A Deep Learning Approach: The Impact of Sentiment Analysis of Bangladeshi Workers over the World

In today's globalized world, the pursuit of better opportunities has led to a significant increase in immigration and foreign labor. This trend is particularly evident in Bangladesh, where many workers migrate annually to destinations such as Malaysia, Qatar, Saudi Arabia, and the UAE. Understanding the sentiments and emotions of these workers is crucial to preventing crimes, suicides, political unrest, and other security issues in host countries. As maximum workers usually come from rural Bangladeshi communicate they use local dialect for conversations and very popular widely used local dialect known as Pabnaia. This study did not identify any prior research specifically focused on the local Bangla dialect, Pabnaia; therefore this research built new dataset. The aim of this research is to classify the sentiment of immigrants who use the Pabnaia dialect in their conversations, which may assist in mitigating the aforementioned risks of misunderstandings in immigrant-friendly countries. Pabnaia, widely used in various domains like drama and comedy in Bangladesh. Data were sourced from social media, comments, Bangla dramas, and translations from standard Bangla to Pabnaia, resulting in a dataset of over 2600 records and 22,000 unique words which was collected manually. TF-IDF vectorization was used for feature extraction, followed by basic machine learning algorithms such as Decision Tree, Support Vector Machine, and Naive Bayes. Deep learning techniques, including Deep Neural Network (DNN), Long short-term memory (LSTM), and convolutional neural network (CNN), demonstrated superior performance, where DNN achieving 83% accuracy and an 84% F1-score on the labelled dataset.