Scholarlink

<p>Understanding student satisfaction in higher education requires more than standardized survey scores alone. While structured survey responses provide standardized and comparable measures of satisfaction, they often fail to capture the heterogeneity of students’ experiences. In contrast, unstructured textual feedback offers a more in-depth understanding but is less easily quantifiable. A data-driven approach to quality evaluation that combines both structured and unstructured data offers a more comprehensive perspective. To combine these perspectives, we investigate both Structural Equation&#xa0;Modeling (SEM) of structured questionnaire data and topic modeling of open-ended responses. Two complementary approaches are adopted: the Structural Topic Model (STM), used to explore lexical and thematic differences between positive aspects and areas for improvement, and the semi-supervised SeededLDA, employed to identify topics guided by the vocabulary characteristic of student groups defined by their latent satisfaction levels. The analysis draws on responses from over 5000 students at an Italian University, covering evaluations of <i>Degree program</i> and <i>University experience</i>. By connecting latent satisfaction scores with thematically guided topics, the proposed framework reveals how themes and language use vary across satisfaction levels, offering a richer and more actionable understanding of quality and student experience to support targeted improvement strategies in higher education.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Semi-supervised evaluation of University quality: from structured measures to student voices

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月31日

查看全文
  • Annalina Sarra,
  • Alex Cucco,
  • Lara Fontanella,
  • Tonio Di Battista,
  • Adelia Evangelista

摘要

Understanding student satisfaction in higher education requires more than standardized survey scores alone. While structured survey responses provide standardized and comparable measures of satisfaction, they often fail to capture the heterogeneity of students’ experiences. In contrast, unstructured textual feedback offers a more in-depth understanding but is less easily quantifiable. A data-driven approach to quality evaluation that combines both structured and unstructured data offers a more comprehensive perspective. To combine these perspectives, we investigate both Structural Equation Modeling (SEM) of structured questionnaire data and topic modeling of open-ended responses. Two complementary approaches are adopted: the Structural Topic Model (STM), used to explore lexical and thematic differences between positive aspects and areas for improvement, and the semi-supervised SeededLDA, employed to identify topics guided by the vocabulary characteristic of student groups defined by their latent satisfaction levels. The analysis draws on responses from over 5000 students at an Italian University, covering evaluations of Degree program and University experience. By connecting latent satisfaction scores with thematically guided topics, the proposed framework reveals how themes and language use vary across satisfaction levels, offering a richer and more actionable understanding of quality and student experience to support targeted improvement strategies in higher education.