SlideShare a Scribd company logo
Learning to Recommend with User
Generated Content
Yueshen Xu1, Zhiyuan Chen2, Jianwei Yin1, Zizheng
Wu1 and Taojun Yao1
1School of Computer Science and Technology, Zhejiang University
2University of Illinois at Chicago
xyshzjucs@zju.edu.cn; xyshzjucs@gmail.com
2015/6/9 1Zhejiang University
Junxiang Wang
Yueshen Xu, WAIM, 2015
Outline
 Background
 Introduction
 Related Work
 Recommendation with UGC in User Side
 Matrix Factorization
 Topic Analysis for Items through Topic Modeling
 User Interest Distribution
 User Topic Regularization
 Recommendation with UGC in Item Side
 Item Topic Regularization
 Experiment and Evaluation
 Reference
2015/6/9 2Zhejiang University
Keywords: Recommendation, User
Generated Content, Topic Modeling, Matrix
Factorization
Yueshen Xu, WAIM, 2015
Background
 Recommendation in General
 Collaborative Filtering (CF)
− Matrix Factorization (MF)
 Content-based approach
− Pandora music genome project
2015/6/9 3Zhejiang University
 User Generated Content (UGC)
 social tag, review, question answer, blog, tweet, etc
 tag-based / review-based recommendation
 Problems in existing works
 not every web site has all kinds of UGC
 the item-word / user-word space is highly sparse
 synonym & polysemy
 most works only focus on a single kind of UGC
item1 item2 item3 item4
user1 r11
user2 r22
user3
user4 r41 r44
user5 r53
Yueshen Xu, WAIM, 2015
Background
2015/6/9 4
 Other related work
 social / trust-based recommendation  helpful but limited
− no social relationship  Amazon, Ebay, Newegg, Jingdong,
Expedia, etc
− UGC √
 Description/Profile-based recommendation
− static content
− fail to distinguish different items
− unrelated to a user’s preference
 UGC, in contrast:
 emphasize an item’s features
− those words received frequently
 increase dynamically
 associated with a user’s preference / interested topics
− I like science fiction films, so I wrote a lot of movie reviews that contain
words like fiction, tech, super, hero, robotic, machine
 natural chunking (social tag)
Yueshen Xu, WAIM, 2015
Contribution
2015/6/9 5Zhejiang University
 Main contributions
 We study UGC in learning user interests and learning item features
 We propose a novel user-oriented collaborative filtering model and a
novel item-oriented collaborative filtering model
 We propose a way to utilize different types of UGC in a unified way in
recommender systems
 We expand an existing dataset by crawling new data, and conduct
sufficient experiments on three real-world datasets, which attest the
effectiveness of proposed models.
Yueshen Xu, WAIM, 2015
Recommendation with UGC in User
Side
2015/6/9 Zhejiang University 6
 Topic analysis for items through topic modeling
 Terms in UGC are combined together to compose the term set W
 each item owns an aggregated term list
 pLSA/LDA/HDP/nCRP/PAM: all are OK
 𝚯 = 𝜽𝒋 (𝜽𝒋 = 𝜃𝒋𝟏, 𝜃𝒋𝟐, … , 𝜃𝒋𝑲, ) is the topic/aspect distribution
of document j (i.e., item j)  what we need
 User Interest Distribution
 Cluster items into groups according to the similarity of their
topics (K-Means/GMM/K-Medoid: all are OK)
Yueshen Xu, WAIM, 2015
Recommendation with UGC in User
Side
2015/6/9 Zhejiang University 7
 User Interest Distribution (cont.)
 Intuition : find items with similar topics, although they are in
different categories: clothes, gadget, book, toy, DVD all about
Harry Potter
 Aggregate each user’s consumption records on each cluster 𝐶 𝑞
𝑆𝑖𝑚 𝑖, 𝑙 =
𝑃𝐶𝐶, 𝒄𝒐𝒔𝒊𝒏𝒆 𝑜𝑟 𝐾𝐿 𝑑𝑖𝑣𝑒𝑟𝑔𝑒𝑛𝑐𝑒
the weight of 𝑙 as one of user 𝑖’s
neighbors: 𝑒𝑖𝑙 𝑖, 𝑙 =
𝑆𝑖𝑚(𝑖,𝑙)
𝑙′∈𝐿(𝑖) 𝑆𝑖𝑚(𝑖,𝑙′)
 A novel regularization : user topic regularization (UTR)
 𝑚𝑖𝑛 𝑖=1
𝑀
∥ 𝑈𝑖 − 𝑙∈𝐿(𝑖) 𝑒𝑖𝑙 𝑈𝑙 ∥ 𝐹
2
 Intuition: users with similar interested topics tend to have similar
latent features
user 𝑖
user 𝑙
Yueshen Xu, WAIM, 2015
Recommendation with UGC in User
Side
2015/6/9 Zhejiang University 8
 A new MF model (UTR-MF)
 𝑚𝑖𝑛 𝑈,𝑉 𝐿 = 𝑖=1
𝑀
𝑗=1
𝑁
𝐼𝑖𝑗(𝑅𝑖𝑗 − 𝑈𝑖
𝑇
𝑉𝑗)2 +
𝜆 𝑈
2
∥ 𝑈 ∥ 𝐹
2
+
𝜆 𝑉
2
∥ 𝑉 ∥ 𝐹
2
+
𝛼
2 𝑖=1
𝑀
∥ 𝑈𝑖 − 𝑙∈𝐿(𝑖) 𝑒𝑖𝑙 𝑈𝑙 ∥ 𝐹
2
 gradient descent/ coordinate descent
 Gradient Descent

