Suggestion Key Phrase Extraction: A Fine-Grained Suggestion Mining from Opinion Reviews
Keywords:
Token classification, Suggestion Mining, Key Phrase Extraction, Sentiment Analysis, Natural Language ProcessingAbstract
The abundance of online opinion reviews provides a valuable insight for understanding customer references and improving products and services. However, extracting fine-grained suggestions from these reviews remains a challenging task. In this paper, we propose a novel token classification model based on Transformer architecture for suggestion key phrase extraction. We formulate suggestion key phrase extraction as a sequence labeling task and fine-tune a pre-trained Transformer model. By applying token classification, the model is trained to assign a label to each token in the review indicating whether it represents a suggestion key phrase or not. This fine-tuning process enables the model to learn the intricate relationships between words and their contextual cues, facilitating the effective identification of relevant suggestions. To evaluate the effectiveness of the Token classification approach, we constructed a dataset consisting of opinion reviews from various domains. We annotated the dataset with suggestion key phrases to serve as ground truth for training and evaluation. We employed state-of-the-art token classification models, such as BERT or DeBERTa of various sizes, and fine-tuned them on our annotated dataset. Experimental results demonstrate that the Token classification approach outperforms traditional methods for suggestion key phrase extraction. The findings of this research have several practical implications for businesses and organizations. By automatically extracting suggestion key phrases from opinion reviews, companies can gain valuable insights into customer preferences and expectations. These insights can be used to enhance product development, improve customer satisfaction, and optimize marketing strategies.
Downloads
References
S. Negi and P. Buitelaar, “Towards the extraction of customer-to-customer suggestions from reviews,” Association for Computational Linguistics, 2015. doi: 10.18653/v1/d15-1258.
S. Negi, M. de Rijke, and P. Buitelaar, “Open Domain Suggestion Mining: Problem Definition and Datasets,” Jun. 2018, [Online]. Available: http://arxiv.org/abs/1806.02179
N. K. Laskari and S. K. Sanampudi, “A SYSTEMATIC STUDY ON SUGGESTION MINING FROM OPINION REVIEWS,” Journal of Theoretical and Applied Information Technology, vol. 100, no. 20. Little Lion Scientific, pp. 6061–6072, Oct. 31, 2022.
S. Negi, K. Asooja, S. Mehrotra, and P. Buitelaar, “A Study of Suggestions in Opinionated Texts and their Automatic Detection.” [Online]. Available: https://feedly.uservoice.com/forums/192636-
“2019 - SemEval-2019 Task 9 Suggestion Mining from Online Reviews and Forums”.
J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, vol. 1, no. Mlm, pp. 4171–4186, 2019.
P. He, X. Liu, J. Gao, and W. Chen, “DeBERTa: Decoding-enhanced BERT with Disentangled Attention,” Jun. 2020, [Online]. Available: http://arxiv.org/abs/2006.03654
N. Jindal and B. Liu, “Review spam detection,” in Proceedings of the 16th international conference on World Wide Web - WWW ’07, 2007. doi: 10.1145/1242572.1242759.
N. K. Laskari and S. K. Sanampudi, “Aspect Based Sentiment Analysis Survey,” vol. 18, no. 2, pp. 24–28, doi: 10.9790/0661-18212428.
A. Viswanathan, P. Venkatesh, B. Vasudevan, R. Balakrishnan, and L. Shastri, “Suggestion mining from customer reviews,” 17th Americas Conference on Information Systems 2011, AMCIS 2011, vol. 2, pp. 1351–1359, 2011.
S. Negi and P. Buitelaar, “Inducing Distant Supervision in Suggestion Mining through Part-of-Speech Embeddings,” Sep. 2017, [Online]. Available: http://arxiv.org/abs/1709.07403
T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” 1st International Conference on Learning Representations, ICLR 2013 - Workshop Track Proceedings, pp. 1–12, 2013.
T. Mikolov, I. Sutskever, K. Chen, G. Corrado, and J. Dean, “Distributed representations ofwords and phrases and their compositionality,” Adv Neural Inf Process Syst, pp. 1–9, 2013.
