This paper narrates the work of the team Amrita_CEN for the shared task on Patronizing and Condescending Language Detection at SemEval 2022. We implemented machine learning algorithms such as Support Vector Machine (SVV), Logistic regression, Naive Bayes, XG Boost and Random Forest for modelling the tasks. At the same time, we also applied a feature engineering method to solve the class imbalance problem with respect to training data. Among all the models, the logistic regression model outperformed all other models and we have submitted results based upon the same.

Depression is one of the most common mentalissues faced by people. Detecting signs ofdepression early on can help in the treatmentand prevention of extreme outcomes like suicide. Since the advent of the internet, peoplehave felt more comfortable discussing topicslike depression online due to the anonymityit provides. This shared task has used datascraped from various social media sites andaims to develop models that detect signs andthe severity of depression effectively. In thispaper, we employ transfer learning by applyingenhanced BERT model trained for Wikipediadataset to the social media text and performtext classification. The model gives a F1-scoreof 63.8% which was reasonably better than theother competing models.