SpringerLink
Log in

Hybrid Model for Sentiment Analysis Based on Both Text and Audio Data

  • Conference paper
  • First Online:
Sentimental Analysis and Deep Learning

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 1408))

  • 1470 Accesses

Abstract

A model for positive/negative sentiment analysis of phone conversations audio data is considered. Over six thousand features are retrieved employing opensmile Python library, afterward the most significant features are selected. Sentiment analysis of the related text data of conversations is also carried out. An attempt to combine features retrieved from audio and text is performed to increase the quality of binary sentiment classification. Practically acceptable results are obtained. An original algorithm is developed and implemented, which includes data preprocessing, model training, and verification. A research software package has been developed to solve the problem of bank scoring.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 249.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free ship** worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Linqin, C., Yaxin, H., Jiangong D., & Sitong Z. (2019). Audio–textual emotion recognition based on improved neural networks. Mathematical Problems in Engineering, 2593036.

    Google Scholar 

  2. Devamanyu, H., Soujanya, P., Roger, Z., & Rada, M. (2021). Conversational transfer learning for emotion recognition. Information Fusion, 65, 1–12.

    Article  Google Scholar 

  3. Srishti, V., & Seba, S. (2021). Highlighting keyphrases using senti-scoring and fuzzy entropy for unsupervised sentiment analysis. Expert Systems With Applications, 169, 1–12.

    Google Scholar 

  4. Yazhou, Z., Prayag, T., Dawei, S., **aoliu, M., Panpan, W., **ang, L., & Hari, M. P. (2021). Learning interaction dynamics with an interactive LSTM for conversational sentiment analysis. Neural Networks, 133, 40–56.

    Article  Google Scholar 

  5. Tsai, M., & Huang, J. (2021). Sentiment analysis of pets using deep learning technologies in artificial intelligence of things system. PPR: PPR301546, 1–16.

    Google Scholar 

  6. Ghorbani, M., Bahaghighat, M., **n, Q., & Ozen, F. (2020). ConvLSTMConv network: A deep learning approach for sentiment analysis in cloud computing. Journal of Cloud Computing, 9(16), 1–12.

    Google Scholar 

  7. Abburi, H., Prasath, R., Shrivastava, M., & Gangashetty, S. V. (2016). Multimodal sentiment analysis using deep neural networks. In Proceeding of the 4th international conference on mining intelligence and knowledge exploration (pp. 13–19).

    Google Scholar 

  8. Kumaran, U., Rammohan, S. R., Nagarajan, S. M., & Prathik, A. (2021). Fusion of MEL and gammatone frequency cepstral coefficients for speech emotion recognition using deep C-RNN. International Journal of Speech Technology, 24, 303–314.

    Article  Google Scholar 

  9. Luo, Z., Xu, H., & Chen, F. (2018). Audio sentiment analysis by heterogeneous signal features learned from utterance-based parallel neural network. EasyChair Preprint No., 668, 1–18.

    Google Scholar 

  10. Li, B., Dimitriadis, D., & Stolcke, A. (2019, May). Acoustic and lexical sentiment analysis for customer service calls. In Proceeding of the IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5876–5880).

    Google Scholar 

  11. Abburi, H., Alluri, K. N. R. K. R., Vuppala, A. K., Shrivastava, M., & Gangashetty, S. V. (2017) Proceeding of the tenth international conference on contemporary computing (IC3) (pp. 1–5).

    Google Scholar 

  12. Sklearn logistic regression documentation. Retrieved on May 30, 2021, from https://scikit-learn.org/stable/modules/classes.html

  13. James, G., Witten, D., Hastie, T., & Tibshirani, R. (2014). An introduction to statistical learning.

    Google Scholar 

  14. Russian open speech to text. Retrieved on May 30, 2021, from https://azure.microsoft.com/en-us/services/open-datasets/catalog/open-speech-to-text/

  15. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning.

    Google Scholar 

  16. Audio feature extraction opensmile. Retrieved on May 30, 2021, from https://www.audeering.com/opensmile/

  17. Vogt, C. C., & Cottrel, G. W. (1999). Fusion via a linear combination of scores. Information Retrieval, 1, 151–173.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. OTPBank, Leningradskoe highway, 16A, bldg. 2, Moscow, 125171, Russian Federation

    D. E. Tolstoukhov

  2. Bauman Moscow State Technical University, ul. Baumanskaya 2-ya, 5/1, Moscow, Russian Federation

    D. E. Tolstoukhov, Y. V. Verina & O. V. Kravchenko

  3. Kotel’nikov Institute of Radioengineering and Electronics of Russian Academy of Sciences, Moscow, 125009, Russian Federation

    D. P. Egorov

  4. Federal Research Center “Computer Science and Control” of RAS, Vavilova st., 40, Moscow, 119333, Russian Federation

    O. V. Kravchenko

Authors
  1. D. E. Tolstoukhov
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. D. P. Egorov
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Y. V. Verina
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. O. V. Kravchenko
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to D. E. Tolstoukhov .

Editor information

Editors and Affiliations

  1. Institute of Engineering, Tribhuvan University, Pulchowk Campus, Lalitpur, Nepal

    Subarna Shakya

  2. Intelligent Systems Research Centre, Aurel Vlaicu University of Arad, Arad, Romania

    Valentina Emilia Balas

  3. Songkla University, Songkhla, Thailand

    Sinchai Kamolphiwong

  4. Department of Electrical and Computer Engineering, Concordia University, Montreal, QC, Canada

    Ke-Lin Du

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Tolstoukhov, D.E., Egorov, D.P., Verina, Y.V., Kravchenko, O.V. (2022). Hybrid Model for Sentiment Analysis Based on Both Text and Audio Data. In: Shakya, S., Balas, V.E., Kamolphiwong, S., Du, KL. (eds) Sentimental Analysis and Deep Learning. Advances in Intelligent Systems and Computing, vol 1408. Springer, Singapore. https://doi.org/10.1007/978-981-16-5157-1_77

Download citation

Publish with us

Policies and ethics

Search

Navigation