A Hybrid CNN-Based Review Helpfulness Filtering Model for Improving E-Commerce Recommendation Service
Source abstract
Abstract
As the e-commerce market grows worldwide, personalized recommendation services have become essential to users’ personalized items or services. They can decrease the cost of user information exploration and have a positive impact on corporate sales growth. Recently, many studies have been actively conducted using reviews written by users to address traditional recommender system research problems. However, reviews can include content that is not conducive to purchasing decisions, such as advertising, false reviews, or fake reviews. Using such reviews to provide recommendation services can lower the recommendation performance as well as a trust in the company. This study proposes a novel review of the helpfulness-based recommendation methodology (RHRM) framework to support users’ purchasing decisions in personalized recommendation services. The core of our framework is a review semantics extractor and a user/item recommendation generator. The review semantics extractor learns reviews representations in a convolutional neural network and bidirectional long short-term memory hybrid neural network for review helpfulness classification. The user/item recommendation generator models the user’s preference on items based on their past interactions. Here, past interactions indicate only records in which the user-written reviews of items are helpful. Since many reviews do not have helpfulness scores, we first propose a helpfulness classification model to reflect the review helpfulness that significantly impacts users’ purchasing decisions in personalized recommendation services. The helpfulness classification model is trained about limited reviews utilizing helpfulness scores. Several experiments with the Amazon dataset show that if review helpfulness information is used in the recommender system, performance such as the accuracy of personalized recommendation service can be further improved, thereby enhancing user satisfaction and further increasing trust in the company.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Recommender Systems and Techniques · Sentiment Analysis and Opinion Mining · Digital Marketing and Social Media
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Big Data Analytics, Kyung Hee University, 26, Kyungheedae-ro, Dongdaemun-gu, Seoul 02447, Korea
School of Management, Kyung Hee University, 26, Kyungheedae-ro, Dongdaemun-gu, Seoul 02447, Korea
Funding
National Research Foundation of Korea
References (69)
Show source-provided references
1. Recommender system application developments: A survey10.1016/j.dss.2015.03.008 ↗
2. Recommender systems survey10.1016/j.knosys.2013.03.012 ↗
3. Das, A.S., Datar, M., Garg, A., and Rajaram, S. (2007, January 8–12). Google news personalization: Scalable online collaborative filtering. Proceedings of the 16th International Conference on World Wide Web, Banff, AB, Canada.10.1145/1242572.1242610 ↗
4. Amazon.com recommendations: Item-to-item collaborative filtering10.1109/MIC.2003.1167344 ↗
5. Bennett, J., and Lanning, S. (2007, January 12). The netflix prize. Proceedings of the KDD Cup and Workshop, San Jose, CA, USA.
6. How do recommender systems affect sales diversity? A cross-category investigation via randomized field experiment10.1287/isre.2018.0800 ↗
7. Kim, J., Choi, I., and Li, Q. (2021). Customer satisfaction of recommender system: Examining accuracy and diversity in several types of recommendation approaches. Sustainability, 13.10.3390/su13116165 ↗
