Fake news detection involves predicting the likelihood that a particular news article is intentionally deceptive. Arabic FND started to receive more attention in the last decade, and many detection approaches demonstrated some ability to detect fake news on multiple datasets. However, most existing approaches do not consider recent advances in natural language processing, i.e., the use of neural networks and transformers. This paper presents a comprehensive comparative study of neural network and transformer-based language models used for Arabic FND. We examine (...) the use of neural networks and transformer-based language models for Arabic FND and show their performance compared to each other. We also conduct an extensive analysis of the possible reasons for the difference in performance results obtained by different approaches. The results demonstrate that transformer-based models outperform the neural network-based solutions, which led to an increase in the F1 score from 0.83 to 0.95, and it boosted the accuracy by 16% compared to the best in neural network-based solutions. Finally, we highlight the main gaps in Arabic FND research and suggest future research directions. (shrink)

Seasonal outbreaks have several different periods that occur primarily during winter in temperate regions, while influenza may occur throughout the year in tropical regions, triggering outbreaks more irregularly. Similarly, dengue occurs in the star of the rainy season in early May and reaches its peak in late June. Dengue and flu brought an impact on various countries in the years 2017–2019 and streaming Twitter data reveals the status of dengue and flu outbreaks in the most affected regions. This research work (...) presents that Social Media Analysis can be used as a detector of the epidemic outbreak and to understand the sentiment of social media users regarding various diseases. Providing awareness about seasonal outbreaks through SMA is an effective approach for researchers and healthcare responders to detect the early outbreaks. The proposed model aims to find the sentiment about the disease in tweets, and the seasonal outbreaks-related tweets are classified into two classes as disease positive and disease negative. This work proposes a machine-learning-based approach to detect dengue and flu outbreaks in social media platform Twitter, using four machine learning algorithms: Random Forest, K-Nearest Neighbor, Support Vector Machine, and Decision Tree, with the help of Term Frequency and Inverse Document Frequency. For experimental analysis, two datasets are analyzed individually. The experimental results show that the RF classifier has outperformed the comparison models in terms of improved accuracy, precision, recall, F1-measure, and Receiver Operating Characteristic curve. The proposed work offers favorable performance with total precision, accuracy, recall, and F1-measure ranging from 84% to 88% for conventional machine learning techniques. (shrink)

Examining the quality perceptions of consumers has often been recommended as an international research paradigm. This study is grounded in the Pakistani consumer market to evaluate the impact of food packaging cues on perceived product quality. The moderating effect of consumer knowledge was also taken into consideration in the study. A signaling theory was used in the study for its established predictive power in consumer behavior, marketing, and various fields of research. Based on the essence of the signaling theory, this (...) study hypothesized that food packaging cues cast a positive impact on perceived product quality and consumer knowledge moderates these relationships. By using the sample of 504 consumers, data were gathered using the mall intercept method following a multi-stage sampling technique. The responses were analyzed using Statistical Package for Social sciences and Smart Partial Least Square. The findings of this study unveil that the extrinsic cues' brand name, price, nutritional labels, and precautionary labels were positively and significantly related to the perceived product quality. However, the country of origin cast no impact on the perceived product quality. Consumer knowledge reflected a moderation effect on the relationships between brand name and country of origin with the perceived product quality whereas it exerted no moderation impact on the relationships of price, nutritional labels, and precautionary labels with the perceived product quality. As the results exhibit that Pakistani consumers rely on food packaging cues for perceiving a product, hence it is recommended that marketers and policymakers develop appropriate marketing strategies focused on the significance of food packaging cues. (shrink)

We report on the first stage of a project on the representations of gender in the coverage of the Arab Spring by Western media. We focus on designing comparable corpora to examine Arab women’s depiction in English and German news during the uprisings. The English corpus is composed of reports published by _The Guardian and The New York Times_. The German corpus consists of articles collected from _Der Spiegel, Die Welt_, _Die Zeit, Frankfurter Allgemeine Zeitung,_ and _Süddeutsche Zeitung_. The datasets (...) were processed through Sketch Engine to identify the terms collocating with _women_ in the English corpus and _Frau_ in the German one. Then, the themes reflected by these expressions in the two corpora were compared. The results show that both news media feature two types of topical frames linked to Arab women; one is associated with the uprisings while the other is related to their recurrent stereotypes in Western news discourse. Yet, there are discrepancies between their focus on related issues to each type. Other differences between the two sets of news outlets include intensity of reporting on Arab women and stressing their nationalities. These findings suggest that although Arab women’s negative stereotypes continued to feature in western news discourse during the Arab Spring, new positive images emerged and contributed to changing their depictions in global media. (shrink)

In 2017, the blockade of Qatar Gulf states caused a plethora of effects on the country. This paper sought to examine the resulting threat effects of this blockade in terms of lowered self-esteem and well-being, and the potential buffering effects of an overarching identity. Using self-report questionnaire data from Qatari secondary school students, multiple moderated mediation models investigated the predictive effects of youngsters’ perceived threat, via self-esteem, on their well-being, and the mitigating roles herein of, respectively, national, Gulf region, and (...) Arab identity. Perceived threat was indeed related to lower well-being via lower self-esteem, and this relationship was equally strong for those low and high in social identity. In terms of the three facets of identity, the overarching Gulf identity seems the most predictive, and it even buffers the negative relationship between threat and reduced self-esteem. (shrink)