Lee H, Hae Rim C, Lee D, (2019), Learning to rank products based on online product reviews using a hierarchical deep neural network, Electronic Commerce Research and Applications, 36.
https://www.sciencedirect.com/science/article/pii/S1567422319300511
Mots clés : Classement des produits, Avis de produits en ligne, Réseau neuronal profond hiérarchique
Résumé : Le classement des produits basé sur les évaluations de produits en ligne consiste à déduire les préférences relatives des utilisateurs entre différents produits en tant que variante de l’analyse des sentiments au niveau de l’entité. Malgré la relation complexe entre la préférence globale de l’utilisateur et les opinions diverses et individuelles, les approches existantes utilisent généralement des hypothèses empiriques sur les caractéristiques de sentiment des produits d’intérêt. Dans cet article, nous proposons une nouvelle approche unifiée pour apprendre à classer les produits en fonction des critiques de produits en ligne. Contrairement aux approches existantes, il utilise des techniques d’apprentissage approfondi pour extraire la représentation de révision latente de haut niveau qui contient les informations les plus sémantiques dans le processus d’apprentissage. Pour cette approche, nous étendons le réseau d’attention hiérarchique récemment proposé pour opérer dans le domaine du classement. Ce réseau apprend de manière hiérarchique les représentations optimales des fonctionnalités des produits et leurs avis grâce à l’utilisation d’encodeurs à deux niveaux basés sur l’attention. Pour construire un modèle de classement plus avancé, plusieurs fonctionnalités ont été ajoutées pour donner suffisamment d’informations sur les préférences relatives des utilisateurs, et deux fonctions représentatives de perte de classement, RankNet et ListNet, ont été appliquées. De plus, nous démontrons que ce réseau surpasse les méthodes existantes de prédiction du classement des ventes sur la base des évaluations de produits en ligne.
Appel, O., Chiclana, F., Carter, J., Fujita, H., 2016. A hybrid approach to the sentiment
analysis problem at the sentence level. Knowl.-Based Syst. 108, 110–124. https://doi.
org/10.1016/j.knosys.2016.05.040.
Bahdanau, D., Cho, K., Bengio, Y., 2015. Neural machine translation by jointly learning to
align and translate. arXiv:1409.0473.
Bashir, S., Afzal, W., Baig, A.R., 2016. Opinion-based entity ranking using learning to
rank. Appl. Soft Comput. 38, 151–163. https://doi.org/10.1016/j.asoc.2015.10.001..
URL: http://www.sciencedirect.com/science/article/pii/S156849461500616X.
Bickart, B., Schindler, R.M., 2001. Internet forums as influential sources of consumer
information. J. Interactive Market. 15, 31–40. https://doi.org/10.1002/dir.1014..
URL: http://www.sciencedirect.com/science/article/pii/S1094996801701843.
Burges, C., Shaked, T., Renshaw, E., Lazier, A., Deeds, M., Hamilton, N., Hullender, G.,
- Learning to rank using gradient descent. In: Proceedings of the 22nd international conference on Machine Learning. New York, NY, USA, pp. 89–96. https://doi.
org/10.1145/1102351.1102363.
Cao, Z., Qin, T., Liu, T.Y., Tsai, M.F., Li, H., 2007. Learning to rank: From pairwise approach to listwise approach. In: Proceedings of the 24th International Conference on
Machine Learning. New York, NY, USA, pp. 129–136. https://doi.org/10.1145/
1273496.1273513.
Chen, T., Xu, R., He, Y., Wang, X., 2017. Improving sentiment analysis via sentence type
classification using bilstm-crf and cnn. Expert Syst. Appl. 72, 221–230. https://doi.
org/10.1016/j.eswa.2016.10.065.. URL: http://www.sciencedirect.com/science/
article/pii/S0957417416305929.
Cooijmans, T., Ballas, N., Laurent, C., Alar Gülehre, Courville, A., 2016. Recurrent batch
normalization. arXiv:1603.09025.
Decker, R., Trusov, M., 2010. Estimating aggregate consumer preferences from online
product reviews. Int. J. Res. Mark. 27https://doi.org/10.1016/j.ijresmar.2010.09.
001.. URL: http://www.sciencedirect.com/science/article/pii/
S0167811610000753.