J. Pennington, R. Socher, and C. D. Manning, “GloVe: Global Vectors for Word Representation.” Accessed: Jun. 27, 2020. [Online]. Available: http://nlp.
“2019 - Yimmon at SemEval-2019 Task 9 Suggestion Mining with Hybrid”.
M. Yamamoto and T. Sekiya, “m y at SemEval-2019 Task 9: Exploring BERT for Suggestion Mining.” [Online]. Available: https://competitions.codalab.org/competitions/19955
R. Alexandros Potamias, A. Neofytou, and G. Siolas, “NTUA-ISLab at SemEval-2019 Task 9: Mining Suggestions in the wild.” [Online]. Available: https://www.tripadvisor.com.gr/
“2019 - MIDAS at SemEval-2019 Task 9 Suggestion Mining from Online Reviews”.
S. Pecar, M. Simko, and M. Bielikova, “NL-FIIT at SemEval-2019 Task 9: Neural Model Ensemble for Suggestion Mining,” Apr. 2019, [Online]. Available: http://arxiv.org/abs/1904.02981
C. Park et al., “ThisIsCompetition at SemEval-2019 Task 9: BERT is unstable for out-of-domain samples,” Apr. 2019, [Online]. Available: http://arxiv.org/abs/1904.03339
J. Liu, S. Wang, and Y. Sun, “OleNet at SemEval-2019 Task 9: BERT based Multi-Perspective Models for Suggestion Mining.”
M. Klimaszewski and P. Andruszkiewicz, “WUT at SemEval-2019 Task 9: Domain-Adversarial Neural Networks for Domain Adaptation in Suggestion Mining.”
S. Prasanna and S. A. Seelan, “Zoho at SemEval-2019 Task 9: Semi-supervised Domain Adaptation using Tri-training for Suggestion Mining,” Feb. 2019, [Online]. Available: http://arxiv.org/abs/1902.10623
P. Yue, J. Wang, and X. Zhang, “YNU-HPCC at SemEval-2019 Task 9: Using a BERT and CNN-BiLSTM-GRU Model for Suggestion Mining.”
N. K. Laskari and S. K. Sanampudi, “a Systematic Study on Suggestion Mining From Opinion Reviews,” J Theor Appl Inf Technol, vol. 100, no. 20, pp. 6061–6072, 2022.
N. K. Laskari and S. K. Sanampudi, “Explainable System for Suggestion Mining using attention,” pp. 679–684, 2022, doi: 10.1109/icaccs54159.2022.9785102.
N. K. Laskari and S. K. Sanampudi, “Weighted Focal Loss Function for Evaluating Effectiveness of Word Embeddings on Suggestion Mining from Opinion Reviews,” vol. 18, no. 6, pp. 1464–1483, 2021.
M. Jain, M. Leekha, and M. Goswami, A Multi-Task Approach to Open Domain Suggestion Mining (Student Abstract, vol. 1. Springer International Publishing, 2020. doi: 10.1609/aaai.v34i10.7180.
N. K. Laskari and S. K. Sanampudi, “ASPECT-ORIENTED SUGGESTION MINING FROM OPINION REVIEWS,” J Theor Appl Inf Technol, vol. 30, no. 12, 2023, [Online]. Available: www.mouthshut.com
A. Vaswani et al., “Attention Is All You Need,” Jun. 2017, [Online]. Available: http://arxiv.org/abs/1706.03762
J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, vol. 1, no. Mlm, pp. 4171–4186, 2019.
M, S. ., A, B. ., R, R. ., Patil, H. Y. ., R, D., A, K. ., Andrews, A. M. ., & Nagpal, A. . (2023). Dual-Level Secured Autonomous Bank Locker System. International Journal on Recent and Innovation Trends in Computing and Communication, 11(4), 269–277. https://doi.org/10.17762/ijritcc.v11i4.6452
Martínez, L., Milić, M., Popova, E., Smit, S., & Goldberg, R. Machine Learning Approaches for Human Activity Recognition. Kuwait Journal of Machine Learning, 1(4). Retrieved from http://kuwaitjournals.com/index.php/kjml/article/view/146
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
