nlpBDpatriots at BLP-2023 Task 2: A Transfer Learning Approach to Bangla Sentiment Analysis
This work addresses sentiment analysis for Bangla language users, but it is incremental as it applies existing methods to a specific dataset in a competition setting.
The paper tackled sentiment analysis on Bangla social media posts by developing a transfer learning approach with data augmentation, achieving a micro F1 score of 0.71 and ranking 12th out of 30 teams in a shared task.
In this paper, we discuss the nlpBDpatriots entry to the shared task on Sentiment Analysis of Bangla Social Media Posts organized at the first workshop on Bangla Language Processing (BLP) co-located with EMNLP. The main objective of this task is to identify the polarity of social media content using a Bangla dataset annotated with positive, neutral, and negative labels provided by the shared task organizers. Our best system for this task is a transfer learning approach with data augmentation which achieved a micro F1 score of 0.71. Our best system ranked 12th among 30 teams that participated in the competition.