𝜕𝐿
𝜕𝑈 𝑖
= 𝑗=1
𝑁
𝐼𝑖𝑗(𝑅𝑖𝑗 − 𝑈𝑖
𝑇
𝑉𝑗)(−𝑉𝑗) + 𝜆 𝑈 𝑈𝑖 + 𝛼 𝑈𝑖 − 𝑙∈𝐿 𝑖 𝑒𝑖𝑙 𝑈𝑖 +
𝛼 𝑔∈𝐺(𝑖)(𝑈𝑔 − 𝑙′∈𝐿 𝑔 𝑒 𝑔𝑙′ 𝑈𝑙′) × (−𝑒 𝑔𝑖)

𝜕𝐿
𝜕𝑉 𝑗
= 𝑖=1
𝑀
𝐼𝑖𝑗(𝑅𝑖𝑗 − 𝑈𝑖
𝑇
𝑉𝑗)(−𝑈𝑖) + 𝜆 𝑉 𝑉𝑗
 𝐺(𝑖) is a set consisting of those users whose neighborhoods
include user 𝑖
Yueshen Xu, WAIM, 2015
Recommendation with UGC in Item
Side
2015/6/9 9
 Intuition for items: similar UGC  similar topic
distribution  similar latent feature
 𝑆𝑖𝑚 𝑗, ℎ : similarity between item j and h  PCC, cosine or KL
divergence
 𝑤 𝑗, ℎ =
𝑆𝑖𝑚(𝑗,ℎ)
ℎ′∈𝐻(𝑗) 𝑆𝑖𝑚(𝑗,ℎ′)
 A novel regularization: item topic regularization (ITR)
 𝑚𝑖𝑛 𝑗=1
𝑁
∥ 𝑉𝑗 − ℎ∈𝐻(𝑗) 𝑤𝑗ℎ 𝑉ℎ ∥ 𝐹
2
 A new MF model (ITR-MF):
‒ 𝑚𝑖𝑛 𝑈,𝑉 𝐿 = 𝑖=1
𝑀
𝑗=1
𝑁
𝐼𝑖𝑗(𝑅𝑖𝑗 − 𝑈𝑖
𝑇
𝑉𝑗)2
+
𝜆 𝑈
2
∥ 𝑈 ∥ 𝐹
2
+
𝜆 𝑉
2
∥ 𝑉 ∥ 𝐹
2
+
𝛼
2 𝑗=1
𝑁
∥ 𝑉𝑗 − ℎ∈𝐻(𝑗) 𝑤𝑗ℎ 𝑉ℎ ∥ 𝐹
2
 A natural combination: UTR + ITR
 gradient descent/coordinate descent
Yueshen Xu, WAIM, 2015
Experiment and Evaluation
2015/6/9 Zhejiang University 10
 Real-world dataset
 Movielens (social tag + rating)
 Last.fm (expanded, social tag + rating)
 Yelp (review + rating)
 Evaluation Metric: RMSE and MAE
 Compared baseline models: UserCF, ItemCF, PMF, TF-IDF MF, CTR
 In social tag case:
Yueshen Xu, WAIM, 2015
Experiment and Evaluation
2015/6/9 Zhejiang University 11
 Experimental results (cont.)
 UTR-MF and ITR-MF outperform other baselines in all cases
 A detailed example, in Last.fm dataset, ITR-MF achieves 14%
improvement than PMF and 8% improvement than CTR
 ITR-MF behaves better than UTR-MF: a user’s preference is harder to
infer. The main reason is probably that a user’s preference can change
dynamically
Yueshen Xu, WAIM, 2015
Experiment and Evaluation
2015/6/9 Zhejiang University 12
 Experimental results (cont.)
 in review case  the improvement is similar to that in the social tag
case
 UTR-MF and ITR-MF outperform other baselines in all cases
 ITR-MF behaves better than UTR-MF: a user’s preference is harder to
infer
 The improvements are significant according to the paired t-test (𝑝 <
0.001)
 For more details, please refer to our paper
Yueshen Xu, WAIM, 2015
Conclusion
 Conclusion
 We demonstrate that different types of UGC can be integrated
into the MF model in a unified way
 User preferences and item features can be learned from UGC
text
 Our two novel regularization terms are effective to model user
preferences and item features
 Our two MF-extended models can achieve large improvements
 Future Work
 Study other types of UGC, such as tweet and blog, to learn user
preferences and influential events in SNS
2015/6/9 Zhejiang University 13
Yueshen Xu, WAIM, 2015
Reference
[1] Adomavicius, G. and Tuzhilin, A.: Toward the next generation of recommender systems: A survey of
the state-of-the-art and possible extensions. In: IEEE TKDE, 17(6):734-749 (2005)
[2] Aggarwal, C.C. and Zhai, C.: Mining Text Data. In: Springer, New York (2012)
[3] Bischo, K., Firan, C.S., Nejdl, W., and Paiu, R.: Can all tags be used for search?In: ACM CIKM, pp.
193-202 (2008)
[4] Blei, D.M., Ng, A. Y., and Jordan, M. I.: Latent dirichlet allocation. In: JMLR,3:993-1022 (2003)
[5] Cantador, I., Brusilovsky, P., and Ku ik, T.: HetRec workshop. In: ACM RecSys,New York, USA (2011)
[6] Chen, C., Zheng, X., Wang, Y., Hong, F. and Lin, Z.: Context-Aware Collaborative Topic Regression
with Social Matrix Factorization for Recommender Systems. In: AAAI, pp. 9-15 (2014)
[7] Fang, Y. and Si, L.: Matrix co-factorization for recommendation with rich side information and implicit
feedback. In: HetRec (workshop of RecSys), pp. 65-69 (2011)
[8] Griths, T. L. and Steyvers, M.: Finding Scientific Topics. In: PNAS (2004)
[9] Koren, Y., Bell, R., and Volinsky, C.: Matrix factorization techniques for recommender systems. In:
Computer, 42(8):30-37 (2009)
[10] Liang, H., Xu, Y., Li, Y., Nayak, R., and Tao, X.: Connecting users and items with weighted tags for
personalized item recommendations. In: Hypertext, pp.51-60(2010)
[11] Liu, X. and Aberer, K.: SoCo: a social network aided context-aware recommendersystem. In: WWW,
pp. 781-802 (2013)
[12] Ma, H., Zhou, D., Liu, C., Lyu, M.R., and King, I.: Recommender systems with social regularization.
In: ACM WSDM, pp. 287-296 (2011)
2015/6/9 Zhejiang University 14
Yueshen Xu, WAIM, 2015
Reference
[13] McAuley, J.J. and Leskovec, J.: Hidden factors and hidden topics: understanding rating
dimensions with review text. In: ACM RecSys, pp. 165-172 (2013)
[14] Moens, M.-F., Li, J. and Chua, T.-S. : Mining User Generated Content. In: Chapman and Hall/CRC
(2014)
[15] Pandora. Music genome project. In: http://www.pandora.com/about/mgp
[16] Purushotham, S. and Liu, Y.: Collaborative topic regression with social matrix factorization for
recommendation systems. In: IEEE ICML, pp. 759-766 (2012)
[17] Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., and Riedl, J.: Grouplens: An open
architecture for collaborative filtering of netnews. In: CSCW, pp. 175-186 (1994)
[18] Rovi. Recommendations api version 2.0. In:
http://proddoc.rovicorp.com/mashery/index.php/Recommendations
[19] Salakhutdinov, R. and Mnih, A.: Probabilistic matrix factorization. In: NIPS
[20] Sarwar, B., Karypis, G., Konstan, J., and Reidl, J.: Item-based collaborative tering
recommendation algorithm. In: WWW, pp. 285-295 (2001)
[21] Wang, C. and Blei, D.M.: Collaborative topic modeling for recommending scientic articles. In: ACM
SIGKDD, pp. 448-456 (2011)
[22] Yang, X., Steck, H., and Liu, Y.: Circle-based recommendation in online social networks. In: ACM
SIGKDD, pp. 1267-1275 (2012)
[23] Zhang, Y., Lai, G., Zhang, M., Zhang, Y., Liu, Y. and Ma, S.: Explicit factor models for explainable
recommendation based on phrase-level sentiment analysis. In: ACM SIGIR, pp. 83-92 (2014)
2015/6/9 Zhejiang University 15
Yueshen Xu, WAIM, 2015
Thank you!
Q&A
2015/6/9 16Zhejiang University

More Related Content

What's hot

Personalizing the web building effective recommender systems
Personalizing the web building effective recommender systemsPersonalizing the web building effective recommender systems
Personalizing the web building effective recommender systems
Aravindharamanan S
 
Broad concepts - Methods in User-Technology Studies
Broad concepts - Methods in User-Technology StudiesBroad concepts - Methods in User-Technology Studies
Broad concepts - Methods in User-Technology Studies
Antti Salovaara
 
Preference Elicitation in Recommender Systems
Preference Elicitation in Recommender SystemsPreference Elicitation in Recommender Systems
Preference Elicitation in Recommender Systems
Anish Shenoy
 
Ijetcas14 580
Ijetcas14 580Ijetcas14 580
Ijetcas14 580
Iasir Journals
 
Information Retrieval Models for Recommender Systems - PhD slides
Information Retrieval Models for Recommender Systems - PhD slidesInformation Retrieval Models for Recommender Systems - PhD slides
Information Retrieval Models for Recommender Systems - PhD slides
Daniel Valcarce
 
Tehrany2014
Tehrany2014Tehrany2014
Tehrany2014
Christian Choez
 
Preference Elicitation Interface
Preference Elicitation InterfacePreference Elicitation Interface
Preference Elicitation Interface
晓愚 孟
 
Team 3 research proposal presentation
Team 3 research proposal presentationTeam 3 research proposal presentation
Team 3 research proposal presentationretromolar
 
Prospect for learning analytics to achieve adaptive learning model
Prospect for learning analytics to achieve adaptive learning modelProspect for learning analytics to achieve adaptive learning model
Prospect for learning analytics to achieve adaptive learning model
Open Cyber University of Korea
 
Tag based recommender system
Tag based recommender systemTag based recommender system
Tag based recommender system
Karen Li
 

What's hot (11)

Personalizing the web building effective recommender systems
Personalizing the web building effective recommender systemsPersonalizing the web building effective recommender systems
Personalizing the web building effective recommender systems
 
Broad concepts - Methods in User-Technology Studies
Broad concepts - Methods in User-Technology StudiesBroad concepts - Methods in User-Technology Studies
Broad concepts - Methods in User-Technology Studies
 
Preference Elicitation in Recommender Systems
Preference Elicitation in Recommender SystemsPreference Elicitation in Recommender Systems
Preference Elicitation in Recommender Systems
 
A critical review of literature in the kenyan context
A critical review of literature in the kenyan contextA critical review of literature in the kenyan context
A critical review of literature in the kenyan context
 
Ijetcas14 580
Ijetcas14 580Ijetcas14 580
Ijetcas14 580
 
Information Retrieval Models for Recommender Systems - PhD slides
Information Retrieval Models for Recommender Systems - PhD slidesInformation Retrieval Models for Recommender Systems - PhD slides
Information Retrieval Models for Recommender Systems - PhD slides
 
Tehrany2014
Tehrany2014Tehrany2014
Tehrany2014
 
Preference Elicitation Interface
Preference Elicitation InterfacePreference Elicitation Interface
Preference Elicitation Interface
 
Team 3 research proposal presentation
Team 3 research proposal presentationTeam 3 research proposal presentation
Team 3 research proposal presentation
 
Prospect for learning analytics to achieve adaptive learning model
Prospect for learning analytics to achieve adaptive learning modelProspect for learning analytics to achieve adaptive learning model
Prospect for learning analytics to achieve adaptive learning model
 
Tag based recommender system
Tag based recommender systemTag based recommender system
Tag based recommender system
 

Viewers also liked

(Hierarchical) topic modeling
(Hierarchical) topic modeling (Hierarchical) topic modeling
(Hierarchical) topic modeling
Yueshen Xu
 
The Conclusion for sigir 2011
The Conclusion for sigir 2011The Conclusion for sigir 2011
The Conclusion for sigir 2011
Yueshen Xu
 
聚类 (Clustering)
聚类 (Clustering)聚类 (Clustering)
聚类 (Clustering)
Yueshen Xu
 
徐悦甡简历
徐悦甡简历徐悦甡简历
徐悦甡简历
Yueshen Xu
 
Non parametric bayesian learning in discrete data
Non parametric bayesian learning in discrete dataNon parametric bayesian learning in discrete data
Non parametric bayesian learning in discrete data
Yueshen Xu
 
Yueshen xu cv
Yueshen xu cvYueshen xu cv
Yueshen xu cv
Yueshen Xu
 
(Hierarchical) Topic Modeling_Yueshen Xu
(Hierarchical) Topic Modeling_Yueshen Xu(Hierarchical) Topic Modeling_Yueshen Xu
(Hierarchical) Topic Modeling_Yueshen XuYueshen Xu
 

Viewers also liked (7)

(Hierarchical) topic modeling
(Hierarchical) topic modeling (Hierarchical) topic modeling
(Hierarchical) topic modeling
 
The Conclusion for sigir 2011
The Conclusion for sigir 2011The Conclusion for sigir 2011
The Conclusion for sigir 2011
 
聚类 (Clustering)
聚类 (Clustering)聚类 (Clustering)
聚类 (Clustering)
 
徐悦甡简历
徐悦甡简历徐悦甡简历
徐悦甡简历
 
Non parametric bayesian learning in discrete data
Non parametric bayesian learning in discrete dataNon parametric bayesian learning in discrete data
Non parametric bayesian learning in discrete data
 
Yueshen xu cv
Yueshen xu cvYueshen xu cv
Yueshen xu cv
 
(Hierarchical) Topic Modeling_Yueshen Xu
(Hierarchical) Topic Modeling_Yueshen Xu(Hierarchical) Topic Modeling_Yueshen Xu
(Hierarchical) Topic Modeling_Yueshen Xu
 

Similar to Learning to recommend with user generated content

System Adoption: Socio-Technical Integration
System Adoption: Socio-Technical IntegrationSystem Adoption: Socio-Technical Integration
System Adoption: Socio-Technical Integration
The International Journal of Business Management and Technology
 
Ullmann
UllmannUllmann
Ullmannanesah
 
Explainable AI for non-expert users
Explainable AI for non-expert usersExplainable AI for non-expert users
Explainable AI for non-expert users
Katrien Verbert
 
JOEUC04.pdf
JOEUC04.pdfJOEUC04.pdf
JOEUC04.pdf
ssuser4a7017
 
Ijmet 10 02_050
Ijmet 10 02_050Ijmet 10 02_050
Ijmet 10 02_050
IAEME Publication
 
Presentation acdec2013
Presentation acdec2013Presentation acdec2013
Presentation acdec2013
Dr. Vignes Gopal
 
Mustafa Degerli - 2010 - What is available about technology acceptance of e-l...
Mustafa Degerli - 2010 - What is available about technology acceptance of e-l...Mustafa Degerli - 2010 - What is available about technology acceptance of e-l...
Mustafa Degerli - 2010 - What is available about technology acceptance of e-l...
Dr. Mustafa Değerli
 
1-s2.0-S0968090X20306471-main.pdf
1-s2.0-S0968090X20306471-main.pdf1-s2.0-S0968090X20306471-main.pdf
1-s2.0-S0968090X20306471-main.pdf
ResearchWriting1
 
RUNNING HEADER Analytics Ecosystem1Analytics Ecosystem4.docx
RUNNING HEADER Analytics Ecosystem1Analytics Ecosystem4.docxRUNNING HEADER Analytics Ecosystem1Analytics Ecosystem4.docx
RUNNING HEADER Analytics Ecosystem1Analytics Ecosystem4.docx
anhlodge
 
Towards the next generation of interactive and adaptive explanation methods
Towards the next generation of interactive and adaptive explanation methodsTowards the next generation of interactive and adaptive explanation methods
Towards the next generation of interactive and adaptive explanation methods
Katrien Verbert
 
THE USE OF CLOUD COMPUTING SYSTEMS IN HIGHER EDUCATION; The Lived Experien...
THE USE OF CLOUD COMPUTING SYSTEMS IN HIGHER EDUCATION;  The Lived Experien...THE USE OF CLOUD COMPUTING SYSTEMS IN HIGHER EDUCATION;  The Lived Experien...
THE USE OF CLOUD COMPUTING SYSTEMS IN HIGHER EDUCATION; The Lived Experien...
African Virtual University
 
A hybrid recommender system user profiling from keywords and ratings
A hybrid recommender system user profiling from keywords and ratingsA hybrid recommender system user profiling from keywords and ratings
A hybrid recommender system user profiling from keywords and ratings
Aravindharamanan S
 
KatKennedy REU D.C. Poster
KatKennedy REU D.C. PosterKatKennedy REU D.C. Poster
KatKennedy REU D.C. PosterKatlynn Kennedy
 
On the benefit of logic-based machine learning to learn pairwise comparisons
On the benefit of logic-based machine learning to learn pairwise comparisonsOn the benefit of logic-based machine learning to learn pairwise comparisons
On the benefit of logic-based machine learning to learn pairwise comparisons
journalBEEI
 
Agent-Based Problem Solving Methods In Big Data Environment
Agent-Based Problem Solving Methods In Big Data EnvironmentAgent-Based Problem Solving Methods In Big Data Environment
Agent-Based Problem Solving Methods In Big Data Environment
Laurie Smith
 
La &amp; edm in practice
La &amp; edm in practiceLa &amp; edm in practice
La &amp; edm in practice
bharati k
 
Using Simulations to Evaluated the Effects of Recommender Systems for Learner...
Using Simulations to Evaluated the Effects of Recommender Systems for Learner...Using Simulations to Evaluated the Effects of Recommender Systems for Learner...
Using Simulations to Evaluated the Effects of Recommender Systems for Learner...
Hendrik Drachsler
 
Classifying Twitter Content
Classifying Twitter ContentClassifying Twitter Content
Classifying Twitter ContentStephen Dann
 

Similar to Learning to recommend with user generated content (20)

System Adoption: Socio-Technical Integration
System Adoption: Socio-Technical IntegrationSystem Adoption: Socio-Technical Integration
System Adoption: Socio-Technical Integration
 
Ullmann
UllmannUllmann
Ullmann
 
Explainable AI for non-expert users
Explainable AI for non-expert usersExplainable AI for non-expert users
Explainable AI for non-expert users
 
JOEUC04.pdf
JOEUC04.pdfJOEUC04.pdf
JOEUC04.pdf
 
Ijmet 10 02_050
Ijmet 10 02_050Ijmet 10 02_050
Ijmet 10 02_050
 
Presentation acdec2013
Presentation acdec2013Presentation acdec2013
Presentation acdec2013
 
Mustafa Degerli - 2010 - What is available about technology acceptance of e-l...
Mustafa Degerli - 2010 - What is available about technology acceptance of e-l...Mustafa Degerli - 2010 - What is available about technology acceptance of e-l...
Mustafa Degerli - 2010 - What is available about technology acceptance of e-l...
 
1-s2.0-S0968090X20306471-main.pdf
1-s2.0-S0968090X20306471-main.pdf1-s2.0-S0968090X20306471-main.pdf
1-s2.0-S0968090X20306471-main.pdf
 
RUNNING HEADER Analytics Ecosystem1Analytics Ecosystem4.docx
RUNNING HEADER Analytics Ecosystem1Analytics Ecosystem4.docxRUNNING HEADER Analytics Ecosystem1Analytics Ecosystem4.docx
RUNNING HEADER Analytics Ecosystem1Analytics Ecosystem4.docx
 
Towards the next generation of interactive and adaptive explanation methods
Towards the next generation of interactive and adaptive explanation methodsTowards the next generation of interactive and adaptive explanation methods
Towards the next generation of interactive and adaptive explanation methods
 
THE USE OF CLOUD COMPUTING SYSTEMS IN HIGHER EDUCATION; The Lived Experien...
THE USE OF CLOUD COMPUTING SYSTEMS IN HIGHER EDUCATION;  The Lived Experien...THE USE OF CLOUD COMPUTING SYSTEMS IN HIGHER EDUCATION;  The Lived Experien...
THE USE OF CLOUD COMPUTING SYSTEMS IN HIGHER EDUCATION; The Lived Experien...
 
Design Presentation-CGillies
Design Presentation-CGilliesDesign Presentation-CGillies
Design Presentation-CGillies
 
A hybrid recommender system user profiling from keywords and ratings
A hybrid recommender system user profiling from keywords and ratingsA hybrid recommender system user profiling from keywords and ratings
A hybrid recommender system user profiling from keywords and ratings
 
Sub1557
Sub1557Sub1557
Sub1557
 
KatKennedy REU D.C. Poster
KatKennedy REU D.C. PosterKatKennedy REU D.C. Poster
KatKennedy REU D.C. Poster
 
On the benefit of logic-based machine learning to learn pairwise comparisons
On the benefit of logic-based machine learning to learn pairwise comparisonsOn the benefit of logic-based machine learning to learn pairwise comparisons
On the benefit of logic-based machine learning to learn pairwise comparisons
 
Agent-Based Problem Solving Methods In Big Data Environment
Agent-Based Problem Solving Methods In Big Data EnvironmentAgent-Based Problem Solving Methods In Big Data Environment
Agent-Based Problem Solving Methods In Big Data Environment
 
La &amp; edm in practice
La &amp; edm in practiceLa &amp; edm in practice
La &amp; edm in practice
 
Using Simulations to Evaluated the Effects of Recommender Systems for Learner...
Using Simulations to Evaluated the Effects of Recommender Systems for Learner...Using Simulations to Evaluated the Effects of Recommender Systems for Learner...
Using Simulations to Evaluated the Effects of Recommender Systems for Learner...
 
Classifying Twitter Content
Classifying Twitter ContentClassifying Twitter Content
Classifying Twitter Content
 

More from Yueshen Xu

Context aware service recommendation
Context aware service recommendationContext aware service recommendation
Context aware service recommendation
Yueshen Xu
 
Course review for ir class 本科课件
Course review for ir class 本科课件Course review for ir class 本科课件
Course review for ir class 本科课件
Yueshen Xu
 
Semantic web 本科课件
Semantic web 本科课件Semantic web 本科课件
Semantic web 本科课件
Yueshen Xu
 
Recommender system slides for undergraduate
Recommender system slides for undergraduateRecommender system slides for undergraduate
Recommender system slides for undergraduate
Yueshen Xu
 
推荐系统 本科课件
 推荐系统 本科课件 推荐系统 本科课件
推荐系统 本科课件
Yueshen Xu
 
Text classification 本科课件
Text classification 本科课件Text classification 本科课件
Text classification 本科课件
Yueshen Xu
 
Thinking in clustering yueshen xu
Thinking in clustering yueshen xuThinking in clustering yueshen xu
Thinking in clustering yueshen xu
Yueshen Xu
 
Text clustering (information retrieval, in chinese)
Text clustering (information retrieval, in chinese)Text clustering (information retrieval, in chinese)
Text clustering (information retrieval, in chinese)
Yueshen Xu
 
Social recommender system
Social recommender systemSocial recommender system
Social recommender system
Yueshen Xu
 
Summary on the Conference of WISE 2013
Summary on the Conference of WISE 2013Summary on the Conference of WISE 2013
Summary on the Conference of WISE 2013
Yueshen Xu
 
Topic model an introduction
Topic model an introductionTopic model an introduction
Topic model an introduction
Yueshen Xu
 
Acoustic modeling using deep belief networks
Acoustic modeling using deep belief networksAcoustic modeling using deep belief networks
Acoustic modeling using deep belief networks
Yueshen Xu
 
Summarization for dragon star program
Summarization for dragon  star programSummarization for dragon  star program
Summarization for dragon star programYueshen Xu
 
Aggregation computation over distributed data streams(the final version)
Aggregation computation over distributed data streams(the final version)Aggregation computation over distributed data streams(the final version)
Aggregation computation over distributed data streams(the final version)
Yueshen Xu
 
Aggregation computation over distributed data streams
Aggregation computation over distributed data streamsAggregation computation over distributed data streams
Aggregation computation over distributed data streams
Yueshen Xu
 
Analysis on tcp ip protocol stack
Analysis on tcp ip protocol stackAnalysis on tcp ip protocol stack
Analysis on tcp ip protocol stack
Yueshen Xu
 
Simple conclusion for sap tech ed 2011
Simple conclusion for sap tech ed 2011Simple conclusion for sap tech ed 2011
Simple conclusion for sap tech ed 2011
Yueshen Xu
 
Stream data mining & CluStream framework
Stream data mining & CluStream frameworkStream data mining & CluStream framework
Stream data mining & CluStream framework
Yueshen Xu
 
Hidden markov chain and bayes belief networks doctor consortium
Hidden markov chain and bayes belief networks doctor consortiumHidden markov chain and bayes belief networks doctor consortium
Hidden markov chain and bayes belief networks doctor consortium
Yueshen Xu
 
Hidden markov chain and bayes belief networks doctor consortium
Hidden markov chain and bayes belief networks doctor consortiumHidden markov chain and bayes belief networks doctor consortium
Hidden markov chain and bayes belief networks doctor consortium
Yueshen Xu
 

More from Yueshen Xu (20)

Context aware service recommendation
Context aware service recommendationContext aware service recommendation
Context aware service recommendation
 
Course review for ir class 本科课件
Course review for ir class 本科课件Course review for ir class 本科课件
Course review for ir class 本科课件
 
Semantic web 本科课件
Semantic web 本科课件Semantic web 本科课件
Semantic web 本科课件
 
Recommender system slides for undergraduate
Recommender system slides for undergraduateRecommender system slides for undergraduate
Recommender system slides for undergraduate
 
推荐系统 本科课件
 推荐系统 本科课件 推荐系统 本科课件
推荐系统 本科课件
 
Text classification 本科课件
Text classification 本科课件Text classification 本科课件
Text classification 本科课件
 
Thinking in clustering yueshen xu
Thinking in clustering yueshen xuThinking in clustering yueshen xu
Thinking in clustering yueshen xu
 
Text clustering (information retrieval, in chinese)
Text clustering (information retrieval, in chinese)Text clustering (information retrieval, in chinese)
Text clustering (information retrieval, in chinese)
 
Social recommender system
Social recommender systemSocial recommender system
Social recommender system
 
Summary on the Conference of WISE 2013
Summary on the Conference of WISE 2013Summary on the Conference of WISE 2013
Summary on the Conference of WISE 2013
 
Topic model an introduction
Topic model an introductionTopic model an introduction
Topic model an introduction
 
Acoustic modeling using deep belief networks
Acoustic modeling using deep belief networksAcoustic modeling using deep belief networks
Acoustic modeling using deep belief networks
 
Summarization for dragon star program
Summarization for dragon  star programSummarization for dragon  star program
Summarization for dragon star program
 
Aggregation computation over distributed data streams(the final version)
Aggregation computation over distributed data streams(the final version)Aggregation computation over distributed data streams(the final version)
Aggregation computation over distributed data streams(the final version)
 
Aggregation computation over distributed data streams
Aggregation computation over distributed data streamsAggregation computation over distributed data streams
Aggregation computation over distributed data streams
 
