English and Arabic Chatbots: A Systematic Literature Review

Abstract

In recent years, the availability of chatbot applications has increased substantially with the advancement of artificial intelligence techniques, and research efforts have been active in the English language, which presents state-of-the-art solutions. However, despite the popularity of the Arabic language, its research community is still in an immature stage. Therefore, the main objective of this systematic literature review is studying state-of-the-art researchfor both the English and Arabic languagesto answer the proposed research questions regarding the development approaches, application domains, evaluation metrics, and development challenges of chatbot applications. The findings show that researchers have devoted more attention to the education domain using retrieval-based approaches while the generation-based approach has grown in popularity recently for providing new responses tasks. Whereas the hybrid approach for ranking multi-possible responses of combining both previous approaches shows a performance improvement. Besides, most metrics used to evaluate chatbot performance are human-based, followed by bilingual evaluation understudy and accuracy metrics. However, defining a common framework for evaluating chatbots remains a challenge. Finally, the open problems and future directions are highlighted to help in developing chatbots with minimal human interference to simulate natural conversations.

Conversational agents: a survey on culturally informed design practices

“…• (1) Design practices in different contexts; • (2) Additional resources to support designers; • (3) Avoid bias with and during design practices; Regarding Design practices in different contexts (1), literature tends to focus on a common context when addressing a topic, as seen in Alsheddi and Alhenaki (2022). Our results have demonstrated a significant interest in discussing cultural design practices in the health domain.…”

“…Therefore, increasing cultural differences in humor can promote student engagement in learning and understanding. Studies also present frame understanding of specific scenarios, for example, Alsheddi and Alhenaki (2022) present an SLR for English and Arabic chatbots and Wołk et al (2022) describe a survey of dialogue systems within Slavic languages. The most advanced chatbots in the niche cultural heritage field are presented by Machidon et al (2018).…”

“…In that case, methods to support the evaluation of the content generated are needed, not just the resulting goals (e.g., persuasion, habits change). However, no universal framework exists to evaluate chatbots (Alsheddi and Alhenaki, 2022), especially considering cultural design practices. It is ethically appropriate to acknowledge the power of designers in making decisions concerning other cultures.…”

An inquiry smart chatbot system for Al-Zaytoonah University of Jordan

“…The reviewed papers suggest that retrieval-based models are used in all models proposed for Arabic chatbot applications [33]- [35]. In other words, a data pool created by pattern-matching techniques serves as the foundation for chatbot answers.…”

“…In other words, a data pool created by pattern-matching techniques serves as the foundation for chatbot answers. The user's input must match the chatbot dataset for the user to obtain the right answer, which may result in limited user response, a restricted chatbot dataset, and a restriction to closed domains [33]- [35].…”