AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
We propose a framework, which is titled “understanding users and items based on Rating-Boosted Latent Topics”, to integrate numerical ratings and textual reviews to model user preferences and item features better

Rating-Boosted Latent Topics: Understanding Users and Items with Ratings and Reviews.

IJCAI, pp.2640-2646, (2016)

Cited by: 118|Views71
EI
Full Text
Bibtex
Weibo

Abstract

The performance of a recommendation system relies heavily on the feedback of users. Most of the traditional recommendation algorithms based only on historical ratings will encounter several difficulties given the problem of data sparsity. Users' feedback usually contains rich textual reviews in addition to numerical ratings. In this paper...More

Code:

Data:

0
Introduction
  • The core of a recommendation system is a personalized algorithm for identifying the preference of users based on their feedback towards items [Bao and Zhang, 2014].
  • There has been significant work focusing on the proper modelling of user preferences and item features for recommendations based on ratings
  • Despite their success, there are still two key challenges affecting the recommendation performance of them.
  • ⇤Corresponding author are difficult to be interpreted because of the neglect of textual reviews, whose very purpose is for users to explain why they rated an item the way they did [McAuley and Leskovec, 2013]
  • These algorithms fail to make recommendations for users or items with few ratings because their preferences or features determined from limited information could be unreliable
Highlights
  • The core of a recommendation system is a personalized algorithm for identifying the preference of users based on their feedback towards items [Bao and Zhang, 2014]
  • There has been significant work focusing on the proper modelling of user preferences and item features for recommendations based on ratings
  • We propose a framework, which is titled “understanding users and items based on Rating-Boosted Latent Topics” (RBLT), to integrate numerical ratings and textual reviews to model user preferences and item features better
  • We extend user preference distribution and item feature distribution in Latent Factor Models model to two components: one modelled based on ratings and the other based on reviews
  • We proposed conducting “understanding users and items based on Rating-Boosted Latent Topics” (RBLT)
  • Our main contributions are: 1) we propose a rating-boosted approach to combine the features discussed in reviews with the sentiment orientations of users towards them; 2) we identify item recommendability distributions and user preference distributions in a shared topic space, which facilitates good recommendation performance and interpretability; 3) we propose a rating prediction model that exploits both ratings and textual reviews for recommendation
Results
  • Experimental results on

    26 real-world datasets from Amazon demonstrate that the approach significantly improves the rating prediction accuracy compared with various state-of-the-art models, such as LFM, HFT, CTR and RMR models.
  • The authors' method benefits much from reviews on top-N recommendation tasks
Conclusion
  • 4.1 Datasets and Experimental Settings

    To evaluate the performance of the model, the authors conducted the experiments on 26 Amazon datasets1 provided by McAuley et al in [McAuley and Leskovec, 2013].
  • Experimental results on 26 real-world datasets show that the model greatly improves the rating prediction accuracy compared with some state-of-the-art methods.
  • This is especially true for the “silent users” and “silent items”; and 4) by linking the ratings and the reviews, the authors gain great improvements on practical top-N recommendation task.
  • Capturing this inconsistency can help them adjust the understanding of users and items, and achieve better recommendations
Tables
  • Table1: Dataset description. The “silent users” in the last column are those users who have no more than 3 ratings
  • Table2: Experimental results of rating prediction. The improvements with * are significant with p-value < 0.05, and the improvements with ** are significant with p-value < 0.01. For there are no detailed results of CTR (c) and RMR (d) available, we do not conduct statistical tests on these two models
  • Table3: Top ten words of each topic discovered by RBLT from Cell Phones & Accessories. Each column is corresponding to a topic attached with an “interpretation” label
  • Table4: Top-N recommendation performance. (i) means dot product and (ii) means cosine similarity, here
Download tables as Excel
Related work
  • There has been significant amount of work focused on providing accurate recommendations based on the historical ratings [Pazzani and Billsus, 2007; Sarwar et al, 2001; Bell and Koren, 2007; Noh et al, 2004; Koren et al, 2009; Lops et al, 2011]. In recent years, however, with the continuous increase of product reviews published, more and more attention has been paid to how to use reviews to improve the performance of recommendation systems. Among these methods, the simultaneous use of ratings and reviews is a popular approach, which is referred to as semantic enhanced recommendation algorithms.

    Ganu et al attempt to extract aspect information (e.g., price) manually depending on abundant domain knowledge [Ganu et al, 2009]. The shortcomings of these types of approaches are that they require abundant domain knowledge and have high human cost; moreover, it is difficult to obtain a mass of feature information. Some work uses sentiment analysis methods to boost the performance of rating prediction automatically [Jakob et al, 2009; Leung et al, 2006; Zhang et al, 2014a; Zhang, 2015; Zhang et al, 2015]. However, these methods usually rely on the performance of natural language processing techniques and only two sentiment orientations (i.e., like and dislike) are taken into account. Some other work measures users/items similarities based on topic allocations extracted from reviews [Wang and Blei, 2011; Xu et al, 2012; Zheng et al, 2014]. However, they ignore user sentiment orientation in each review and are of high computation cost because of similarity calculation.
Funding
  • This work was supported by National Key Basic Research Program (2015CB358700), Natural Science Foundation (61532011, 61472206) of China and TsinghuaSamsung Joint Laboratory for Intelligent Media Computing
Reference
  • [Bao and Zhang, 2014] Yang Bao and Hui Fang Jie Zhang. Topicmf: Simultaneously exploiting ratings and reviews for recommendation. AAAI, pages 2–8, 2014.
    Google ScholarLocate open access versionFindings
  • [Bell and Koren, 2007] Robert M Bell and Yehuda Koren. Improved neighborhood-based collaborative filtering. KDD Cup and Workshop at the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2007.
    Google ScholarLocate open access versionFindings
  • [Blei et al., 2003] David M Blei, Andrew Y Ng, and Michael I Jordan. Latent dirichlet allocation. the Journal of machine Learning research, 3:993–1022, 2003.
    Google ScholarLocate open access versionFindings
  • [Cremonesi et al., 2010] Paolo Cremonesi, Yehuda Koren, and Roberto Turrin. Performance of recommender algorithms on top-n recommendation tasks. Proceedings of the fourth ACM conference on Recommender systems, pages 39–46, 2010.
    Google ScholarLocate open access versionFindings
  • [Ganu et al., 2009] Gayatree Ganu, Noemie Elhadad, and Amelie Marian. Beyond the stars: Improving rating predictions using review text content. WebDB, 2009.
    Google ScholarLocate open access versionFindings
  • [Jakob et al., 2009] Niklas Jakob, Stefan Hagen Weber, Mark Christoph Muller, and Iryna Gurevych. Beyond the stars: exploiting free-text user reviews to improve the accuracy of movie recommendations. Proceedings of the 1st international CIKM workshop on Topic-sentiment analysis for mass opinion, pages 57–64, 2009.
    Google ScholarLocate open access versionFindings
  • [Koren et al., 2009] Yehuda Koren, Robert Bell, and Chris Volinsky. Matrix factorization techniques for recommender systems. Computer, 42(8):30–37, 2009.
    Google ScholarLocate open access versionFindings
  • [Leung et al., 2006] Cane WK Leung, Stephen CF Chan, and Fu-lai Chung. Integrating collaborative filtering and sentiment analysis: A rating inference approach. Proceedings of The ECAI 2006 Workshop on Recommender Systems, pages 62–66, 2006.
    Google ScholarLocate open access versionFindings
  • [Ling et al., 2014] Guang Ling, Michael R Lyu, and Irwin King. Ratings meet reviews, a combined approach to recommend. pages 105–112. ACM, 2014.
    Google ScholarFindings
  • [Lops et al., 2011] Pasquale Lops, Marco De Gemmis, and Giovanni Semeraro. Content-based recommender systems: State of the art and trends. Recommender systems handbook, pages 73–105, 2011.
    Google ScholarLocate open access versionFindings
  • [McAuley and Leskovec, 2013] Julian McAuley and Jure Leskovec. Hidden factors and hidden topics: understanding rating dimensions with review text. Proceedings of the 7th ACM conference on Recommender systems, pages 165–172, 2013.
    Google ScholarLocate open access versionFindings
  • [Noh et al., 2004] Hyunju Noh, Minjung Kwak, and Ingoo Han. Improving the prediction performance of customer behavior through multiple imputation. Intelligent Data Analysis, 8(6):563–577, 2004.
    Google ScholarLocate open access versionFindings
  • [Pazzani and Billsus, 2007] Michael J Pazzani and Daniel Billsus. Content-based recommendation systems. The adaptive web, pages 325–341, 2007.
    Google ScholarLocate open access versionFindings
  • [Sarwar et al., 2001] Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. Item-based collaborative filtering recommendation algorithms. Proceedings of the 10th international conference on World Wide Web, pages 285– 295, 2001.
    Google ScholarLocate open access versionFindings
  • [Su and Khoshgoftaar, 2009] Xiaoyuan Su and Taghi M Khoshgoftaar. A survey of collaborative filtering techniques. Advances in artificial intelligence, 2009:4, 2009.
    Google ScholarLocate open access versionFindings
  • [Wang and Blei, 2011] Chong Wang and David M Blei. Collaborative topic modeling for recommending scientific articles. Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 448–456, 2011.
    Google ScholarLocate open access versionFindings
  • [Xu et al., 2012] Jingnan Xu, Xiaolin Zheng, and Weifeng Ding. Personalized recommendation based on reviews and ratings alleviating the sparsity problem of collaborative filtering. e-Business Engineering (ICEBE), 2012 IEEE Ninth International Conference on, pages 9–16, 2012.
    Google ScholarLocate open access versionFindings
  • [Zhang et al., 2014a] Yongfeng Zhang, M Zhang, Y Zhang, Y Liu, and S Ma. Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. Proc. of SIGIR, 14, 2014.
    Google ScholarLocate open access versionFindings
  • [Zhang et al., 2014b] Yongfeng Zhang, Min Zhang, Yi Zhang, Yiqun Liu, and Shaoping Ma. Understanding the sparsity: Augmented matrix factorization with sampled constraints on unobservables. Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, pages 1189–1198, 2014.
    Google ScholarLocate open access versionFindings
  • [Zhang et al., 2015] Yongfeng Zhang, Min Zhang, Yi Zhang, Guokun Lai, Yiqun Liu, Honghui Zhang, and Shaoping Ma. Daily-aware personalized recommendation based on feature-level time series analysis. In Proceedings of the 24th International Conference on World Wide Web, pages 1373–1383, 2015.
    Google ScholarLocate open access versionFindings
  • [Zhang, 2004] Tong Zhang. Solving large scale linear prediction problems using stochastic gradient descent algorithms. Proceedings of the twenty-first international conference on Machine learning, page 116, 2004.
    Google ScholarLocate open access versionFindings
  • [Zhang, 2015] Yongfeng Zhang. Incorporating phrase-level sentiment analysis on textual reviews for personalized recommendation. Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, pages 435–440, 2015.
    Google ScholarLocate open access versionFindings
  • [Zheng et al., 2014] Xiaolin Zheng, Weifeng Ding, Jingnan Xu, and Deren Chen. Personalized recommendation based on review topics. Service Oriented Computing and Applications, 8(1):15–31, 2014.
    Google ScholarLocate open access versionFindings
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科