Skip to main content
SpringerLink
Log in

Movie Keyword Search Using Large-Scale Language Model with User-Generated Rankings and Reviews

  • Conference paper
  • First Online:
Information Integration and Web Intelligence (iiWAS 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14416))

Abstract

The paper proposes a novel method for conducting keyword-based movie searches using user-generated rankings and reviews, by utilizing the BERT language model for task-specific fine-tuning. The model was trained on paired titles and reviews, enabling it to predict the likelihood of a movie appearing in a ranking that includes a particular keyword. An experiment using data from a reputable Japanese movie review site demonstrated that the method outperformed existing similarity-based approaches. However, some aspects, such as pooling methods, could be improved for accuracy.

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 69.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 89.99
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

Notes

  1. 1.

    Kurohashi Lab. Kyoto University: https://nlp.ist.i.kyoto-u.ac.jp/EN/.

  2. 2.

    MeCab: Yet Another Part-of-Speech and Morphological Analyzer: https://taku910.github.io/mecab/.

  3. 3.

    mecab-ipadic-NEologd: Neologism dictionary for MeCab https://github.com/neologd/mecab-ipadic-neologd.

References

  1. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL 2019, pp. 4171–4186 (2019)

    Google Scholar 

  2. Karmaker Santu, S.K., Sondhi, P., Zhai, C.: On application of learning to rank for e-commerce search. In: Proceedings of SIGIR 2017, pp. 475–484 (2017)

    Google Scholar 

  3. Kurihara, K., Shoji, Y., Fujita, S., Dürst, M.J.: Learning to rank-based approach for movie search by keyword query and example query. In: Proceedings of iiWAS 2021, pp. 137–145 (2021)

    Google Scholar 

  4. Liu, T.Y.: Learning to rank for information retrieval. Found. Trends Inf. Retr. 3, 225–331 (2009)

    Article  Google Scholar 

  5. Ramanand, J., Bhavsar, K., Pedanekar, N.: Wishful thinking - finding suggestions and ’buy’ wishes from product reviews. In: Proceedings of NAACL 2010, pp. 54–61 (2010)

    Google Scholar 

  6. Shao, Y., et al.: BERT-PLI: modeling paragraph-level interactions for legal case retrieval. In: IJCAI, pp. 3501–3507 (2020)

    Google Scholar 

  7. Soleimani, A., Monz, C., Worring, M.: Bert for evidence retrieval and claim verification. In: Proceedings of ECIR2020, pp. 359–366 (2020)

    Google Scholar 

  8. Yang, W., Zhang, H., Lin, J.: Simple applications of bert for ad hoc document retrieval. arXiv preprint arXiv:1903.10972 (2019)

  9. Yu, L., Hermann, K., Blunsom, P., Pulman, S.: Deep learning for answer sentence selection. In: Proceedings of NIPS 2014 (2014)

    Google Scholar 

Download references

Acknowledgments

This work was supported by JSPS KAKENHI Grants Numbers 21H03775, 21H03774, and 22H03905.

Author information

Authors and Affiliations

  1. Aoyama Gakuin University, Sagamihara, Kanagawa, 252 -5258, Japan

    Tensho Miyashita, Yoshiyuki Shoji & Martin J. Dürst

  2. Shizuoka University, Hamamatsu, Shizuoka, 432–8011, Japan

    Yoshiyuki Shoji

  3. Yahoo Japan Corporation, Chiyoda, Tokyo, 102–8282, Japan

    Sumio Fujita

Authors
  1. Tensho Miyashita
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yoshiyuki Shoji
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sumio Fujita
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Martin J. Dürst
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yoshiyuki Shoji .

Editor information

Editors and Affiliations

  1. Monash University, Melbourne, VIC, Australia

    Pari Delir Haghighi

  2. La Trobe University, Melbourne, VIC, Australia

    Eric Pardede

  3. University of Auckland, Auckland, New Zealand

    Gillian Dobbie

  4. University of Auckland, Auckland, New Zealand

    Vithya Yogarajan

  5. Udayana University, Denpasar, Indonesia

    Ngurah Agus Sanjaya ER

  6. Johannes Kepler University Linz, Linz, Austria

    Gabriele Kotsis

  7. Johannes Kepler University Linz, Linz, Austria

    Ismail Khalil

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Miyashita, T., Shoji, Y., Fujita, S., Dürst, M.J. (2023). Movie Keyword Search Using Large-Scale Language Model with User-Generated Rankings and Reviews. In: Delir Haghighi, P., et al. Information Integration and Web Intelligence. iiWAS 2023. Lecture Notes in Computer Science, vol 14416. Springer, Cham. https://doi.org/10.1007/978-3-031-48316-5_25

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-48316-5_25

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-48315-8

  • Online ISBN: 978-3-031-48316-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation