Lanfrica Talks #7 | Sentiment Analysis in Low-Resource African Languages by Shamsuddeen H. Muhammad скачать в хорошем качестве

Lanfrica Talks #7 | Sentiment Analysis in Low-Resource African Languages by Shamsuddeen H. Muhammad

Links Competition : https://codalab.lisn.upsaclay.fr/comp... AfriSenit: https://afrisenti-semeval.github.io NaijaSenti: https://github.com/hausanlp/NaijaSenti Learn more about Lanfrica Talks at https://lanfrica.com/blog/lanfrica-talks Abstract Due to the widespread use of the Internet and social media platforms, most languages are becoming digitally available. This allows for various artificial intelligence (AI) applications that enable tasks such as sentiment analysis, hateful content detection, and content translation, among other natural language processing (NLP) tasks. However, most African languages do not have curated datasets for developing such AI applications. Recently, various individual and funded initiatives have set out to reverse this trend and create such datasets for African languages. However, research is required to determine both the suitability of current NLP techniques and the development of novel techniques to maximize the applications of the datasets. In this talk, I will present our work on sentiment analysis for Nigerian languages (NaijaSenti) and our SemEval shared-task on sentiment analysis in African languages (AfriSenti-SemEval2023). Bio Shamsuddeen is a PhD candidate in Computer Science at the University of Porto, Portugal. He is also a faculty member at Bayero University, Kano, Nigeria. His research focuses on NLP for low-resource African languages. Currently, he is interested in classification tasks such as sentiment analysis and hate speech detection. Shamsuddeen is an active member of the Masakhane NLP group and co-founder of HausaNLP.