8. Customer-driven content recommendation over a network of customers10.1109/TSMCA.2011.2147306 ↗
9. A hybrid online-product recommendation system: Combining implicit rating-based collaborative filtering and sequential pattern analysis10.1016/j.elerap.2012.02.004 ↗
10. A literature review and classification of recommender systems research10.1016/j.eswa.2012.02.038 ↗
11. Personalized recommendation over a customer network for ubiquitous shopping10.1109/TSC.2009.7 ↗
12. Ricci, F., Rokach, L., and Shapira, B. (2011). Introduction to recommender systems handbook. Recommender Systems Handbook, Springer.10.1007/978-0-387-85820-3 ↗
13. A multi-theoretical kernel-based approach to social network-based recommendation10.1016/j.dss.2014.05.006 ↗
14. Aspect-based latent factor model by integrating ratings and reviews for recommender system10.1016/j.knosys.2016.07.033 ↗
15. Attitude predictability and helpfulness in online reviews: The role of explained actions and reactions10.1093/jcr/ucv003 ↗
16. Srifi, M., Oussous, A., Ait Lahcen, A., and Mouline, S. (2020). Recommender systems based on collaborative filtering using review texts—A survey. Information, 11.10.3390/info11060317 ↗
17. Helpfulness-aware review based neural recommendation10.1007/s42486-019-00023-0 ↗
18. Opinion mining from online hotel reviews–a text summarization approach10.1016/j.ipm.2016.12.002 ↗
19. Exploring reviews and review sequences on e-commerce platform: A study of helpful reviews on Amazon. in10.1016/j.jretconser.2018.08.002 ↗
20. An expert system for extracting knowledge from customers’ reviews: The case of amazon. com, inc10.1016/j.eswa.2017.05.008 ↗
21. Application of diversity of recommender system according to user preference change
22. A hybrid recommender system using artificial neural networks10.1016/j.eswa.2017.04.046 ↗
23. Commenders: A recommendation procedure for online book communities10.1016/j.elerap.2011.03.002 ↗
24. A hybrid collaborative filtering-based product recommender system using search keywords
25. A survey of collaborative filtering techniques10.1155/2009/421425 ↗
26. Al-Bashiri, H., Abdulgabber, M.A., Romli, A., and Kahtan, H. (2018). An improved memory-based collaborative filtering method based on the TOPSIS technique. PLoS ONE, 13.10.1371/journal.pone.0204434 ↗
27. A survey of active learning in collaborative filtering recommender systems10.1016/j.cosrev.2016.05.002 ↗
28. Breese, J.S., Heckerman, D., and Kadie, C. (1998, January 24–26). Empirical analysis of predictive algorithms for collaborative filtering. Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, San Francisco, CA, USA.
29. Recommendation systems: Principles, methods and evaluation10.1016/j.eij.2015.06.005 ↗
30. TV Program recommender system using viewing time patterns
31. Guy, I., Mejer, A., Nus, A., and Raiber, F. (2017, January 3–7). Extracting and ranking travel tips from user-generated reviews. Proceedings of the 26th International Conference on World Wide Web, Perth, Australia.10.1145/3038912.3052632 ↗
32. Leung, C.W., Chan, S.C., and Chung, F.-l. (September, January 28). Integrating collaborative filtering and sentiment analysis: A rating inference approach. Proceedings of the ECAI 2006 Workshop on Recommender Systems, Riva del Garda, Italy.
33. Pessimists and optimists: Improving collaborative filtering through sentiment analysis10.1016/j.eswa.2013.06.049 ↗
34. Zhang, Z., Zhang, D., and Lai, J. (2014, January 7–9). urCF: User review enhanced collaborative filtering. Proceedings of the 20th Americas Conference on Information Systems, Savannah, GA, USA.
