I am a datascience PhD student conducting research in Sentiment Analysis for dialectal languages on social media with a specific focus for Arabic. Unlike other languages, Arabic is very dialectal and differs significantly among regions. Many Arabs tend to express their natural mother-tongue in text on social media without following a unified orthography. This unstructured form of language lacks semantic and linguistic resources, making it a challenge for the Arabic Natural Language Processing. Through my research I plan to leverage sentiment analysis methods to handle the heterogeneous Arabic social data. Extracting sentiment from text stems from my interest in Affective Computing: Developing machines that can understand, and react to, human emotion.
SenZi: A Sentiment Analysis Lexicon for the Latinised Arabic (Arabizi) (2019)
Tobaili, Taha; Fernandez, Miriam; Alani, Harith; Sharafeddine, Sanaa; Hajj, Hazem and Glavas, Goran
In : RANLP 2019 (2-4 Sep 2019, Varna, Bulgaria) (pp. 1204-1212)