Integrasi AI dan Model Case Study dalam Perancangan Instrumen Tes Pemahaman Strategi Bertutur Mahasiswa PBSI FBS UNP

Integration of AI and Case Study Models in the Design of Test Instruments for Understanding Speaking Strategies for PBSI FBS UNP Students This study aims to identify the needs of students and lecturers for pragmatic learning evaluation instruments, describe the process of designing artificial intelligence (AI)-based test instruments with a Case Study model, and determine the feasibility of test instruments in measuring the understanding of speaking strategies of students of the Indonesian Language and Literature Education Study Program (PBSI), Faculty of Language and Arts, State University of Padang (FBS UNP). This research is motivated by the low understanding of students on the application of speaking strategies in accordance with pragmatic principles and the limitations of contextual and applicative evaluation instruments. This research uses the research and development (R&D) method with reference to the 4-D model, which is limited to the development stage, which is a test of the validity of the instrument. Validation is carried out by three validators consisting of learning experts, linguists, and graphic experts. Data were obtained through validation questionnaires and analyzed in a quantitative descriptive manner. The results showed that the AI-based pragmatic test instrument with the Case Study model obtained a content feasibility percentage of 77.5% (valid), linguistic feasibility of 84.61% (very valid), and graphic feasibility of 88.46% (very valid). Overall, the instrument obtained a validity value of 83.52% with a very valid category. Thus, the AI-based test instrument with the Case Study model is declared feasible to be used as a pragmatic learning evaluation instrument, although it still requires minor refinement according to the validator's suggestions.