TOWARDS EFFECTIVE ARGUMENTATION: DESIGN AND IMPLEMENTATION OF A GENERATIVE AI-BASED EVALUATION AND FEEDBACK SYSTEM

Hunkoog Jho; Minsu Ha

Error message

Strict warning: Declaration of csl_names::render() should be compatible with csl_rendering_element::render($data, $mode = NULL) in module_load_include() (line 330 of /home/scientia/domains/scientiasocialis.lt/public_html/jbse/includes/module.inc).

Strict warning: Declaration of csl_date::render() should be compatible with csl_rendering_element::render($data, $mode = NULL) in module_load_include() (line 330 of /home/scientia/domains/scientiasocialis.lt/public_html/jbse/includes/module.inc).

Strict warning: Declaration of csl_date_part::render() should be compatible with csl_rendering_element::render($data, $mode = NULL) in module_load_include() (line 330 of /home/scientia/domains/scientiasocialis.lt/public_html/jbse/includes/module.inc).

Strict warning: Declaration of csl_number::render() should be compatible with csl_rendering_element::render($data, $mode = NULL) in module_load_include() (line 330 of /home/scientia/domains/scientiasocialis.lt/public_html/jbse/includes/module.inc).

Strict warning: Declaration of csl_group::render() should be compatible with csl_rendering_element::render($data, $mode = NULL) in module_load_include() (line 330 of /home/scientia/domains/scientiasocialis.lt/public_html/jbse/includes/module.inc).

Strict warning: Declaration of csl_layout::render() should be compatible with csl_rendering_element::render($data, $mode = NULL) in module_load_include() (line 330 of /home/scientia/domains/scientiasocialis.lt/public_html/jbse/includes/module.inc).

Strict warning: Only variables should be passed by reference in theme_biblio_tabular() (line 276 of /home/scientia/domains/scientiasocialis.lt/public_html/jbse/modules/biblio/includes/biblio_theme.inc).

TOWARDS EFFECTIVE ARGUMENTATION: DESIGN AND IMPLEMENTATION OF A GENERATIVE AI-BASED EVALUATION AND FEEDBACK SYSTEM

Title	TOWARDS EFFECTIVE ARGUMENTATION: DESIGN AND IMPLEMENTATION OF A GENERATIVE AI-BASED EVALUATION AND FEEDBACK SYSTEM
Publication Type	Journal Article
Year of Publication	2024
Authors	Jho, H, Ha, M
Journal	Journal of Baltic Science Education
Volume	23
Issue	2
Start Page	280-291
Pagination	Continuous
Date Published	April/2024
Type of Article	Original article
ISSN	1648-3898
Other Numbers	E-2538-7138
Keywords	argumentative writing, Artificial Intelligence, automated assessment, natural language processing, web architecture
Abstract	This study aimed at examining the performance of generative artificial intelligence to extract argumentation elements from text. Thus, the researchers developed a web-based framework to provide automated assessment and feedback relying on a large language model, ChatGPT. The results produced by ChatGPT were compared to human experts across scientific and non-scientific contexts. The findings revealed marked discrepancies in the performance of AI for extracting argument components, with a significant variance between issues of a scientific nature and those that are not. Higher accuracy was noted in identifying claims, data, and qualifiers, as opposed to rebuttals, backing, and warrants. The study illuminated AI's promise for educational applications but also its shortcomings, such as the increased frequency of erroneous element identification when accuracy was low. This highlights the essential need for more in-depth comparative research on models and the further development of AI to enhance its role in supporting argumentation training.
URL	https://oaji.net/articles/2023/987-1713273011.pdf
DOI	10.33225/jbse/24.23.280
Refereed Designation	Refereed
Full Text