FASSILA: A Corpus for Algerian Dialect Fake News Detection and Sentiment Analysis
This addresses the problem of low-resource language processing for researchers and practitioners in NLP, though it is incremental as it applies existing methods to new data.
The authors tackled the lack of annotated corpora for the Algerian dialect by creating FASSILA, a dataset of 10,087 sentences for fake news detection and sentiment analysis, achieving promising results in classification experiments.
In the context of low-resource languages, the Algerian dialect (AD) faces challenges due to the absence of annotated corpora, hindering its effective processing, notably in Machine Learning (ML) applications reliant on corpora for training and assessment. This study outlines the development process of a specialized corpus for Fake News (FN) detection and sentiment analysis (SA) in AD called FASSILA. This corpus comprises 10,087 sentences, encompassing over 19,497 unique words in AD, and addresses the significant lack of linguistic resources in the language and covers seven distinct domains. We propose an annotation scheme for FN detection and SA, detailing the data collection, cleaning, and labelling process. Remarkable Inter-Annotator Agreement indicates that the annotation scheme produces consistent annotations of high quality. Subsequent classification experiments using BERT-based models and ML models are presented, demonstrate promising results and highlight avenues for further research. The dataset is made freely available on GitHub (https://github.com/amincoding/FASSILA) to facilitate future advancements in the field.