Abstract
The Enhanced ArabChat is a complement of the previous version of ArabChat. This paper details an enhancements development of a novel and practical Conversational Agent for the Arabic language called the “Enhanced ArabChat”. A conversational Agent is a computer program that attempts to simulate conversations between machine and human. Some of lessons was learned by evaluating the previous work of ArabChat . These lessons revealed that two major issues affected the ArabChat’s performance negatively. Firstly, the need for a technique to distinguish between question and non-question utterances to reply with a more suitable response depending on the utterance’s type (question and non-question based utterances). Secondly, the need for a technique to handle an utterance targeting many topics that require firing many rules at the same time. Therefore, in this paper, the “Enhanced ArabChat” will cover these enhancements to improve the ArabChat’s performance. A real experiment has been done in Applied Science University in Jordan as an information point advisor for their native Arabic students to evaluate the Enhanced ArabChat.
Highlights
From Turing test time[1], which he was tried to solve his test by answering his question ―if a computer could think, how could we tell?‖, number of researches tries to solve his test by developing a conversational agent
The Enhanced ArabChat usability evaluation: the Enhanced ArabChat usability was evaluated through 3 items in the questionnaire which are 4, 7, and 8. 96.2% of users agreed that they experienced no technical problems while using the Enhanced ArabChat. 79.2% of users agreed that difficulty contacting the university by phone or email, as well as difficulty accessing their needed information on the university website were the reasons that caused them to use the Enhanced ArabChat
Experiment Results The results show that the average of RMUT for the 17 users is 72.12%
Summary
From Turing test (imitation game) time[1], which he was tried to solve his test by answering his question ―if a computer could think, how could we tell?‖, number of researches tries to solve his test by developing a conversational agent. Number of CAs types has been raised due to the diversity of applications that‘s could CAs applied in. This is including Embodied CA, Linguistic CA and mixed approach between them [3]. Linguistic CAs deals with spoken or/and written conversations without to embed the embodied abilities. The mixed approach which can share the features of both types [3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
