Abstract: Sentiment Analysis is an aspect of natural languageprocessing (NLP) that has been a topicof research. While most studies focus on highresourcelanguages with an extensive amountof available data, the study on low-resource languageswith insufficient data needs attention.To address this issue, we propose a transformerbasedmethod for sentiment analysis for lowresourcesAfrican languages, Nigerian Pidginand Yoruba. To evaluate the effectiveness ofour multilingual language models for monolingualsentiment classification, we participated inthe AfriSenti SemEval shared task 2023 competition.On the official e valuation s et, ourgroup (named as Bhattacharya\_Lab) ranked1 out of 33 participating groups in the MonolingualSentiment Classification task (i.e., TaskA) for Nigerian Pidgin (i.e., Track 4), and inthe Top 5 among 33 participating groups inthe Monolingual Sentiment Classification taskfor Yoruba (i.e., Track 2) respectively, demonstratingthe potential for our transformer-basedlanguage models to improve sentiment analysisin low-resource languages. Overall, ourstudy highlights the importance of exploringthe potential of NLP in low-resource languagesand the impact of transformer-based multilinguallanguage models in sentiment analysis forthe low-resource African languages, NigerianPidgin and Yoruba.