Dellarocas, C., Zhang, X.M., Awad, N.F., 2007. Exploring the value of online product
reviews in forecasting sales: the case of motion pictures. J. Interactive Market. 21,
23–45. https://doi.org/10.1002/dir.20087.
Engonopoulos, N., Lazaridou, A., Paliouras, G., Chandrinos, K., 2011. Els: a word-level
method for entity-level sentiment analysis. In: Proceedings of the International
Conference on Web Intelligence, Mining and Semantics. ACM, New York, NY, USA.
https://doi.org/10.1145/1988688.1988703. pp. 12:1–12:9.
Fan, Z.P., Che, Y.J., Chen, Z.Y., 2017. Product sales forecasting using online reviews and
historical sales data: a method combining the bass model and sentiment analysis. J.
Business Res. 74, 90–100. https://doi.org/10.1016/j.jbusres.2017.01.010.. URL:
http://www.sciencedirect.com/science/article/pii/S0148296317300231.
Ganesan, K., Zhai, C., 2012. Opinion-based entity ranking. Inform. Retrieval 15, 116–150.
https://doi.org/10.1007/s10791-011-9174-8.
Gerani, S., Mehdad, Y., Carenini, G., Ng, R.T., Nejat, B., 2014. Abstractive summarization
of product reviews using discourse structure. In: Proceedings of the 2014 Conference
on Empirical Methods in Natural Language Processing (EMNLP). Association for
Computational, Linguistics, Doha, Qatar, pp. 1602–1613. URL: http://www.aclweb.
org/anthology/D14-1168.
He, R., McAuley, J., 2016. Ups and downs: Modeling the visual evolution of fashion
trends with one-class collaborative filtering. In: Proceedings of the 25th International
Conference on World Wide Web, International World Wide Web Conferences Steering
Committee, Republic and Canton of Geneva Switzerland, pp. 507–517. https://doi.
org/10.1145/2872427.2883037.
Hennig-Thurau, T., Gwinner, K.P., Walsh, G., Gremler, D.D., 2004. Electronic word-ofmouth via consumer-opinion platforms: what motivates consumers to articulate
themselves on the internet? J. Interactive Market. 18, 38–52. https://doi.org/10.
1002/dir.10073.. URL: http://www.sciencedirect.com/science/article/pii/
Table 5
Top 10 highly weighted tokens in the testing set for sampled categories.
Categories Top 10 tokens
Action Figures & Statues grandson, tattoo, tock, momma, equipped, pterodactyl, detachable, husky, grace
Camera & Photo portable, films, recycled, powerfull, film-, 5-pack, zoom, handycam, focus, spruce
Cell Phones console, pros-, oversized, evolutionary, maturity, realllly, clearance, excellent, snaps, resistant
Kitchen & Dining chalkboard, gauze, flex, Christian, gripping, shiny, terrier, wide, shipment, mistral
Skin Care embrace, gland, popularity, inspiration, highlight, boron, frizz, revise, 5 min, spot
H.-C. Lee, et al. Electronic Commerce Research and Applications 36 (2019) 100874
9
S1094996804700961.
Huang, Z., Xu, W., Yu, K., 2015. Bidirectional lstm-crf models for sequence tagging.
arXiv:1508.01991.
Jannach, D., Resnick, P., Tuzhilin, A., Zanker, M., 2016. Recommender systems — beyond
matrix completion. Commun. ACM 59, 94–102. https://doi.org/10.1145/2891406.
Jindal, N., Liu, B., 2006. Identifying comparative sentences in text documents. In:
Proceedings of the 29th Annual International ACM SIGIR Conference on Research
and Development in Information Retrieval. ACM, New York, NY, USA, pp. 244–251.
https://doi.org/10.1145/1148170.1148215.
Kessler, W., Kuhn, J., 2013. Detection of product comparisons – how far does an out-ofthe-box semantic role labeling system take you? In: Proceedings of the 2013
Conference on Empirical Methods in Natural Language Processing Association for
Computational Linguistics, Seattle, Washington, USA, pp. 1892–1897. URL: http://
www.aclweb.org/anthology/D13-1194.
Kim, Y., 2014. Convolutional neural networks for sentence classification. In: Proceedings
of the 2014 Conference on Empirical Methods in Natural Language Processing
(EMNLP). Association for Computational, Linguistics, Doha, Qatar, pp. 1746–1751.
