Comprehensive analysis of discussion forum participation

from speech acts to discussion dynamics and course outcomes

Srecko Joksimovic, Jelena Jovanovic, Vitomir Kovanović, Dragan Gašević, Nikola Milikić, Amal Zouaq, Jan Paul Van Staalduinen

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Learning in digitally connected, computer-mediated settings represents a complex, multidimensional process. This complexity calls for a comprehensive analytical approach that would allow for understanding of various dimensions of learner generated discourse and the structure of the underlying social interactions. Current research, however, primarily focuses on manual or, more recently, supervised methods for discourse analysis. Moreover, discourse and social structures are typically analyzed separately without the use of computational methods that can offer a holistic perspective. This paper proposes an approach that addresses these two challenges i) by using an unsupervised machine learning approach to extract speech acts as representations of knowledge construction processes and finds transition probabilities between speech acts across different messages; and ii) by integrating the use of discovered speech acts to explain the formation of social ties and predicting course outcomes. We extracted six categories of speech acts from messages exchanged in discussion forums of two MOOCs and each category corresponded to knowledge construction processes from well-established theoretical models. We further showed how measures derived from discourse analysis explained the ways how social ties were created that framed emerging social networks. Multiple regression models showed that the combined use of measures derived from discourse analysis and social ties predicted learning outcomes.
Original languageEnglish
Number of pages14
JournalIEEE Transactions on Learning Technologies
DOIs
Publication statusPublished - 14 May 2019

Keywords

  • learning analytics
  • online discussions
  • massive open online course
  • speech act
  • computational lingustics
  • Social network analysis

Cite this

Joksimovic, Srecko ; Jovanovic, Jelena ; Kovanović, Vitomir ; Gašević, Dragan ; Milikić, Nikola ; Zouaq, Amal ; Van Staalduinen, Jan Paul. / Comprehensive analysis of discussion forum participation : from speech acts to discussion dynamics and course outcomes. In: IEEE Transactions on Learning Technologies. 2019.
@article{3c91aefade554d74a54112ed86033deb,
title = "Comprehensive analysis of discussion forum participation: from speech acts to discussion dynamics and course outcomes",
abstract = "Learning in digitally connected, computer-mediated settings represents a complex, multidimensional process. This complexity calls for a comprehensive analytical approach that would allow for understanding of various dimensions of learner generated discourse and the structure of the underlying social interactions. Current research, however, primarily focuses on manual or, more recently, supervised methods for discourse analysis. Moreover, discourse and social structures are typically analyzed separately without the use of computational methods that can offer a holistic perspective. This paper proposes an approach that addresses these two challenges i) by using an unsupervised machine learning approach to extract speech acts as representations of knowledge construction processes and finds transition probabilities between speech acts across different messages; and ii) by integrating the use of discovered speech acts to explain the formation of social ties and predicting course outcomes. We extracted six categories of speech acts from messages exchanged in discussion forums of two MOOCs and each category corresponded to knowledge construction processes from well-established theoretical models. We further showed how measures derived from discourse analysis explained the ways how social ties were created that framed emerging social networks. Multiple regression models showed that the combined use of measures derived from discourse analysis and social ties predicted learning outcomes.",
keywords = "learning analytics, online discussions, massive open online course, speech act, computational lingustics, Social network analysis",
author = "Srecko Joksimovic and Jelena Jovanovic and Vitomir Kovanović and Dragan Gašević and Nikola Milikić and Amal Zouaq and {Van Staalduinen}, {Jan Paul}",
year = "2019",
month = "5",
day = "14",
doi = "10.1109/TLT.2019.2916808",
language = "English",
journal = "IEEE Transactions on Learning Technologies",
issn = "1939-1382",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",

}

Comprehensive analysis of discussion forum participation : from speech acts to discussion dynamics and course outcomes. / Joksimovic, Srecko; Jovanovic, Jelena; Kovanović, Vitomir; Gašević, Dragan; Milikić, Nikola; Zouaq, Amal; Van Staalduinen, Jan Paul.

In: IEEE Transactions on Learning Technologies, 14.05.2019.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Comprehensive analysis of discussion forum participation

T2 - from speech acts to discussion dynamics and course outcomes

AU - Joksimovic, Srecko

AU - Jovanovic, Jelena

AU - Kovanović, Vitomir

AU - Gašević, Dragan

AU - Milikić, Nikola

AU - Zouaq, Amal

AU - Van Staalduinen, Jan Paul

PY - 2019/5/14

Y1 - 2019/5/14

N2 - Learning in digitally connected, computer-mediated settings represents a complex, multidimensional process. This complexity calls for a comprehensive analytical approach that would allow for understanding of various dimensions of learner generated discourse and the structure of the underlying social interactions. Current research, however, primarily focuses on manual or, more recently, supervised methods for discourse analysis. Moreover, discourse and social structures are typically analyzed separately without the use of computational methods that can offer a holistic perspective. This paper proposes an approach that addresses these two challenges i) by using an unsupervised machine learning approach to extract speech acts as representations of knowledge construction processes and finds transition probabilities between speech acts across different messages; and ii) by integrating the use of discovered speech acts to explain the formation of social ties and predicting course outcomes. We extracted six categories of speech acts from messages exchanged in discussion forums of two MOOCs and each category corresponded to knowledge construction processes from well-established theoretical models. We further showed how measures derived from discourse analysis explained the ways how social ties were created that framed emerging social networks. Multiple regression models showed that the combined use of measures derived from discourse analysis and social ties predicted learning outcomes.

AB - Learning in digitally connected, computer-mediated settings represents a complex, multidimensional process. This complexity calls for a comprehensive analytical approach that would allow for understanding of various dimensions of learner generated discourse and the structure of the underlying social interactions. Current research, however, primarily focuses on manual or, more recently, supervised methods for discourse analysis. Moreover, discourse and social structures are typically analyzed separately without the use of computational methods that can offer a holistic perspective. This paper proposes an approach that addresses these two challenges i) by using an unsupervised machine learning approach to extract speech acts as representations of knowledge construction processes and finds transition probabilities between speech acts across different messages; and ii) by integrating the use of discovered speech acts to explain the formation of social ties and predicting course outcomes. We extracted six categories of speech acts from messages exchanged in discussion forums of two MOOCs and each category corresponded to knowledge construction processes from well-established theoretical models. We further showed how measures derived from discourse analysis explained the ways how social ties were created that framed emerging social networks. Multiple regression models showed that the combined use of measures derived from discourse analysis and social ties predicted learning outcomes.

KW - learning analytics

KW - online discussions

KW - massive open online course

KW - speech act

KW - computational lingustics

KW - Social network analysis

U2 - 10.1109/TLT.2019.2916808

DO - 10.1109/TLT.2019.2916808

M3 - Article

JO - IEEE Transactions on Learning Technologies

JF - IEEE Transactions on Learning Technologies

SN - 1939-1382

ER -