Connecting Arabs

Ali, Ahmed; Chowdhury, Shammur Absar; Afify, Mohamed; El-Hajj, Wassim; Hajj, Hazem; Abbas, Mourad; Hussein, Amir; Ghneim, Nada; Abushariah, Mohammad A. M.; Alqudah, Assal Ali Mustafa

doi:10.1145/3451150

Cited by 13 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the field of NLP [27][28][29][30], each feature can be encoded into a highdimensional one-hot vector. These features are very sparse and can be converted into low-dimensional dense features after embedding layer [16].…”

Section: Embedding Layermentioning

confidence: 99%

Click-Through Rate Prediction Based on User Behaviors and Feature Importance

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Click-through rate prediction is one of the hot topics in the field ofrecommendation and advertising systems. The existing CTR predictionmodels mainly include feature interaction and behavior sequence. Forexample, PNN, DCN and other models use deep learning methods toextract feature interaction information, while DIN and DIEN captureuser interest through user’s historical behavior, and then use attentionmechanism to model the relationship between target items and behavior sequences. However, the existing CTR prediction techniques eitherignore both aspects or only consider one of them, which limit the prediction performance. In order to solve the above problems, we proposea click-through prediction model CUBFI that combines user behaviorand feature importance in this paper. Firstly, In order to extract interests, Global-local Gate and Post-LN Informer module are proposed atthe interest extraction layer. In addition, we introduce auxiliary losses tosupervise the extraction of user interest features. Secondly, In the interestupdate layer, we introduce A-GRU to enhance the relationship betweeninterest expression and target items. Finally, for non-temporal features,this paper proposes a multi-cross layer to increase the nonlinear abilityof the model. Experiments show that our model can effectively improve the click-through rate prediction accuracy of advertisements. The codes will be available at https://github.com/jihuiqin2/sequence ctr.

show abstract

Section: Embedding Layermentioning

confidence: 99%

Click-Through Rate Prediction Based on User Behaviors and Feature Importance

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…74–5). There have been recent initiatives since the 2010s, with the launch of social media platforms and the use of social media analytics, but the main difficulty is that Arab users post in a variety of dialects (Ali et al, 2021: p. 127). This problem requires heavy investment in Arabic NLP, and the problem is exacerbated by the lack of digital talents in the Arab region, coupled with the unwillingness of some Big Tech companies to develop digital tools in the Arabic language since the bulk of their revenue is generated in North America.…”

Section: Losing the Digital Ad Marketmentioning

confidence: 99%

The digital divide in the journalism sector

Mellor

2023

Convergence: The International Journal of Research into New Med

View full text Add to dashboard Cite

This article argues that the digital sphere has maintained the offline hierarchal forms of political, economic, and cultural powers, taking the Arab journalism sector as a topical case study. The article explores the potential of digital platforms as a new source of revenue for Arab news media and a new site for disseminating informative content that helps push the freedom of speech in the region. It demonstrates the difficulty of achieving either goal partly due to the monopoly of Big Tech over the digital advertising market and partly due to the competition among Arab media outlets to use clickbait content to lure audiences and hence increase superficial metrics such as clicks and shares. The article draws on different forms of evidence, including articles penned by Arab journalists, in which they reflect on their experiences in the digital sphere, papers by Arab scholars, in addition to informal conversations with selected Arab journalists.

show abstract

The Application and Research of Intelligent Mobile Terminal in Mixed Listening and Speaking Teaching of College English

Jiang

2024

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Connecting Arabs

Cited by 13 publications

References 7 publications

Click-Through Rate Prediction Based on User Behaviors and Feature Importance

Click-Through Rate Prediction Based on User Behaviors and Feature Importance

The digital divide in the journalism sector

The Application and Research of Intelligent Mobile Terminal in Mixed Listening and Speaking Teaching of College English

Contact Info

Product

Resources

About