35. Ontology-supported polarity mining10.1002/asi.20735 ↗
36. A collaborative filtering system combined with users’ review mining: Application to the recommendation of smartphone apps
37. How to improve the accuracy of recommendation systems: Combining ratings and review texts sentiment scores
38. Cheng, Z., Ding, Y., Zhu, L., and Kankanhalli, M. (2018, January 23–27). Aspect-aware latent factor model: Rating prediction with ratings and reviews. Proceedings of the 2018 World Wide Web Conference, Lyon, France.10.1145/3178876.3186145 ↗
39. Scalable multi-channel dilated CNN–BiLSTM model with attention mechanism for Chinese textual sentiment analysis10.1016/j.future.2021.01.024 ↗
40. Attention-based BiLSTM fused CNN with gating mechanism model for Chinese long text classification10.1016/j.csl.2020.101182 ↗
41. Deep neural network architecture for sentiment analysis and emotion identification of Twitter messages10.1007/s11042-018-6168-1 ↗
42. P-CNN: Enhancing text matching with positional convolutional neural network10.1016/j.knosys.2019.01.028 ↗
43. Deep learning-based sentiment classification of evaluative text based on Multi-feature fusion10.1016/j.ipm.2019.02.018 ↗
44. LSTM with sentence representations for document-level sentiment classification10.1016/j.neucom.2018.04.045 ↗
45. Hassan, A., and Mahmood, A. (2017, January 18–21). Efficient deep learning model for text classification based on recurrent and convolutional layers. Proceedings of the 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), Cancun, Mexico.10.1109/ICMLA.2017.00009 ↗
46. Convolutional recurrent deep learning model for sentence classification10.1109/ACCESS.2018.2814818 ↗
47. Bidirectional LSTM with attention mechanism and convolutional layer for text classification10.1016/j.neucom.2019.01.078 ↗
48. Semantic-emotion neural network for emotion recognition from text10.1109/ACCESS.2019.2934529 ↗
49. A hybrid bidirectional recurrent convolutional neural network attention-based model for text classification10.1109/ACCESS.2019.2932619 ↗
50. A new method of emotional analysis based on CNN–BiLSTM hybrid neural network10.1007/s10586-020-03055-9 ↗
51. A CNN-BiLSTM based deep learning model for mid-term solar radiation prediction
52. Jang, B., Kim, M., Harerimana, G., Kang, S.-u., and Kim, J.W. (2020). Bi-LSTM model to increase accuracy in text classification: Combining Word2vec CNN and attention mechanism. Appl. Sci., 10.10.3390/app10175841 ↗
53. A CNN-BiLSTM model for document-level sentiment analysis10.3390/make1030048 ↗
54. A review semantics based model for rating prediction10.1109/ACCESS.2019.2962075 ↗
55. Helpfulness of online consumer reviews: A multi-perspective approach10.1016/j.ipm.2021.102538 ↗
56. Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN10.1016/j.eswa.2016.10.065 ↗
57. Kim, Y. (2014, January 25–29). Convolutional neural networks for sentence classification. Proceedings of the EMNLP, Doha, Qatar.10.3115/v1/D14-1181 ↗
58. Ekstrand, M.D., Riedl, J.T., and Konstan, J.A. (2011). Collaborative Filtering Recommender Systems, Now Publishers Inc.10.1561/9781601984432 ↗
59. Evaluating collaborative filtering recommender systems10.1145/963770.963772 ↗
60. He, X., Liao, L., Zhang, H., Nie, L., Hu, X., and Chua, T.-S. (, January 3–7). Neural collaborative filtering. Proceedings of the 26th International Conference on World Wide Web, Perth, Australia.
61. Deep learning based recommender system: A survey and new perspectives10.1145/3158369 ↗
62. He, R., and McAuley, J. (2016, January 11–15). Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. Proceedings of the 25th International Conference on World Wide Web, Montreal, QC, Canada.10.1145/2872427.2883037 ↗
63. McAuley, J., Targett, C., Shi, Q., and Van Den Hengel, A. (2015, January 9–13). Image-based recommendations on styles and substitutes. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, Santiago, Chile.10.1145/2766462.2767755 ↗
64. Liu, Y., Huang, X., An, A., and Yu, X. (2008, January 15–19). Modeling and predicting the helpfulness of online reviews. Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, Pisa, Italy.10.1109/ICDM.2008.94 ↗
65. Park, S., and Woo, J. (2019). Gender classification using sentiment analysis and deep learning in a health web forum. Appl. Sci., 9.10.3390/app9061249 ↗
66. Social media contents based sentiment analysis and prediction system10.1016/j.eswa.2018.03.055 ↗
67. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
68. Sentiment analysis for E-commerce product reviews in Chinese based on sentiment lexicon and deep learning10.1109/ACCESS.2020.2969854 ↗
69. Detection of spam reviews: A sentiment analysis approach10.1007/s40012-018-0193-0 ↗