Sexism has become a growing concern on social media platforms as it impacts the health of the internet and can have negative impacts on society. This paper describes the coco system that participated in SemEval-2023 Task 10, Explainable Detection of Online Sexism (EDOS), which aims at sexism detection in various settings of natural language understanding. We develop a novel neural framework for sexism detection and misogyny that can combine text representations obtained using pre-trained language model models such as Bidirectional Encoder Representations from Transformers and using BiLSTM architecture to obtain the local and global semantic information. Further, considering that the EDOS dataset is relatively small and extremely unbalanced, we conducted data augmentation and introduced two datasets in the field of sexism detection. Moreover, we introduced Focal Loss which is a loss function in order to improve the performance of processing imbalanced data classification. Our system achieved an F1 score of 78.95\% on Task A - binary sexism.