The abundance of user-generated online content has presented significant challenges in handling big data. One challenge involves analyzing short posts on social media, ranging from sentiment identification to abusive content detection. Despite recent advancements in pre-trained language models and transfer learning for textual data analysis, the classification performance is hindered by imbalanced data, where anomalous data represents only a small portion of the dataset. To address this, we propose Deep One-Class Fine-Tuning (DOCFT), a versatile method for fine-tuning transfer learning-based textual classifiers. DOCFT uses a one-class SVM-style hyperplane to encapsulate anomalous data. This approach involves a two-step fine-tuning process and utilizes an alternating optimization method based on a custom OC-SVM loss function and quantile regression. Through evaluations on four different hate-speech datasets, we observe that significant performance improvements can be achieved by our met
Introducing LexiFuse+: a semi-supervised model merging lexicon features, BERT transfer learning, and one-class classifiers to detect anomalous content in short texts. It tackles challenges of informal text and imbalanced datasets, excelling in hate speech detection. By leveraging one-class classifiers in a fully deep fine-tuned network trained with unlabeled data, LexiFuse+ surpasses base models.