版权说明 操作指南
首页 > 成果 > 详情

Prompt-based and Fine-tuned GPT Models for Context-Dependent and -Independent Deductive Coding in Social Annotation

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文、会议论文
作者:
Hou, Chenyu;Zhu, Gaoxia;Zheng, Juan;Zhang, Lishan;Huang, Xiaoshan;...
通讯作者:
Zhu, GX
作者机构:
[Hou, Chenyu; Zhong, Tianlong] Nanyang Technol Univ, Singapore, Singapore.
[Zhu, Gaoxia; Ker, Chin Lee] Nanyang Technol Univ, Natl Inst Educ, Singapore, Singapore.
[Li, Shan; Zheng, Juan] Lehigh Univ, Bethlehem, PA USA.
[Zhang, Lishan] Cent China Normal Univ, Wuhan, Peoples R China.
[Huang, Xiaoshan] McGill Univ, Montreal, PQ, Canada.
通讯机构:
[Zhu, GX ] N
Nanyang Technol Univ, Natl Inst Educ, Singapore, Singapore.
语种:
英文
关键词:
Context-Dependent;Fine-tuning;GPT;Prompt Engineering;Social Annotation;deductive coding
期刊:
FOURTEENTH INTERNATIONAL CONFERENCE ON LEARNING ANALYTICS & KNOWLEDGE, LAK 2024
年:
2024
页码:
518–528
会议名称:
14th Annual International Conference on Learning Analytics and Knowledge (LAK) - Learning Analytics in the Age of Artificial Intelligence
会议论文集名称:
LAK '24: Proceedings of the 14th Learning Analytics and Knowledge Conference
会议时间:
MAR 18-22, 2024
会议地点:
Kyoto, JAPAN
会议主办单位:
[Hou, Chenyu;Zhong, Tianlong] Nanyang Technol Univ, Singapore, Singapore.^[Zhu, Gaoxia;Ker, Chin Lee] Nanyang Technol Univ, Natl Inst Educ, Singapore, Singapore.^[Zheng, Juan;Li, Shan] Lehigh Univ, Bethlehem, PA USA.^[Zhang, Lishan] Cent China Normal Univ, Wuhan, Peoples R China.^[Huang, Xiaoshan] McGill Univ, Montreal, PQ, Canada.^[Du, Hanxiang] Western Washington Univ, Bellingham, WA USA.
出版地:
1601 Broadway, 10th Floor, NEW YORK, NY, UNITED STATES
出版者:
ASSOC COMPUTING MACHINERY
ISBN:
979-8-4007-1618-8
基金类别:
NTU Edex Teaching and Learning Grants [NTU EdeX 1/22 ZG]; National Natural Science Foundation of China [62377017]
机构署名:
本校为其他机构
摘要:
GPT has demonstrated impressive capabilities in executing various natural language processing (NLP) and reasoning tasks, showcasing its potential for deductive coding in social annotations. This research explored the effectiveness of prompt engineering and fine-tuning approaches of GPT for deductive coding of context-dependent and context-independent dimensions. Coding context-dependent dimensions (i.e., Theorizing, Integration, Reflection) requires a contextualized understanding that connects the target comment with reading materials and previous comments, whereas coding context-independent d...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com