Conversational AI is one of the most active research areas in AI, and it has gained more attention from academia as well as industry. Given recent advancements in several conversational AI systems in addition to the availability of several datasets, the aim of this study is to explore the landscape of Arabic text-based conversational AI systems. In this work, we provide a thorough review of recent Arabic conversational AI systems. We group them into three categories based on their functionality: (1) questionanswering (QA) systems, (2) task-oriented dialogue systems (DS), and (3) chatbots. Furthermore, we describe the common datasets used in building and evaluating conversational AI systems in Arabic. Few surveys have targeted the conversational AI field for the Arabic language, and we aim to cover this gap with this study. Our contribution focuses on reviewing and analyzing the literature in the field and highlighting future research directions towards human-like conversational AI systems in Arabic.

Mobile app stores provide an extremely rich source of information on app descriptions, characteristics, and usage, and analyzing these data provides insights and a deeper understanding of the nature of apps. However, manual analysis of this vast amount of information on mobile apps is not a simple and straightforward task; it is costly in terms of human effort and time. Computational methods such as topic modeling can provide an efficient and satisfactory approach to mobile app information analysis. Topic modeling is a type of statistical modeling technique for discovering abstract topics that occur in a set of documents. This study explores the relationship between features of Arabic apps and investigates how well the current predefined Google Play app categories represent the type and genre of Arabic mobile apps. Based on the textual app description analysis, we aim to design and develop a sustainable classification system using the Latent Dirichlet Allocation (LDA) method of topic modeling in order to cover the Arabic apps classification in Google Play app store. Our study supports the hypothesis that the textual app descriptions are effective in suggesting new categories for Arabic mobile apps in Google Play app store. Also, the results indicated that the current classification on Google Play app store is not suitable for our case study “Arabic apps,” as well as it is not sustainable, as it can not cover the new app types including Arabic apps. This study offers an important contribution to Arabic app analysis and design, to improve app search and exploration in several domains such as business, marketing, and technical development. Furthermore, it provides insights for the future of Arabic app research and provides guidance for the development of an Arabic app dashboard that will support users on how to select an app based on their specific needs.

Task-oriented dialogue systems (DS) are designed to help users perform daily activities using natural language. Task-oriented DS for English language have demonstrated promising performance outcomes; however, developing such systems to support Arabic remains a challenge. This challenge is mainly due to the lack of Arabic dialogue datasets. This study introduces the first Arabic end-to-end generative model for task-oriented DS (AraConv), which uses the multi-lingual transformer model mT5 with different settings. We also present an Arabic dialogue dataset (Arabic-TOD) and used it to train and test the proposed AraConv model. The results obtained are reasonable compared to those reported in the studies of English and Chinese using the same mono-lingual settings. To avoid problems associated with a small training dataset and to improve the AraConv model’s results, we suggest joint-training, in which the model is jointly trained on Arabic dialogue data and data from one or two high-resource languages such as English and Chinese. The findings indicate the AraConv model performed better in the joint-training setting than in the mono-lingual setting. The results obtained from AraConv on the Arabic dialogue dataset provide a baseline for other researchers to build robust end-to-end Arabic task-oriented DS that can engage with complex scenarios.

Due to the promising performance of pre-trained language models for task-oriented dialogue systems (DS) in English, some efforts to provide multilingual models for task-oriented DS in low-resource languages have emerged. These efforts still face a long-standing challenge due to the lack of high-quality data for these languages, especially Arabic. To circumvent the cost and time-intensive data collection and annotation, cross-lingual transfer learning can be used when few training data are available in the low-resource target language. Therefore, this study aims to explore the effectiveness of cross-lingual transfer learning in building an end-to-end Arabic task-oriented DS using the mT5 transformer model. We use the Arabic task-oriented dialogue dataset (Arabic-TOD) in the training and testing of the model. We present the cross-lingual transfer learning deployed with three different approaches: mSeq2Seq, Cross-lingual Pre-training (CPT), and Mixed-Language Pre-training (MLT). We obtain good results for our model compared to the literature for Chinese language using the same settings. Furthermore, cross-lingual transfer learning deployed with the MLT approach outperform the other two approaches. Finally, we show that our results can be improved by increasing the training dataset size.

With the growth in the smartphone market, many applications can be downloaded by users. Users struggle with the availability of a massive number of mobile applications in the market while finding a suitable application to meet their needs. Indeed, there is a critical demand for personalized application recommendations. To address this problem, we propose a model that seamlessly combines content-based filtering with application profiles. We analyzed the applications available on the Google Play app store to extract the essential features for choosing an app and then used these features to build app profiles. Based on the number of installations, the number of reviews, app size, and category, we developed a content-based recommender system that can suggest some apps for users based on what they have searched for in the application's profile. We tested our model using a k-nearest neighbor algorithm and demonstrated that our system achieved good and reasonable results.