COMPUTER DOMAIN
Published July 10, 2023 | Version v1
Journal article Open

Multimodal Sentiment Analysis using LSTM and RoBerta

Authors/Creators

  • 1. Assistant Professor,Dept of Information Technology ,MSIT , New Delhi, India
  • 2. Student, Dept of Information Technology ,MSIT , New Delhi, India

Description

Social media is a valuable data source for understanding people's thoughts and feelings. Sentiment analysis and affective computing help analyze sentiment and emotions in social media posts. Our research paper proposes a model for tweet emotions analysis using LSTM, GloVe embeddings, and RoBERTa. This model captures sequential dependencies in tweets, leverages semantic representations, and enhances contextual understanding. We evaluate the model on a tweet emotions dataset, demonstrating its effectiveness in accurately classifying emotions in tweets.Through evaluation on a tweet emotions dataset, we demonstrate the effectiveness of our proposed model in accurately classifying the emotions expressed in tweets.

Files

Multimodal Sentiment Analysis using LSTM and RoBerta -Formatted Paper.pdf

Files (428.2 kB)

Additional details

References

  • 1.Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., & Mihalcea, R. (2018). Meld: A multimodal multi-party dataset for emotion recognition in conversations. arXiv preprint arXiv:1810.02508.
  • 2.Wankhade, M., Rao, A. C. S., & Kulkarni, C. (2022). A survey on sentiment analysis methods, applications, and challenges. Artificial Intelligence Review, 55(7), 5731-5780.
  • 3.Montoyo, A., Martínez-Barco, P., & Balahur, A. (2012). Subjectivity and sentiment analysis: An overview of the current state of the area and envisaged developments. Decision Support Systems, 53(4): 675-679.
  • 4.Nandwani P, Verma R (2021). A review on sentiment analysis and emotion detection from text. Soc Netw Anal Min.11(1):81.
  • 5.Cui, J., Wang, Z., Ho, S. B., & Cambria, E. (2023). Survey on sentiment analysis: evolution of research methods and topics. Artificial Intelligence Review, 1-42..
  • 6.Dahl, G. E., Yu, D., Deng, L., & Acero, A. (2011). Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Transactions on audio, speech, and language processing, 20(1), 30-42.
  • 7.Ong, B. T., Sugiura, K., & Zettsu, K. (2016). Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM 2.5. Neural Computing and Applications, 27, 1553-1566.
  • 8.Koroteev, M. V. (2021). BERT: a review of applications in natural language processing and understanding. arXiv preprint arXiv:2103.11943..
  • 9.Kalchbrenner, N., Grefenstette, E., & Blunsom, P. (2014). A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188..
  • 10.Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., & Hovy, E. (2016, June). Hierarchical attention networks for document classification. In Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: human language technologies (pp. 1480-1489).