東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Automated Detection of Disruptive Talk in Collaborative Game-Based Learning Environments.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Automated Detection of Disruptive Talk in Collaborative Game-Based Learning Environments./
作者:	Park, Kyungjin.
面頁冊數:	1 online resource (101 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-04, Section: B.
Contained By:	Dissertations Abstracts International84-04B.
標題:	Student organizations. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29420048click for full text (PQDT)
ISBN:	9798352654712

Automated Detection of Disruptive Talk in Collaborative Game-Based Learning Environments.
Park, Kyungjin.

Automated Detection of Disruptive Talk in Collaborative Game-Based Learning Environments. - 1 online resource (101 pages)

Source: Dissertations Abstracts International, Volume: 84-04, Section: B.

Thesis (Ph.D.)--North Carolina State University, 2022.

Includes bibliographical references

Collaborative game-based learning environments show significant promise for creating engaging group learning experiences. Online chat plays a pivotal role in these environments by providing students with a means to communicate freely during problem solving. These chat-based discussions and negotiations support the coordination of students' in-game learning activities. However, this freedom of expression comes with the possibility that some students might engage in undesirable communicative behaviors.A key challenge posed by collaborative game-based learning environments is determining how to manage disruptive talk that purposefully disrupts team dynamics and problem-solving interactions. Disruptive talk during collaborative game-based learning is particularly damaging because, if allowed to persist, it can generate frustration and significantly impede the learning process for students. However, due to the complexities of group communication, reliably detecting disruptive talk presents a significant computational challenge. Since users can be involved in multiple concurrent conversation threads of different topics, it is critical to examine the characteristics of group conversation dynamics based on the purpose of a conversation and target user group.This dissertation introduces a deep learning-based framework for detecting disruptive talk in a collaborative game-based learning environment for middle school science education, investigates how disruptive talk behaviors influence students' learning outcomes, and explores how these behaviors vary across students' gender and students' prior knowledge. The framework automatically identifies disruptive talk during the collaborative learning process. To accomplish this, the framework utilizes linguistic features from text-based group conversation, individual and group-level features from game interactions, and attributes consisting of gender and prior knowledge.The preliminary research presented an empirical evaluation has demonstrated that long short-term memory and gated recurrent unit-based disruptive talk detection models utilizing linguistic features from text-based group conversation and student attribute features outperform competitive baseline models. Results indicate that these deep sequential modeling approaches offer significant potential for supporting effective collaborative game-based learning through the identification of disruptive talk.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798352654712Subjects--Topical Terms:

3682086
Student organizations.
Index Terms--Genre/Form:

542853
Electronic books.

Automated Detection of Disruptive Talk in Collaborative Game-Based Learning Environments.
LDR:03710nmm a2200337K 4500 001 2361734
005 20231027101310.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798352654712
035 $a (MiAaPQ)AAI29420048
035 $a (MiAaPQ)NCState_Univ18402039883
035 $a AAI29420048
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Park, Kyungjin. $3 3702419
245 1 0 $a Automated Detection of Disruptive Talk in Collaborative Game-Based Learning Environments.
264 0 $c 2022
300 $a 1 online resource (101 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-04, Section: B.
500 $a Advisor: Lester, James;Mott, Bradford.
502 $a Thesis (Ph.D.)--North Carolina State University, 2022.
504 $a Includes bibliographical references
520 $a Collaborative game-based learning environments show significant promise for creating engaging group learning experiences. Online chat plays a pivotal role in these environments by providing students with a means to communicate freely during problem solving. These chat-based discussions and negotiations support the coordination of students' in-game learning activities. However, this freedom of expression comes with the possibility that some students might engage in undesirable communicative behaviors.A key challenge posed by collaborative game-based learning environments is determining how to manage disruptive talk that purposefully disrupts team dynamics and problem-solving interactions. Disruptive talk during collaborative game-based learning is particularly damaging because, if allowed to persist, it can generate frustration and significantly impede the learning process for students. However, due to the complexities of group communication, reliably detecting disruptive talk presents a significant computational challenge. Since users can be involved in multiple concurrent conversation threads of different topics, it is critical to examine the characteristics of group conversation dynamics based on the purpose of a conversation and target user group.This dissertation introduces a deep learning-based framework for detecting disruptive talk in a collaborative game-based learning environment for middle school science education, investigates how disruptive talk behaviors influence students' learning outcomes, and explores how these behaviors vary across students' gender and students' prior knowledge. The framework automatically identifies disruptive talk during the collaborative learning process. To accomplish this, the framework utilizes linguistic features from text-based group conversation, individual and group-level features from game interactions, and attributes consisting of gender and prior knowledge.The preliminary research presented an empirical evaluation has demonstrated that long short-term memory and gated recurrent unit-based disruptive talk detection models utilizing linguistic features from text-based group conversation and student attribute features outperform competitive baseline models. Results indicate that these deep sequential modeling approaches offer significant potential for supporting effective collaborative game-based learning through the identification of disruptive talk.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Student organizations. $3 3682086
650 4 $a Neural networks. $3 677449
650 4 $a Support vector machines. $3 2058743
650 4 $a Computer science. $3 523869
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a North Carolina State University. $3 1018772
773 0 $t Dissertations Abstracts International $g 84-04B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29420048 $z click for full text (PQDT)