A Hybrid Deep Learning Model for Sentiment Analysis of Multilingual Comments on Trending YouTube Videos
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".