The application of Artificial Intelligence technology has demonstrated significant potential in various fields, including Arabic language education. Despite the growing popularity of AI chatbots, studies on the accuracy of the content they provide remain limited. This research aims to assess the accuracy of the interpretation of Arabic syntactic rules (naḥwu), particularly the chapter on maf’ūl bih, as presented by Chatsonic, and to compare it with the explanation in the book Jāmi’ ad-Durus al-Arabiyyah by Muṣṭafā al-Galāyainī. This qualitative research employs a descriptive approach. Data collection was conducted through literature review, and data analysis followed the qualitative content analysis procedure as outlined by Klaus Krippendorff. The findings indicate that some theories regarding maf’ūl bih presented by Chatsonic align with Jāmi’ ad-Durus al-Arabiyyah, particularly in terms of definition, examples of maf’ūl bih in sentences, and certain general rules regarding the prioritization (taqdīm) and delay (ta’khīr) of maf’ūl bih. However, on more complex rules, such as the legal judgments concerning maf’ūl bih, its classifications, and the omission of maf’ūl bih from verbs of perception (af’ālul qulūb), inaccuracies were found. Additionally, discrepancies were identified in several aspects of taqdīm and ta’khīr, including a contradictory statement about the obligatory precedence of the subject (fā’il) over maf’ūl bih. These findings are expected to provide deeper insights into the effectiveness and accuracy of Chatsonic in Arabic syntactic rules, particularly in understanding the concept of maf’ūl bih.
Copyrights © 2024