

• Xiaoming Zhai, University of Georgia
  Presenting Author