首页|Researcher at Purdue University Details Research in Machine Learning (Evaluating the Performance of Topic Modeling Techniques with Human Validation to Support Q ualitative Analysis)
Researcher at Purdue University Details Research in Machine Learning (Evaluating the Performance of Topic Modeling Techniques with Human Validation to Support Q ualitative Analysis)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Research findings on artificial intell igence are discussed in a new report. According to news reporting originating fr om West Lafayette, Indiana, by NewsRx correspondents, research stated, "Examinin g the effectiveness of machine learning techniques in analyzing engineering stud ents' decisionmaking processes through topic modeling during simulation-based d esign tasks is crucial for advancing educational methods and tools." Funders for this research include National Science Foundation. The news journalists obtained a quote from the research from Purdue University: "Thus, this study presents a comparative analysis of different supervised and un supervised machine learning techniques for topic modeling, along with human vali dation. Hence, this manuscript contributes by evaluating the effectiveness of th ese techniques in identifying nuanced topics within the argumentation framework and improving computational methods for assessing students' abilities and perfor mance levels based on their informed decisions. This study examined the decision -making processes of engineering students as they participated in a simulation-b ased design challenge. During this task, students were prompted to use an argume ntation framework to articulate their claims, evidence, and reasoning, by record ing their informed design decisions in a design journal. This study combined qua litative and computational methods to analyze the students' design journals and ensured the accuracy of the findings through the researchers' review and interpr etations of the results. Different machine learning models, including random for est, SVM, and K-nearest neighbors (KNNs), were tested for multilabel regression, using preprocessing techniques such as TF-IDF, GloVe, and BERT embeddings."
Purdue UniversityWest LafayetteIndia naUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesEn gineeringMachine Learning
NETL
NSTL
