使用机器学习探究大学生群体的幸福感
Introspecting the Happiness amongst University Students using Machine Learning
AI总结：
本研究针对大学生幸福感问题，结合统计分析与机器学习聚类方法，在多数据集上验证了结合聚类的RF模型性能最优，明确了不同院系幸福感差异及各影响因素的相关性与显著性。
摘要：
幸福感体现了特定人群基于积极心理结果的直观建构，是认知能力的基石，探究大学生幸福感近年来已成为研究者的核心议题。本研究通过统计分布图分析大学生幸福感及其维度，并设计了相关研究问题。此外，研究分别将回归分析、机器学习与聚类算法应用于世界幸福数据集与大学生数据集进行训练与测试。结果显示，哲学系是幸福感最高的院系，社会学系最低，平均幸福感得分分别为2.8与2.44；健康维度的皮尔逊相关系数为0.74；预测幸福感得分为5.2，模型拟合优度为51%，训练误差与测试误差分别为0.52与0.47。在5%的置信区间（CI）下，校园环境（CE）与大学声誉（UR）的p值最小，课外活动（ECA）与工作平衡（WB）的p值最大，分别为0.184与0.228。结合聚类的随机森林（RF）准确率最高（89%）、F值最高（0.98）且误差最低（17.91%），是本研究的最优模型。
英文摘要：
Happiness underlines the intuitive constructs of a specified population based on positive psychological outcomes. It is the cornerstone of the cognitive skills and exploring university student's happiness has been the essence of the researchers lately. In this study, we have analyzed the university student's happiness and its facets using statistical distribution charts; designing research questions. Furthermore, regression analysis, machine learning, and clustering algorithms were applied on the world happiness dataset and university student's dataset for training and testing respectively. Philosophy was the happiest department while Sociology the saddest; average happiness score being 2.8 and 2.44 respectively. Pearson coefficient of correlation was 0.74 for Health. Predicted happiness score was 5.2 and the goodness of model fit was 51%. train and test error being 0.52, 0.47 respectively. On a Confidence Interval(CI) of 5% p-value was least for Campus Environment(CE) and University Reputation(UR) and maximum for Extra-curricular Activities(ECA) and Work Balance(WB) (i.e. 0.184 and 0.228 respectively). RF with Clustering got the highest accuracy(89%) and F score(0.98) and the least error(17.91%), hence turned out to be best for our study
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