URL: http://www.aclweb.org/anthology/D14-1181.
Kingma, D.P., Ba, J., 2014. Adam: a method for stochastic optimization. arXiv:1412.6980.
Liu, Q., Huang, H., Zhang, C., Chen, Z., Chen, J., 2013. Chinese comparative sentence
identification based on the combination of rules and statistics. In: International
Conference on Advanced Data Mining and Applicationspp. 300–310. https://doi.org/
10.1007/978-3-642-53917-6_27.
Liu, Y., 2006. Word of mouth for movies: its dynamics and impact on box office revenue.
J. Marketing 70, 74–89. https://doi.org/10.1509/jmkg.70.3.74.
Liu, Y., Bi, J.W., Fan, Z.P., 2017. Ranking products through online reviews: a method
based on sentiment analysis technique and intuitionistic fuzzy set theory. Inform.
Fusion 36, 149–161. https://doi.org/10.1016/j.inffus.2016.11.012.. URL: http://
www.sciencedirect.com/science/article/pii/S1566253516301580.
Liu, Y., Huang, X., An, A., Yu, X., 2007. Arsa: A sentiment-aware model for predicting
sales performance using blogs. In: Proceedings of the 30th Annual International ACM
SIGIR Conference on Research and Development in Information Retrieval. ACM, New
York, NY, USA, pp. 607–614. https://doi.org/10.1145/1277741.1277845.
Liu, Y., Huang, X., An, A., Yu, X., 2008. Modeling and predicting the helpfulness of online
reviews. In: 2008 Eighth IEEE International Conference on Data Mining, IEEE, pp.
443–452. https://doi.org/10.1109/ICDM.2008.94.. URL: https://ieeexplore.ieee.
org/abstract/document/4781139.
McAuley, J., Targett, C., Shi, Q., van den Hengel, A., 2015. Image-based recommendations on styles and substitutes. In: Proceedings of the 38th International ACM SIGIR
Conference on Research and Development in Information Retrieval. ACM, New York,
NY, USA, pp. 43–52. https://doi.org/10.1145/2766462.2767755.
Najmi, E., Hashmi, K., Malik, Z., Rezgui, A., Khan, H.U., 2015. Capra: a comprehensive
approach to product ranking using customer reviews. Computing 97, 843–867.
https://doi.org/10.1007/s00607-015-0439-8.
Raffel, C., Ellis, D.P.W., 2015. Feed-forward networks with attention can solve some longterm memory problems. arXiv:1512.08756.
Romeo, S., Da San Martino, G., Barrón-Cedeno, A., Moschitti, A., Belinkov, Y., Hsu, W.N.,
Zhang, Y., Mohtarami, M., Glass, J., 2016. Neural attention for learning to rank
questions in community question answering. In: Proceedings of COLING 2016, the
26th International Conference on Computational Linguistics: Technical Papers.
Association for Computational, Linguistics, New York, NY, USA, pp. 1734–1745.
URL: http://www.aclweb.org/anthology/C/C16/C16-1163.pdf.
Saumya, S., Singh, J.P., Baabdullah, A.M., Rana, N.P., Dwivedi, Y.K., 2018. Ranking
online consumer reviews. Electron. Commer. Res. Appl. 29, 78–89. https://doi.org/
10.1016/j.elerap.2018.03.008.. URL: http://www.sciencedirect.com/science/
article/pii/S1567422318300358.
Schneider, M.J., Gupta, S., 2016. Forecasting sales of new and existing products using
consumer reviews: A random projections approach. Int. J. Forecast. 32, 243–256.
https://doi.org/10.1016/j.ijforecast.2015.08.005.. URL: http://www.sciencedirect.
com/science/article/pii/S0169207015001235.
Song, Y., Wang, H., He, X., 2014. Adapting deep ranknet for personalized search. In:
Proceedings of the 7th ACM International Conference on Web Search and Data
Mining. ACM, New York, NY, USA, pp. 83–92. https://doi.org/10.1145/2556195.
2556234.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R., 2014. Dropout:
A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15,
1929–1958. URL: http://jmlr.org/papers/v15/srivastava14a.html.
