Nowadays, machine-based conversational systems known as chatbots have emerged for many applications in our lives Chatbots are intelligent tools that use the concept of Artificial Intelligence (AI) in order to communicate with humans using their natural languages The inherent role of chatbots is to understand users’ questions and provide the most appropriate responses intelligently and naturally Chatbots have been very successful in some of the most spoken languages;however, Arabic chatbots have not reached the expected level Recently, many researchers have attempted to fill the gap in implementing Arabic chatbots trying to overcome the complex linguistic features of Arabic language Although Arabic chatbots can be utilized as a supportive tool for Saudi university students, their implementation, especially in Arabic language, is surprisingly neglected Moreover, during changing the mode of education into distance learning due to (COVID-19) pandemic, it did not help the emergence of Arabic chatbots in Saudi universities This research focuses on language-related challenges and obstacles that hinder the implementation of Arabic chatbots Additionally, this paper presents fundamental recommendations for implementing effective Arabic chatbots for academic uses In summary, it is noticed that Arabic chatbots literature suffers from paucity, which means further studies are needed in this area © 2021, IAENG International Journal of Computer Science All Rights Reserved
The ongoing novel coronavirus disease (COVID-19) pandemic has ravaged human society and inflicted serious damage The transmission history of COVID-19 demonstrates how infectious diseases can become global threats if they are not contained Efficient response policies are required to contain these outbreaks However, it is challenging to rapidly formulate and promulgate suitable response policies in various countries that experience outbreaks, given that the experience of controlling epidemics of highly contagious diseases is limited This paper proposes a modified SEIR model that can simulate COVID-19 outbreaks by accounting for the capacity of the local healthcare system and possible intervention techniques to support decision-making during such outbreaks Our paper provides answers to the following three questions: "What feasible intervention methods may serve to control outbreaks?", "To what extent can these methods reduce the damage caused by outbreaks?" and "What are the ideal intervention methods under various circumstances?" © 2021, IAENG International Journal of Computer Science All Rigths Reserved
Nowadays, the world suffers a Coronavirus mutation in 2019 (COVID-19) The COVID-19 data sources possess three main characteristics: big volume, velocity, and variety These challenges have compelled the authors to employ Big Data technology, data mining techniques, and Ontology-based approaches instead of using a statistics hypothesis Big Data Frameworks are involved in most data-related activities, such as storing, processing, analyzing, and sharing Nevertheless, most of them miss having a semantic layer that is required for meaning-related activities, such as decision support, reasoning, and event detection A semantic layer is based on Ontology, Semantic Query Engine, Association Rule Mining, and Fuzzy Logic Therefore, this research aims to build Ontology and transform Big Data from Big Data Frameworks to semantic environments This paper presents Onto-NoSQL, a Protégé plug-in that supports the creation of Ontology and transformation of a column-oriented NoSQL datastore like Hbase into Protégé Besides, the whole process of transformation is carried out automatically without any external intervention It demonstrates the proposed plug-in through a case study of air pollution and weather phenomena’s data The proposed plug-in is utilized to predict COVID-19 prevalence and the relationship between COVID-19 prevalence and weather factors Moreover, the plug-in handles many challenges due to Big Data size and time processing The time consumption to import up to 64 GB data is 17 minutes The data prediction accuracy is 96 9% applying association rules discovery on Ontology creation © 2020 All Rights Reserved
