Applications of deep language models for reflective writings

J 2023

Applications of deep language models for reflective writings

NEHYBA, Jan and Michal ŠTEFÁNIK

Basic information

Original name

Applications of deep language models for reflective writings

Authors

NEHYBA, Jan (203 Czech Republic, guarantor, belonging to the institution) and Michal ŠTEFÁNIK (703 Slovakia, belonging to the institution)

Edition

Education and Information Technologies, UNITED STATES, SPRINGER, 2023, 1360-2357

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

50301 Education, general; including training, pedagogy, didactics [and education systems]

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 5.500 in 2022

RIV identification code

RIV/00216224:14330/23:00129992

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1007/s10639-022-11254-7

UT WoS

000849683800001

Keywords in English

Deep learning; Natural language processing; Reflection dataset; Reflection classification; Analyses of reflective journals; Generalized linear mixed models

Abstract

V originále

Social sciences expose many cognitively complex, highly qualified, or fuzzy problems, whose resolution relies primarily on expert judgement rather than automated systems. One of such instances that we study in this work is a reflection analysis in the writings of student teachers. We share a hands-on experience on how these challenges can be successfully tackled in data collection for machine learning. Based on the novel deep learning architectures pre-trained for a general language understanding, we can reach an accuracy ranging from 76.56–79.37% on low-confidence samples to 97.56–100% on high confidence cases. We open-source all our resources and models, and use the models to analyse previously ungrounded hypotheses on reflection of university students. Our work provides a toolset for objective measurements of reflection in higher education writings, applicable in more than 100 other languages worldwide with a loss in accuracy measured between 0–4.2% Thanks to the outstanding accuracy of the deep models, the presented toolset allows for previously unavailable applications, such as providing semi-automated student feedback or measuring an effect of systematic changes in the educational process via the students’ response.

Links

MUNI/A/1339/2022, interní kód MU

Name: Rozvoj technik pro zpracování dat pro podporu vyhledávání, analýz a vizualizací rozsáhlých datových souborů s využitím umělé inteligence

Investor: Masaryk University, Development of data processing techniques to support search, analysis and visualization of large datasets using artificial intelligence

Citovat

NEHYBA, Jan and Michal ŠTEFÁNIK. Applications of deep language models for reflective writings. Education and Information Technologies. UNITED STATES: SPRINGER, 2023, vol. 28, No 3, p. 2961-2999. ISSN 1360-2357. Available from: https://dx.doi.org/10.1007/s10639-022-11254-7.

@article{1876027,
   author = {Nehyba, Jan and Štefánik, Michal},
   article_location = {UNITED STATES},
   article_number = {3},
   doi = {http://dx.doi.org/10.1007/s10639-022-11254-7},
   keywords = {Deep learning; Natural language processing; Reflection dataset; Reflection classification; Analyses of reflective journals; Generalized linear mixed models},
   language = {eng},
   issn = {1360-2357},
   journal = {Education and Information Technologies},
   title = {Applications of deep language models for reflective writings},
   url = {https://link.springer.com/article/10.1007/s10639-022-11254-7},
   volume = {28},
   year = {2023}
}

TY  - JOUR
ID  - 1876027
AU  - Nehyba, Jan - Štefánik, Michal
PY  - 2023
TI  - Applications of deep language models for reflective writings
JF  - Education and Information Technologies
VL  - 28
IS  - 3
SP  - 2961-2999
EP  - 2961-2999
PB  - SPRINGER
SN  - 13602357
KW  - Deep learning
KW  - Natural language processing
KW  - Reflection dataset
KW  - Reflection classification
KW  - Analyses of reflective journals
KW  - Generalized linear mixed models
UR  - https://link.springer.com/article/10.1007/s10639-022-11254-7
N2  - Social sciences expose many cognitively complex, highly qualified, or fuzzy problems, whose resolution relies primarily on expert judgement rather than automated systems. One of such instances that we study in this work is a reflection analysis in the writings of student teachers. We share a hands-on experience on how these challenges can be successfully tackled in data collection for machine learning. Based on the novel deep learning architectures pre-trained for a general language understanding, we can reach an accuracy ranging from 76.56–79.37% on low-confidence samples to 97.56–100% on high confidence cases. We open-source all our resources and models, and use the models to analyse previously ungrounded hypotheses on reflection of university students. Our work provides a toolset for objective measurements of reflection in higher education writings, applicable in more than 100 other languages worldwide with a loss in accuracy measured between 0–4.2% Thanks to the outstanding accuracy of the deep models, the presented toolset allows for previously unavailable applications, such as providing semi-automated student feedback or measuring an effect of systematic changes in the educational process via the students’ response.
ER  -

NEHYBA, Jan and Michal ŠTEFÁNIK. Applications of deep language models for reflective writings. \textit{Education and Information Technologies}. UNITED STATES: SPRINGER, 2023, vol.~28, No~3, p.~2961-2999. ISSN~1360-2357. Available from: https://dx.doi.org/10.1007/s10639-022-11254-7.

Detailed Information on Publication Record