Skip to main content
SpringerLink
Log in

Active Learning Enhanced Sequence Labeling for Aspect Term Extraction in Review Data

  • Conference paper
  • First Online:
Advanced Computing (IACC 2020)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1367))

Included in the following conference series:

Abstract

Analyzing reviews with respect to each aspect gives better understanding as compared to overall opinions and this requires the aspect terms and their corresponding opinions to be extracted. Supervised models for aspect term extraction require large amount of labeled data. Aspect annotated data is scarcely available for use and the cost of manual annotation of the entire data is huge. This study proposes a way of using Active Learning to select a highly informative subset of the data that needs to be labeled, to train the supervised model. The identification of aspect terms is defined as a sequence labelling problem with the help of BiLSTM network and CRF. The model is trained on publicly available SemEval (2014–16) datasets for restaurant and laptop reviews. The results show a 36% and 42% reduction in annotation cost for restaurants and laptops respectively, with negligible effect on the model’s performance. A significant difference in cost is observed between active learning guided sampling and random sampling approaches.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping 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. Search Engine Land. https://searchengineland.com/88-consumers-trust-online-reviews-much-personal-recommendations-195803. Accessed 14 July 2017

  2. Pavlopoulos, J., Androustsopoulos, I.: Aspect term extraction for sentiment analysis: new datasets, new evaluation measures and improved unsupervised method. In: Proceedings of the 5th Workshop on Language Analysis for Social Media, pp. 44–52. Association for Computational Linguistics, Gothenburg (2014)

    Google Scholar 

  3. Kholgi, M.: Active learning for concept extraction from clinical free text. Ph.D. thesis, Queensland University of Technology (2017)

    Google Scholar 

  4. Vu, V., Labroche, N.: Active seed selection for constrained clustering. Intell. Syst. 21, 537–552 (2017)

    Google Scholar 

  5. Ishwaran, H., et al.: Random survival forests. Ann. Appl. Stat. 2(3), 841–860 (2008)

    Article  MathSciNet  Google Scholar 

  6. Sutton, R.S., Barto, A.G.: Reinforcement Learning, 2nd edn. MIT Press, London (2018)

    MATH  Google Scholar 

  7. Bagheri, A., Saraee, M., de Jong, F.: An unsupervised aspect detection model for sentiment analysis of reviews. In: Métais, E., Meziane, F., Saraee, M., Sugumaran, V., Vadera, S. (eds.) NLDB 2013. LNCS, vol. 7934, pp. 140–151. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38824-8_12

    Chapter  Google Scholar 

  8. Liu, B., Hu, M.: Opinion mining, sentiment analysis, and opinion spam detection dataset (2004)

    Google Scholar 

  9. He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: An unsupervised neural attention model for aspect extraction. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL, Vancouver, pp. 388–397 (2017)

    Google Scholar 

  10. Luo, L., et al.: Unsupervised neural aspect extraction with sememes. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI, Macao, China, pp. 5123–5129 (2019)

    Google Scholar 

  11. Chauhan, G.S., et al.: An unsupervised multiple word-embedding method with attention model for cross domain aspect term extraction. In: 3rd International Conference on Emerging Technologies in Computer Engineering, pp. 110–116. IEEE, Jaipur (2020)

    Google Scholar 

  12. Giannakopoulos, A., et al.: Unsupervised aspect term extraction with Bi-LSTM & CRF using automatically labeled datasets. In: Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pp. 180–188. Association for Computational Linguistics, Copenhagen (2017)

    Google Scholar 

  13. Fu, X., et al.: Semi-supervised aspect-level sentiment classification model based on variational autoencoder. Knowl. Based Syst. 171, 81–92 (2019)

    Article  Google Scholar 

  14. Tandra, S., Nautiyal, A., Gupta, D.: An efficient text labeling framework using active learning model. In: Thampi, S.M. (ed.) Intelligent Systems, Technologies and Applications. AISC, vol. 1148, pp. 141–155. Springer, Singapore (2020). https://doi.org/10.1007/978-981-15-3914-5_11

    Chapter  Google Scholar 

  15. Xiang, Y., He, H., Zheng, J.: Aspect term extraction based on MFE-CRF. Information 9, 198 (2018)

    Article  Google Scholar 

  16. Li, X., et al.: Aspect term extraction with history attention and selective transformation. In: Proceedings of 27th International Joint Conference on Artificial Intelligence, IJCAI, Stockholm, Sweden, pp. 4194–4200 (2018)

    Google Scholar 

  17. Dalal, H., Gao, G.: Aspect extraction from reviews using conditional random fields. In: The Sixth International Conference on Data Analytics, pp. 158–167, Data Analytics, Barcelona, Spain (2015)

    Google Scholar 

  18. Cahyadi, A., Khodra, M.L.: Aspect-based sentiment analysis using convolution neural networks and bidirectional long short-term memory. In: Proceedings of the 5th International Conference on Advanced Informatics: Concept Theory and Applications, pp. 124–129. IEEE, Krabi (2018)

