Content-Localization based System for Analyzing Sentiment and Hate Behaviors in Low-Resource Dialectal Arabic: English to Levantine and Gulf
Not on the map. Why?
Abstract (arXiv)
Even though online social movements can quickly become viral on social media, languages can be a barrier to timely monitoring and analyzing the underlying online social behaviors (OSB). This is especially true for under-resourced languages on social media like dialectal Arabic; the primary language used by Arabs on social media. Therefore, it is crucial to provide solutions to efficiently exploit resources from high-resourced languages to solve language-dependent OSB analysis in under-resourced languages. This paper proposes to localize content of resources in high-resourced languages into under-resourced Arabic dialects. Content localization goes beyond content translation that converts text from one language to another; content localization adapts culture, language nuances and regional preferences from one language to a specific language/dialect. Automating understanding of the natural and familiar day-to-day expressions in different regions, is the key to achieve a wider analysis of OSB especially for smart cities. In this paper, we utilize content-localization based neural machine translation to develop sentiment and hate classifiers for two low-resourced Arabic dialects: Levantine and Gulf. Not only this but we also leverage unsupervised learning to facilitate the analysis of sentiment and hate predictions by inferring hidden topics from the corresponding data and providing coherent interpretations of those topics in their native language/dialects. The experimental evaluations and proof-of-concept COVID-19 case study on real data have validated the effectiveness of our proposed system in precisely distinguishing sentiments and accurately identifying hate content in both Levantine and Gulf Arabic dialects. Our findings shed light on the importance of considering the unique nature of dialects within the same language and ignoring the dialectal aspect would lead to misleading analysis.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 15 of its 52 references that are in the map. First posted on arXiv 27 Nov 2023.
Builds on
15 of 52 references.
References · 15
- 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
- 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 801
- 2019SemEval-2017 Task 4: Sentiment Analysis in Twittercited by 210
- 2021The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Modelscited by 119
- 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 109
- 2019Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classificationcited by 63
- 2020Detecting White Supremacist Hate Speech using Domain Specific Word Embedding with Deep Learning and BERTcited by 19
- 2021Let-Mi: An Arabic Levantine Twitter Dataset for Misogynistic Languagecited by 15
- 2020Detecting Topic and Sentiment Dynamics Due to COVID-19 Pandemic Using Social Mediacited by 12
- 2019ArSentD-LEV: A Multi-Topic Corpus for Target-based Sentiment Analysis in Arabic Levantine Tweetscited by 11
- 2021Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translationcited by 10
- 2018A Combined CNN and LSTM Model for Arabic Sentiment Analysiscited by 7
Built on by
Citing papers per year: 2023: 1.
1 paper.