Sun, J., Long, C., Zhu, X., Huang, M., 2009. Mining reviews for product comparison and
recommendation. In: Polibitspp. 33–40. https://doi.org/10.1145/1148170.1148215.
Varathan, K.D., Giachanou, A., Crestani, F., 2017. Comparative opinion mining: a review.
J. Assoc. Inform. Sci. Technol. 68, 811–829. https://doi.org/10.1002/asi.23716.
Wang, B., Klabjan, D., 2017. An attention-based deep net for learning to rank. arXiv:1702.
06106.
Wang, J., Zhao, W.X., He, Y., Li, X., 2015. Leveraging product adopter information from
online reviews for product recommendation. In: Ninth International AAAI Conference
on Web and Social Mediapp. 464–472. URL: https://www.aaai.org/ocs/index.php/
ICWSM/ICWSM15/paper/view/10475.
Wang, L., Ling, W., 2016. Neural network-based abstract generation for opinions and
arguments. arXiv:1606.02785.
Ward, C.B., Choi, Y., Skiena, S., Xavier, E.C., 2011. Empath: A framework for evaluating
entity-level sentiment analysis. In: 2011 8th International Conference Expo on
Emerging Technologies for a Smarter Worldpp. 1–6. https://doi.org/10.1109/
CEWIT.2011.6135866.
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y., - Show, attend and tell: Neural image caption generation with visual attention.
In: Bach, F., Blei, D. (Eds.), Proceedings of the 32nd International Conference on
Machine Learning, PMLR Lille, France, pp. 2048–2057.
Yagci, I.A., Das, S., 2014. Box office prediction based on microblog. Expert Syst. Appl. 41,
1680–1689. https://doi.org/10.1016/j.eswa.2013.08.065.
Yagci, I.A., Das, S., 2018. Measuring design-level information quality in online reviews.
Electron. Commer. Res. Appl. 30, 102–110. https://doi.org/10.1016/j.elerap.2018.
05.010.
Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., Hovy, E., 2016. Hierarchical attention
networks for document classification. In: Proceedings of the 2016 Conference of the
North American Chapter of the Association for Computational Linguistics: Human
Language Technologies Association for Computational Linguistics, San Diego,
California, pp. 1480–1489. URL: http://www.aclweb.org/anthology/N16-1174.
Yu, J., Zha, Z.J., Wang, M., Chua, T.S., 2011. Aspect ranking: Identifying important
product aspects from online consumer reviews. In: Proceedings of the 49th Annual
Meeting of the Association for Computational Linguistics: Human Language
Technologies, vol. 1. Association for Computational Linguistics, Stroudsburg, PA,
USA, pp. 607–614. URL: http://dl.acm.org/citation.cfm?id=2002472.2002654.
Zhang, K., Cheng, Y., Liao, W.K., Choudhary, A., 2011. Mining millions of reviews: A
technique to rank products based on importance of reviews. In: Proceedings of the
13th International Conference on Electronic Commerce. ACM, New York, NY, USA.
https://doi.org/10.1145/2378104.2378116. pp. 12:1–12:8.
Zhang, K., Narayanan, R., Choudhary, A., 2010. Voice of the customers: Mining online
customer reviews for product feature-based ranking. In: Proceedings of the 3rd
Wonference on Online Social Networks USENIX Association, Berkeley, CA, USA. pp.
11–11. URL: http://dl.acm.org/citation.cfm?id=1863190.1863201.
Zhang, Z., Guo, C., Goes, P., 2013. Product comparison networks for competitive analysis
of online word-of-mouth. ACM Trans. Manage Inf. Syst. 3, 20:1–20:22. https://doi.
org/10.1145/2407740.2407744.
Zheng, L., Noroozi, V., Yu, P.S., 2017. Joint deep modeling of users and items using
reviews for recommendation. In: Proceedings of the Tenth ACM International
Conference on Web Search and Data Mining. ACM, New York, NY, USA, pp. 425–434.
https://doi.org/10.1145/3018661.3018665.
Zhu, F., Zhang, X.M., 2010. Impact of online consumer reviews on sales: The moderating
role of product and consumer characteristics. J. Marketing 74, 133–148. https://doi.
org/10.1509/jmkg.74.2.133. DOI: 10.1509/jmkg.74.2.133.