YOSM: A NEW YORUBA SENTIMENT CORPUS FOR MOVIE REVIEWS

Iyanuoluwa Shode, David Ifeoluwa Adelani, Anna Feldman

Keywords: Yoruba, Sentiment Analysis, Corpus, Movie Reviews, BERT

Abstract: People’s opinions and judgments regarding a particular movie differ. A movie that is thoroughly enjoyed and recommended by an individual might be hated by another. One characteristic of humans is the ability to have positive or negative feelings. To automatically classify and study human feelings, an aspect of natural language processing, sentiment analysis was designed to understand human feelings regarding several issues which could affect a product, social media platforms, government, societal discussions, or even movies. Due to the scarcity of datasets and linguistic architectures that will suit low resource languages, African languages "low resource languages" have not been fully explored when it comes to tackling natural language processing tasks. Several works on sentiment analysis have been done on high resource languages while low resources languages like Yoruba and other African languages have received little attention. For this reason, our attention is placed on Yoruba to explore sentiment analysis on reviews of Nigerian movies. The data comprised 1500 movie reviews that were sourced from IMDB, Rotten Tomatoes, Letterboxd, Cinemapointer, and Nollyrated. We develop sentiment classification models using state-of-the-art pre-trained language models like mBERT and AfriBERTa to classify the movie reviews.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/yosm-a-new-yoruba-sentiment-corpus-for-movie/code)