Text

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

---

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”.

---

Availability

No copy data

Detail Information

Series Title

-

Call Number

-

Publisher

Florence : Firenze University Press, Genova University Press., 2023

Collation

-

Language

English

ISBN/ISSN

9791221501063

Classification

NONE

Content Type

text

Media Type

computer

Carrier Type

online resource

Edition

-

Subject(s)

Student feedback
digital learning ecosystem
open-ended questions
pandemic context
structural topic models

Specific Detail Info

-

Statement of Responsibility

-

Other Information

Cataloger

Candra

Source

-

Validator

-

Digital Object Identifier (DOI)

https://doi.org/10.36253/979-12-215-0106-3.36

Journal Volume

-

Journal Issue

-

Subtitle

-

Parallel Title

-

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment