Abstract
Most item shopping websites currently provide social network services (SNS) to collect their users’ opinions on items available for purchasing. This information is often used to reduce information overload and improve both the efficiency of the marketing process and user’s experience by means of user-modeling and hyper-personalization of contents. Whereas a variety of recommendation systems focus almost exclusively on ranking the items, we intend to extend this basic approach by predicting the sets of words that users would use should they express their opinions and interests on items not yet reviewed. To this end, we pay careful attention to the internal consistency of our model by relying on well-known facts of linguistic analysis, collaborative filtering techniques and matrix factorization methods. Still at an early stage of development, we discuss some encouraging results and open challenges of this new approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
From now on, we will use the opinion and review terms without distinction whenever we refer to the text (or a representative part of it) that a user writes about a product.
- 2.
We work with opinion-words provided by a natural language analysis tool. Terms may be compositions of several words.
- 3.
- 4.
- 5.
We use 20 executors with 8 cores and 16 GB RAM on a Hadoop cluster with a total of 695 GB RAM, 336 cores, and 2 TB HDFS. Our implemented algorithms are easily scalable, so any RAM limitation might be solved using a cluster with a sufficiently large number of nodes.
- 6.
It is part of the MLlib Apache’s Library.
- 7.
Apache Spark’s scalable machine learning library.
References
Almashraee, M., Monett Díaz, D., Paschke, A.: Emotion level sentiment analysis: the affective opinion evaluation. In: Joint Proceedings of the 2th Workshop on Emotions, Modality, Sentiment Analysis and the Semantic Web and the 1st International Workshop on Extraction and Processing of Rich Semantics from Medical Texts Co-located with ESWC 2016, Heraklion, Greece, 29 May (2016)
Benjamins, R., Cadenas, D., Alonso, P., Valderrabanos, A., Gomez, J.: The voice of the customer for digital telcos. In: Proceedings of the Industry Track at the International Semantic Web Conference (2014)
Bennet, J., Lanning, S.: The netflix prize. In: KDD Cup and Workshop (2007)
Cami Bagher, R., Hassanpour, H., Mashayekhi, H.: User trends modeling for a content-based recommender system. Expert Syst. Appl. 87, 209–219 (2017). ISSN 0957–4174
Diao, Q., Qiu, M., Wu, C.Y., Smola, A.J., Jiang, J., Wang, C.G: Jointly modeling aspects, ratings and sentiments for movie recommendation (JMARS). In: KDD 2014, pp. 193–202. https://doi.org/10.1145/2623330.2623758
Ekstrand, M.D., Riedl, J.T., Konstan, J.A.: Collaborative filtering recommender systems. Found. Trends Hum.-Comput. Interact. 4, 81–173 (2012)
Feltoni Gurini, D., Gasparetti, F., Micarelli, A., Sansonetti, G.: A sentiment-based approach to Twitter user recommendation. In: Proceedings of the International ACM Recommendation Systems Conference, RecSys (2013)
Ganu, G., Elhadad, N., Marian, A.: Beyond the stars: improving rating predictions using review text content. In: WebDB (2009)
García-Cuesta, E., Gómez-Vergel, D., Gracia-Expósito, L., Vela-Pérez, M.: Prediction of user opinion for products - a bag of words and collaborative filtering based approach. In: Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods ICPRAM 2017, pp. 233–238. Science and Technology Publications (2017)
Guy, I., Zwerdling, N., Ronen, I., Carmel, D., Uziel, E.: Social media recommendation based on people and tags. In: Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2010), pp. 194–201. ACM, New York (2010)
Hu, Y., Koren, Y., Volinsky, C.: Collaborative filtering for implicit feedback datasets. In: 8th IEEE International Conference on Data Mining, IDCM 2008, Pisa, Italy, pp. 263–272 (2008)
Hu, X., Tang, J., Gao, H., Liu, H.: Unsupervised sentiment analysis with emotional signals. In: WWW 2013, pp. 607–618. https://doi.org/10.1145/2488388.2488442
Koren, Y., Bell, R., Volinsky, C.: Matrix factorization techniques for recommender systems. J. Comput. 42, 30–37 (2009)
Ling, G., Lyu, M.R., King, I.: Ratings meet reviews, a combined approach to recommend. In: RecSys, vol. 14, pp. 105–112 (2014) https://doi.org/10.1145/2645710.2645728
B. Liu, Sentiment Analysis: Mining Opinions, Sentiments, and Emotions. Cambridge University Press, Cambridge (2015)
Shan, L., Dong, Y., Chai, J.: Research of personalized news recommendation system based on hybrid collaborative filtering algorithm. In: 2016 2nd IEEE International Conference on Computer and Communications (ICCC). IEEE (2016)
Lops, P., de Gemmis, M., Semeraro, G.: Content-based recommender systems: state of the art and trends. In: Ricci, F., Rokach, L., Shapira, B., Kantor, P.B. (eds.) Recommender Systems Handbook, pp. 73–105. Springer, Boston (2011). https://doi.org/10.1007/978-0-387-85820-3_3
Luo, X., Zhou, M., Shang, M., Li, S., Xia, Y.: A novel approach to extracting non-negative latent factors from non-negative big sparse matrices. IEEE Access 4, 2649–2655 (2016)
Luo, X., Zhou, M., Shang, M., Li, S., You, Z., Xia, Y., Zhu, Q.: A nonnegative latent factor model for large-scale sparse matrices in recommender systems via alternating direction method. IEEE Trans. Neural Netw. Learn. Syst. 27(3), 579–592 (2015). https://doi.org/10.1109/TNNLS.2015.2415257
McAuley, J., Leskovec, J.: From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews. In: WWW (2013)
McAuley, J., Leskovec, J.: Hidden factors and hidden topics: understanding rating dimension with review text. In: Proceedings of the 7th ACM Conference on Recommender Systems, RecSys (2013)
McAuley, J., Leskovec, J., Jurafsky, D.: Learning attitudes and attributes from multi-aspect reviews. In: ICDM (2012)
McAuley, J., Pandey, R., Leskovec, J.: Inferring networks of substitutable and complementary products. In: Knowledge Discovery and Data Mining (2015)
Pilászy, I., Zibriczky, D., Tikk, D.: Fast ALS-based matrix factorization for explicit and implicit feedback datasets. In: Proceedings of the 4th ACM Conference on Recommender Systems, pp. 71–78. ACM (2010)
Schafer, J.B., Frankowski, D., Herlocker, J., Sen, S.: Collaborative filtering recommender systems. In: Brusilovsky, P., Kobsa, A., Nejdl, W. (eds.) The Adaptive Web. LNCS, vol. 4321, pp. 291–324. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-72079-9_9
Sharma, A., Cosley, D.: Do social explanations work? Studying and modeling the effects of social explanations in recommender systems. In: WWW (2013)
Titov, I., McDonald, R.: A joint model of text and aspect ratings for sentiment summarization. In: ACL (2008)
Wang, H., Lu, Y., Zhai, C.: Latent aspect rating analysis on review text data: a rating regression approach. In: KDD (2010)
Webb, G.I., Pazzani, M.J., Billsus, D.: Machine learning for user modeling. User Model. User Adap. Interact. 11, 19–20 (2001)
Wyllys, R.E.: Empirical and theoretical bases of Zipf’s law. Libr. Trends 30(1), 53–64 (1981)
Zhang, W., Wang, J.: Integrating topic and latent factors for scalable personalized review-based rating prediction. IEEE Trans. Knowl. Data Eng. 28(11), 3013–3027 (2016). https://doi.org/10.1109/TKDE.2016.2598740
Zipf, G.K.: Human Behaviour and the Principle of Least Effort. Addison-Wesley, Reading (1949)
Acknowledgements
The authors want to thank Bitext (http://bitext.com) for providing NLP services for research. They also acknowledge the support of the Universidad Europea de Madrid through the E-Modelo research project. Special thanks to Hugo Ferrando for developing a significant part of the code used for experimentation, and to Javier García-Blas for their insightful comments. This work has been partially supported by the Spanish7 Ministry of Economy and Competitiveness through the MTM2014-57158-R project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
García-Cuesta, E., Gómez-Vergel, D., Gracia-Expósito, L., López-López, J.M., Vela-Pérez, M. (2018). Prediction of User Interest by Predicting Product Text Reviews. In: De Marsico, M., di Baja, G., Fred, A. (eds) Pattern Recognition Applications and Methods. ICPRAM 2017. Lecture Notes in Computer Science(), vol 10857. Springer, Cham. https://doi.org/10.1007/978-3-319-93647-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-93647-5_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-93646-8
Online ISBN: 978-3-319-93647-5
eBook Packages: Computer ScienceComputer Science (R0)