    Google Scholar 

  19. Dai, H.L., Song, Y.Q.: Neural aspect and opinion term extraction with mined rules as weak supervision. In: Proceedings of the 57th Annual Meeting of Association for Computational Linguistics, ACL, Florence, Italy, pp. 5268–5277 (2019)

    Google Scholar 

  20. Query ID="Q4" Text="Kindly provide the page range for Ref. [20], if possible." Ray, P., Chakrabarti, A.: A mixed approach of deep learning method and rule-based method to improve aspect level sentiment analysis. Appl. Comput. Inform. 15(1) (2019)

    Google Scholar 

  21. Ning, L., Bo, S.: Aspect-based sentiment analysis with gated alternate neural network. Knowl.-Based Syst. 188, 105010 (2019)

    Google Scholar 

  22. Augustyniak, L., Kajdanowicz, T., Kazienko, P.: Comprehensive analysis of aspect term extraction methods using various text embeddings. arXiv (2019)

    Google Scholar 

  23. Venugopalan, M., Gupta, D.: An unsupervised hierarchical rule based model for aspect term extraction augmented with pruning strategies. Procedia Comput. Sci. 171, 22–31 (2020)

    Article  Google Scholar 

  24. Narasimhan, K., Yala, A., Barzilay, R.: Improving information extraction by acquiring external evidence with reinforcement learning. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 2355–2365. ACL, Austin (2016)

    Google Scholar 

  25. Meng, F., Yuan, L., Cohn, T.: Learning how to active learn: a deep reinforcement learning approach. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 595–605. ACL, Copenhagen (2017)

    Google Scholar 

  26. Diligach, D., Palmer, M.: Good seed makes a good crop: accelerating active learning using language modelling. In: Proceedings of 49th Annual Meeting of the Association of Computational Linguistics, pp. 6–10. ACM, Portland (2011)

    Google Scholar 

  27. Chairi, I., Alaoui, S., Lyhyaouier, A.: Sample selection based active learning for imbalanced data. In: Proceedings of the 10th International Conference on Signal-Image Technology & Internet-Based Systems, pp. 645–651. IEEE, Marrakech (2014)

    Google Scholar 

  28. Yang, B., et al.: Effective multi-label active learning for text classification. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 917–926. ACM, Paris (2009)

    Google Scholar 

  29. Li, H.: Deep learning for natural language processing: advantages and challenges. Natl. Sci. Rev. 5(1), 24–26 (2017)

    Article  Google Scholar 

  30. Wick, C.: Deep learning. Informatik-Spektrum 40(1), 103–107 (2016). https://doi.org/10.1007/s00287-016-1013-2

    Article  Google Scholar 

  31. Sherstinsky, A.: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Phys. D: Nonlinear Phenom. 404, 132306 (2020)

    Article  MathSciNet  Google Scholar 

  32. Greff, K., et al.: LSTM: a search space odessy. IEEE Trans. Neural Netw. Learn. Syst. 28(10), 2222–2232 (2017)

    Article  MathSciNet  Google Scholar 

  33. Settles, B.: Active learning literature survey. Computer Sciences Technical Report 1648. University of Wisconsin–Madison (2009)

    Google Scholar 

  34. Settles, B., Craven, M., Ray, S.: Multiple-instance active learning. In: Proceedings of the 20th International Conference on Neural Information Processing Systems, pp. 1289–1296. Curran Associated Inc., Red Hook (2007)

    Google Scholar 

  35. Understanding Actor Critic Methods and A2C. https://towardsdatascience.com/understanding-actor-critic-methods-931b97b6df3f. Accessed 16 Feb 2019

  36. Word Mover’s Distance for Text Similarity. https://towardsdatascience.com/word-movers-distance-for-text-similarity-7492aeca71b0. Accessed 26 Aug 2019

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Amrita School of Engineering, Bengaluru, Amrita Vishwa Vidyapeetham, Bengaluru, India

    K. Shyam Sundar & Deepa Gupta

Authors
  1. K. Shyam Sundar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Deepa Gupta
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to K. Shyam Sundar .

Editor information

Editors and Affiliations

  1. Bennett University, Greater Noida, Uttar Pradesh, India

    Deepak Garg

  2. University College London, London, UK

    Kit Wong

  3. Missouri University of Science and Technology, Rolla, MO, USA

    Jagannathan Sarangapani

  4. Bennett University, Greater Noida, Uttar Pradesh, India

    Suneet Kumar Gupta

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Shyam Sundar, K., Gupta, D. (2021). Active Learning Enhanced Sequence Labeling for Aspect Term Extraction in Review Data. In: Garg, D., Wong, K., Sarangapani, J., Gupta, S.K. (eds) Advanced Computing. IACC 2020. Communications in Computer and Information Science, vol 1367. Springer, Singapore. https://doi.org/10.1007/978-981-16-0401-0_27

Download citation

  • DOI: https://doi.org/10.1007/978-981-16-0401-0_27

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-16-0400-3

  • Online ISBN: 978-981-16-0401-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation