A Hybrid Deep Learning Model for Sentiment Analysis of Multilingual Comments on Trending YouTube Videos

The rapid growth of social media platforms has resulted in a vast and diverse collection of user-generated content in multiple languages, such as user comments. Analyzing the sentiment expressed in these comments in multiple languages can provide valuable insights into public opinion. Again, conducting sentiment analysis on multilingual and multi-regional data in real-time presents unique challenges, particularly due to language and cultural variations. While sentiment analysis has been extensively explored using various state-of-the-art methods, hybrid deep learning models have proven effective in capturing complex language structures. Therefore, the objective of this research is to propose a hybrid deep learning model for analyzing sentiments based on multilingual comments from trending YouTube videos across different regions. To achieve this objective, this study proposes a hybrid deep learning model that combines Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) algorithms with GloVe embeddings for sentiment analysis. The research focuses on Bangla and English languages; and evaluating the model’s performance using trending YouTube videos from four countries: Bangladesh, the USA, the UK, and Canada. The proposed hybrid model achieved an accuracy of 90.95% for user comments in Bangla and 97.42% for comments in English that demonstrate its effectiveness in analyzing multi-lingual comments from multi-regional YouTube trending videos.