Chapter Students' feedback on the digital ecosystem: a structural topic modeling approach

• 第一著者: Evangelista, Adelia (auth)
• その他の著者: Sarra, Annalina (auth), Di Battista, Tonio (auth)
• フォーマット: 電子媒体 図書の章
• 言語: 英語
• 出版事項: Florence Firenze University Press, Genova University Press 2023
• シリーズ: Proceedings e report 134
• 主題: Society & social sciences; Student feedback; digital learning ecosystem; open-ended questions; pandemic context; structural topic models
• オンライン･アクセス: OAPEN Library: download the publication; OAPEN Library: description of the publication

要約

Starting from March 2020, strict containment measures against COVID-19 forced the Italian Universities to activate remote learning and supply didactic methods online. This work is aimed at showing students' perceptions towards a learning-teaching experience practised within a digital learning ecosystem designed in the period of first emergency and then re-proposed for the blended mode. Specifically, students, attending six teaching large courses held by four professors in two different Italian universities, were asked to express their impression in a text guided by questions, requiring the reflections and clarification of their and inner deep thoughts on the ecosystem. To automate the analysis of the resulting open-ended responses and avoid a labour-intensive human coding, we focused on a machine learning approach based on structural topic modelling (STM). Alike to Latent Dirichlet Allocation model (LDA), STM is a probabilistic generative model that defines a document generated as a mixture of hidden topics. In addition, STM extends the LDA framework by allowing covariates of interest to be included in the prior distributions for open-ended-response topic proportions and topic word distributions. Based on model diagnostics and researchers' expertise, a 10-topic model is best fitted the data. Prevalent topics described by respondents include: "Physical space", "Bulding the community: use of Whatsapp", "Communication and tools", "Interaction with Teacher", "Feedback".

物理的記述

1 electronic resource (6 p.)

ISBN

979-12-215-0106-3.36
9791221501063

アクセス

Open Access