Sentiment analysis (SA) of Arabic tweets is a complex task due to the rich morphology of the Arabic language and the informal nature of language on Twitter. Previous research on the SA of tweets mainly focused on manually extracting features from the text. Recently, neural word embeddings have been utilized as less labor-intensive representations than manual feature engineering. Most of these word-embeddings model the syntactic information of words while ignoring the sentiment context. In this paper, we propose to learn sentiment-specific word embeddings from Arabic tweets and use them in the Arabic Twitter sentiment classification. Moreover, we propose a feature ensemble model of surface and deep features. The surface features are manually extracted features, and the deep features are generic word embeddings and sentimentspecific word embeddings. The extensive experiments are performed to test the effectiveness of the surface and deep features ensemble, pooling functions, embeddings size, and cross-dataset models. The recent language representation model BERT is also evaluated on the task of SA of Arabic tweets. The models are evaluated on three different datasets of Arabic tweets, and they outperform the previous results on all these datasets with a significant increase in the F-score. The experimental results demonstrate that: 1) the highest performing model is the ensemble of surface and deep features and 2) the approach achieves the state-of-the-art results on several benchmarking datasets. INDEX TERMS Arabic sentiment analysis, arabic sentiment embeddings, arabic tweets, surface and deep features ensemble.

Numerical reasoning based machine reading comprehension is a task that involves reading comprehension along with using arithmetic operations such as addition, subtraction, sorting, and counting. The DROP benchmark (Dua et al., 2019) is a recent dataset that has inspired the design of NLP models aimed at solving this task. The current standings of these models in the DROP leaderboard, over standard metrics, suggest that the models have achieved near-human performance. However, does this mean that these models have learned to reason? In this paper, we present a controlled study on some of the top-performing model architectures for the task of numerical reasoning. Our observations suggest that the standard metrics are incapable of measuring progress towards such tasks.

This paper describes the research conducted to design the Arabic Brain Communicator (ABC), which is a braincontrolled typing system designed to facilitate communication for people with severe motor disabilities in Arabic. A user centered design was adopted; it included empirical investigations and meetings with Subject-Matter Experts and possible users. Activities conducted in the analysis and design of the system are discussed.

No abstract

Abstract. In this paper, we describe the User Interface (UI) design issues for serious games aimed at developing phonological processing skills of people with specific learning difficulties such as dyslexia. These games are designed with Brain-Computer Interfaces (BCI) which take the compelling and creative aspects of traditional computer games designed for Arabic interfaces and apply them for cognitive skills' development purposes. Immersion and engagement in the games are sought with novel interaction methods; the interaction mode for these games involved mind-control coupled with cursor-based selection. We describe the conceptual design of these serious games and an overview of the BCI software development framework.