Citation
Computational Dialogue Analysis and Visualizations to Empower Children to Reflect on Their Collaborative Dialogue

Material Information

Title:
Computational Dialogue Analysis and Visualizations to Empower Children to Reflect on Their Collaborative Dialogue
Creator:
Celepkolu, Mehmet
Place of Publication:
[Gainesville, Fla.]
Florida
Publisher:
University of Florida
Publication Date:
Language:
english
Physical Description:
1 online resource (145 p.)

Thesis/Dissertation Information

Degree:
Doctorate ( Ph.D.)
Degree Grantor:
University of Florida
Degree Disciplines:
Computer Science
Computer and Information Science and Engineering
Committee Chair:
Boyer,Kristy
Committee Co-Chair:
Huang,Kejun
Committee Members:
Chuyew Yee,Sharon Lynn
Israel,Maya
Graduation Date:
8/8/2020

Subjects

Subjects / Keywords:
cs-education -- data-visualization -- dialogue-analysis -- nlp
Computer and Information Science and Engineering -- Dissertations, Academic -- UF
Genre:
bibliography ( marcgt )
theses ( marcgt )
government publication (state, provincial, terriorial, dependent) ( marcgt )
born-digital ( sobekcm )
Electronic Thesis or Dissertation
Computer Science thesis, Ph.D.

Notes

Abstract:
Collaborative learning is an essential part of young learners' development, positively impacting academic achievement and fostering higher levels of reasoning. However, young learners often face challenges when taking turns in conversation, openly listening to ideas, and respecting different viewpoints. One way to foster collaborative skills may be to learners' awareness of their own collaborative dialogue. Previous research investigated how providing (or mirroring) knowledge-related group awareness information on how the collaboration is going can help learners to observe, regulate, and adjust their collaborative behaviors. Several studies have suggested using visual analytics that mine dialogue and visualize metadata shown to the group members to increase students' awareness of their participation in collaborative problem solving. While visualization systems have shown promise in supporting collaborative learning with respect to encouraging more equitable participation, previous research often overlooked three important points: First, most studies have overlooked the importance of involving children in the development process, designing visualization applications for educators or adults rather than children. Second, existing applications often display only summative visualizations of the total number of contributions within a dialogue, disregarding temporal dynamics that are key facets of the unfolding dialogue process over time. Third, existing applications do not provide users with information about the content of the dialogue, instead presenting only information about word counts or turn taking. In this dissertation research, I iteratively refined and investigated a dialogue visualization application that addresses all three of the above shortcomings. I conducted studies with 56 middle school children, explored how they interacted with the dialogue visualizations, and examined their relationship with children's future collaborative dialogue. The qualitative results showed that most children had positive feelings toward the visualizations, interpreted them as intended, perceived them as useful, and even reported benefits in their subsequent collaborations after having viewed the visualizations. The quantitative results showed that less-engaged students talked more and asked more questions after seeing the dialogue visualizations. Moreover, dialogue visualizations fostered more balanced dialogues between pairs. Overall, this research provides evidence that young learners are able to deeply reason about the data being provided, reflect on their collaborative dialogue and improve their behaviors based on the needs of the team. ( en )
General Note:
In the series University of Florida Digital Collections.
General Note:
Includes vita.
Bibliography:
Includes bibliographical references.
Source of Description:
Description based on online resource; title from PDF title page.
Source of Description:
This bibliographic record is available under the Creative Commons CC0 public domain dedication. The University of Florida Libraries, as creator of this bibliographic record, has waived all rights to it worldwide under copyright law, including all related and neighboring rights, to the extent allowed by law.
Thesis:
Thesis (Ph.D.)--University of Florida, 2020.
Local:
Adviser: Boyer,Kristy.
Local:
Co-adviser: Huang,Kejun.
Statement of Responsibility:
by Mehmet Celepkolu.

Record Information

Source Institution:
UFRGP
Rights Management:
Applicable rights reserved.
Classification:
LD1780 2020 ( lcc )

Downloads

This item has the following downloads:


Full Text

PAGE 30

n N

PAGE 33

nn

PAGE 34

n

PAGE 36

n

PAGE 93

n

PAGE 103

jj

PAGE 104

jj

PAGE 108

<

PAGE 110

===

PAGE 125

2 2 2 2 2 2 2

PAGE 126

2 2 2 2 2 2