Sentiment Analysis for YouTube Comments and Video Using AI
Keywords:
Web services, Recommendation, KNNAbstract
The YouTube Comments and Videos Sentiment Analysis project is a sophisticated system designed to automatically classify the sentiments of comments and video transcripts linked to YouTube videos. By leveraging Natural Language Processing and state-of-the-art deep learning models, it can identify whether the sentiments expressed are positive, negative, or neutral. This system makes use of tools like the YouTube Data API to pull in comments and the YouTube Transcript API to gather video transcripts. It employs advanced preprocessing techniques such as tokenization, lemmatization, and stop word removal to get the text ready for sentiment analysis. The project utilizes pre-trained models, including BERT for analyzing comment sentiments and LSTM and GRU for assessing video transcript sentiments, which helps ensure high accuracy in classification. Users can engage with the system through a web-based interface where they simply enter a YouTube video URL. The system then fetches the comments and transcripts, conducts sentiment analysis, and presents the findings in a user-friendly graphical format. It evaluates the models using metrics like accuracy, precision, recall, and F1-score, which helps confirm the system's reliability.
Downloads
References
Athindran, N.S., Manikandaraj, S., & Kamaleshwar, R. Sentiment analysis from YouTube video using Bi-LSTM-GRU classification. In SpringerLink (2018).
Tan, K.L., Lee, C.P., & Lim, K.M. RoBERTa-GRU: A hybrid deep learning model for enhanced sentiment analysis. Appl. Sci., 13, 3915 (2023).
Murfi, H., Syamsyuriani, T., Gowandi, T., & Ardaneswari, G. BERT-based combination of convolutional and recurrent neural network for Indonesian sentiment analysis. arXiv preprint arXiv:2211.05273 (2022).
Khan, A.H., Qamar, U., & Bashir, S. Integrated BERT embeddings, BiLSTM-BiGRU, and 1-D CNN model for sentiment classification analysis of movie reviews. Multimed. Tools Appl., 80, 11443–11458 (2019).
Liu, B., Cao, G., & Yin, J. Bi-level attention model for sentiment analysis of short texts. IEEE Access, 7, 13–22 (2019).
Li, W., Gao, S., Zhou, H., Huang, Z., & Zhang, K. The automatic text classification method based on BERT and feature union. IEEE Parallel and Distributed Systems, 25, 774–777 (2019).
Minaee, S., Azimi, E., & Abdolrashidi, A.A. Deep-sentiment: Sentiment analysis using an ensemble of CNN and bi-LSTM models. arXiv preprint arXiv:1904.04206v1 (2019).
Le, Q., & Mikolov, T. Distributed representations of sentences and documents. International Conference on Machine Learning, 1188–1196 (2014).
Liu, W., & Cambria, E. Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM. AAAI Conference on Artificial Intelligence, 32(1) (2018).
Talaat, A.S. Sentiment analysis classification system using hybrid BERT models. J Big Data, 10, 110 (2023).
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
