(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 12, No. 12, 2021 OBEInsights: Visual Analytics Design for Predictive OBE Knowledge Generation Leona Donna Lumius, Mohammad Fadhli Asli * Faculty of Computing and Informatics Universiti Malaysia Sabah, Malaysia Abstract—Gaining traction in modern higher education, outcome-based education (OBE) focuses on strategizing peda- gogical approaches to help the student achieve specified learning outcomes. In the context of Malaysia, OBE is oriented towards holistic development of graduates to ensure readiness towards the working sector. To empower OBE implementation, standardized measuring instrument iCGPA was introduced to higher education institutions nationwide. With lower dependency on provided curriculum, graduate abilities and values development are also attainable via extracurricular activities. However, analyzing the curriculum results in hand with extracurricular activities can be a daunting task, albeit the potential enriched performance assessment. In addition, the current iCGPA instrument employs radar map that restricts data exploration despite its capability in visualizing multivariate information. This study aims to enable predictive knowledge generation on understanding the relation- ship between learning activities and performance in OBE. There- fore, a predictive visual analytics system namely OBEInsights is proposed to facilitate education analysts in assessing OBE. The system development started with the identification of crucial design and analytic requirements via a domain expert case study. The system is then built with deliberate considerations of guiding factors of a design framework conceptualized from the case study. Subsequently, the system was then evaluated in usability testing with 10 domain experts that consist of usability rating and expert validation. The evaluation and expert validation results demonstrated the effectiveness and usability of OBEInsights in facilitating OBE predictive assessment. Several design insights on constructing visual analytics for OBE assessment were also discovered in terms of effective visualization, predictive modeling, and knowledge generation. Analytic designers and builders can leverage the reported design insights to enhance knowledge generation tools for OBE assessment. Keywords—Visual analytics; visualization; learning analytics; outcome-based education (OBE) I. I NTRODUCTION Outcome-based education (OBE) has become a prominent higher education strategy and pedagogical approach around the globe. OBE focuses on organizing teaching and assessment that help students achieve specified outcomes or goals [1]. Many countries have adopted the OBE approach in their higher education structures and initiatives along with addi- tional unique goals. In Malaysia, OBE in higher education is oriented towards the development of holistic graduates and readiness towards the working sector. To achieve this goal, an initiative and instrument namely Integrated Cumulative Grade Point (iCGPA) were introduced to Malaysian higher education institutions [2]. iCGPA helps the institutions in determining the graduate’s achievement based on the program learning outcomes (PLO) set by the faculty. The instrument also eases the recording of graduates’ ability and values attainment throughout the study program duration. The recorded data is then visualized in the form of a radar map, indicating the graduate’s improvement in terms of abilities and acquisition of values. However, graduate abilities and values attainments are also attainable via extracurricular activities with less dependency to the provided curriculum. Analyzing the curriculum results with extracurricular activities could provide enriched understandings towards assessing the student performance. Despite these potentials, merging curriculum results with extracurricular activities in an analysis can cause information overload. In addition, the current radar map representation of iCGPA restricts data exploration despite its capability in visualizing multivariate information. Visual analytics is a data exploration method supported by interactive visualization [3], allowing the analyst to pursue new inquiry throughout the exploration [4]. The main motivation of this study is to facilitate education analysts in performing predictive analysis on OBE learning activities and performance. Prior studies on educational visual analytics were observed to primarily focus on visualization tool creation and system features [5], [6]. Furthermore, this study found limited visualization work that discusses OBE-specific domain users, analysis tasks, and visualization design. This paper reports our empirical investigation on the visual- ization design for supporting OBE knowledge generation with regard to design requirements, development, and evaluation. To address the gap, this study proposes a predictive visual analytic namely OBEInsights that enables education analysts and practitioners to perform predictive OBE assessment. This study firstly explores the design requirements and analytic practices by interviewing 5 domain experts in a domain char- acterization case study. A design framework is conceptualized based on the identified requirements and analysis tasks from the case study. Next, the visual analytic OBEInsights was designed and developed with design consideration guidance of the framework. Subsequently, this study evaluated and demonstrated the effectiveness of OBEInsights in usability testing with 10 domain experts. The major contributions of this paper are as follows: 1) A novel visual analytics design framework for sup- porting OBE knowledge generation. 2) A visualization system namely OBEInsights for fa- cilitating OBE predictive learning analysis. 3) Empirical evaluation report to demonstrate the ef- fectiveness of OBEInsights in supporting knowledge generation. www.ijacsa.thesai.org 895 | Page