Enhancing project based learning with unsupervised learning of project reflections

• 主要作者: FWA, Hua Leong
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2021
• 主題: datasets; neural networks; project-based learning; Databases and Information Systems; Higher Education; Numerical Analysis and Scientific Computing
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/6858; https://ink.library.smu.edu.sg/context/sis_research/article/7861/viewcontent/3488466.3488480_pv.pdf

Natural Language Processing (NLP) is an area of research and application that uses computers to analyze human text. It has seen wide adoption within several industries but few studies have investigated it for use in evaluating the effectiveness of educational interventions and pedagogies. Pedagogies such as Project based learning (PBL) centers on learners solving an authentic problem or challenge which leads to knowledge creation and higher engagement. PBL also lends itself well in plugging the gap between what is taught in classrooms and applying the knowledge gained to the real working environment. In this study, we seek to investigate how we can use NLP techniques to uncover insights into and enhance our PBL process. Both topic modelling and sentiment analysis techniques are applied to analyze final year students’ reflections written as part of their final year project module. We described the entire process from text cleansing, pre-processing, modelling to visualization and evaluated the use of Latent Dirichlet Allocation and Attention Based Aspect Extraction for topic modelling. The results or visualizations which we derived from the topic and sentiment models showed that we can both effectively infer the key topics as reflected by our learners and extract actionable insights on the PBL process.