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 e...

Full description

Bibliographic Details
Format: eBook
Language:English
Published: Florence Firenze University Press, Genova University Press 2023
Series:Proceedings e report
Subjects:
Online Access:Open Access: DOAB: description of the publication
Open Access: DOAB, download the publication
LEADER 03256namaa2200469uu 4500
001 doab111711
003 oapen
005 20230805
006 m o d
007 cr|mn|---annan
008 230805s2023 xx |||||o ||| 0|eng d
020 |a 979-12-215-0106-3.36 
020 |a 9791221501063 
024 7 |a 10.36253/979-12-215-0106-3.36  |2 doi 
040 |a oapen  |c oapen 
041 0 |a eng 
042 |a dc 
072 7 |a J  |2 bicssc 
720 1 |a Evangelista, Adelia  |4 aut 
720 1 |a Di Battista, Tonio  |4 aut 
720 1 |a Sarra, Annalina  |4 aut 
245 0 0 |a Chapter Students' feedback on the digital ecosystem: a structural topic modeling approach 
260 |a Florence  |b Firenze University Press, Genova University Press  |c 2023 
300 |a 1 online resource (6 p.) 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
490 1 |a Proceedings e report 
506 0 |a Open Access  |f Unrestricted online access  |2 star 
520 |a 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". 
540 |a Creative Commons  |f https://creativecommons.org/licenses/by/4.0/  |2 cc  |u https://creativecommons.org/licenses/by/4.0/ 
546 |a English 
650 7 |a Society & social sciences  |2 bicssc 
653 |a digital learning ecosystem 
653 |a open-ended questions 
653 |a pandemic context 
653 |a structural topic models 
653 |a Student feedback 
773 1 |7 nnaa  |o OAPEN Library UUID: ASA 2022 Data-Driven Decision Making 
793 0 |a DOAB Library. 
856 4 0 |u https://directory.doabooks.org/handle/20.500.12854/111711  |7 0  |z Open Access: DOAB: description of the publication 
856 4 0 |u https://library.oapen.org/bitstream/20.500.12657/74908/1/9791221501063-36.pdf  |7 0  |z Open Access: DOAB, download the publication