id |
oapen-20.500.12657-74908
|
record_format |
dspace
|
spelling |
oapen-20.500.12657-749082023-08-03T17:59:38Z Chapter Students’ feedback on the digital ecosystem: a structural topic modeling approach Evangelista, Adelia Sarra, Annalina Di Battista, Tonio Student feedback digital learning ecosystem open-ended questions pandemic context structural topic models bic Book Industry Communication::J Society & social sciences 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”. 2023-08-03T15:06:24Z 2023-08-03T15:06:24Z 2023 chapter ONIX_20230803_9791221501063_104 2704-5846 9791221501063 https://library.oapen.org/handle/20.500.12657/74908 eng Proceedings e report application/pdf Attribution 4.0 International 9791221501063-36.pdf https://books.fupress.com/doi/capitoli/979-12-215-0106-3_36 Firenze University Press, Genova University Press ASA 2022 Data-Driven Decision Making 10.36253/979-12-215-0106-3.36 10.36253/979-12-215-0106-3.36 9223d3ac-6fd2-44c9-bb99-5b98ca9d2fad 863aa499-dbee-4191-9a14-3b5d5ef9e635 9791221501063 134 6 Florence open access
|
institution |
OAPEN
|
collection |
DSpace
|
language |
English
|
description |
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”.
|
title |
9791221501063-36.pdf
|
spellingShingle |
9791221501063-36.pdf
|
title_short |
9791221501063-36.pdf
|
title_full |
9791221501063-36.pdf
|
title_fullStr |
9791221501063-36.pdf
|
title_full_unstemmed |
9791221501063-36.pdf
|
title_sort |
9791221501063-36.pdf
|
publisher |
Firenze University Press, Genova University Press
|
publishDate |
2023
|
url |
https://books.fupress.com/doi/capitoli/979-12-215-0106-3_36
|
_version_ |
1799945196248498176
|