A major challenge in analysing social me-dia data belonging to languages that use non-English script is its code-mixed nature. Recentresearch has presented state-of-the-art contex-tual embedding models (both monolingual s.a.BERT and multilingual s.a.XLM-R) as apromising approach. In this paper, we showthat the performance of such embedding mod-els depends on multiple factors, such as thelevel of code-mixing in the dataset, and thesize of the training dataset. We empiricallyshow that a newly introduced Capsule+biGRUclassifier could outperform a classifier built onthe English-BERT as well as XLM-R just witha training dataset of about 6500 samples forthe Sinhala-English code-mixed data.