Analysis on tcp ip protocol stack
Analysis on tcp ip protocol stackAnalysis on tcp ip protocol stack
Analysis on tcp ip protocol stack
 
Simple conclusion for sap tech ed 2011
Simple conclusion for sap tech ed 2011Simple conclusion for sap tech ed 2011
Simple conclusion for sap tech ed 2011
 
Stream data mining & CluStream framework
Stream data mining & CluStream frameworkStream data mining & CluStream framework
Stream data mining & CluStream framework
 
Hidden markov chain and bayes belief networks doctor consortium
Hidden markov chain and bayes belief networks doctor consortiumHidden markov chain and bayes belief networks doctor consortium
Hidden markov chain and bayes belief networks doctor consortium
 
Hidden markov chain and bayes belief networks doctor consortium
Hidden markov chain and bayes belief networks doctor consortiumHidden markov chain and bayes belief networks doctor consortium
Hidden markov chain and bayes belief networks doctor consortium
 

Recently uploaded

一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
v3tuleee
 
Machine learning and optimization techniques for electrical drives.pptx
Machine learning and optimization techniques for electrical drives.pptxMachine learning and optimization techniques for electrical drives.pptx
Machine learning and optimization techniques for electrical drives.pptx
balafet
 
Empowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptxEmpowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptx
benishzehra469
 
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdfCh03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
haila53
 
一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单
ewymefz
 
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdfSample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Linda486226
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
Subhajit Sahu
 
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
NABLAS株式会社
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
ewymefz
 
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
axoqas
 
The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...
jerlynmaetalle
 
Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)
TravisMalana
 
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
u86oixdj
 
SOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape ReportSOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape Report
SOCRadar
 
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
ahzuo
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghh
ArpitMalhotra16
 
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
ewymefz
 
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
mbawufebxi
 
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
vcaxypu
 
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Subhajit Sahu
 

Recently uploaded (20)

一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
 
Machine learning and optimization techniques for electrical drives.pptx
Machine learning and optimization techniques for electrical drives.pptxMachine learning and optimization techniques for electrical drives.pptx
Machine learning and optimization techniques for electrical drives.pptx
 
Empowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptxEmpowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptx
 
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdfCh03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
 
一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单
 
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdfSample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
 
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
 
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
 
The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...
 
Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)
 
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
 
SOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape ReportSOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape Report
 
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghh
 
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
 
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
 
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
 
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
 

Learning to recommend with user generated content

  • 1. Learning to Recommend with User Generated Content Yueshen Xu1, Zhiyuan Chen2, Jianwei Yin1, Zizheng Wu1 and Taojun Yao1 1School of Computer Science and Technology, Zhejiang University 2University of Illinois at Chicago xyshzjucs@zju.edu.cn; xyshzjucs@gmail.com 2015/6/9 1Zhejiang University Junxiang Wang
  • 2. Yueshen Xu, WAIM, 2015 Outline  Background  Introduction  Related Work  Recommendation with UGC in User Side  Matrix Factorization  Topic Analysis for Items through Topic Modeling  User Interest Distribution  User Topic Regularization  Recommendation with UGC in Item Side  Item Topic Regularization  Experiment and Evaluation  Reference 2015/6/9 2Zhejiang University Keywords: Recommendation, User Generated Content, Topic Modeling, Matrix Factorization
  • 3. Yueshen Xu, WAIM, 2015 Background  Recommendation in General  Collaborative Filtering (CF) − Matrix Factorization (MF)  Content-based approach − Pandora music genome project 2015/6/9 3Zhejiang University  User Generated Content (UGC)  social tag, review, question answer, blog, tweet, etc  tag-based / review-based recommendation  Problems in existing works  not every web site has all kinds of UGC  the item-word / user-word space is highly sparse  synonym & polysemy  most works only focus on a single kind of UGC item1 item2 item3 item4 user1 r11 user2 r22 user3 user4 r41 r44 user5 r53
  • 4. Yueshen Xu, WAIM, 2015 Background 2015/6/9 4  Other related work  social / trust-based recommendation  helpful but limited − no social relationship  Amazon, Ebay, Newegg, Jingdong, Expedia, etc − UGC √  Description/Profile-based recommendation − static content − fail to distinguish different items − unrelated to a user’s preference  UGC, in contrast:  emphasize an item’s features − those words received frequently  increase dynamically  associated with a user’s preference / interested topics − I like science fiction films, so I wrote a lot of movie reviews that contain words like fiction, tech, super, hero, robotic, machine  natural chunking (social tag)
  • 5. Yueshen Xu, WAIM, 2015 Contribution 2015/6/9 5Zhejiang University  Main contributions  We study UGC in learning user interests and learning item features  We propose a novel user-oriented collaborative filtering model and a novel item-oriented collaborative filtering model  We propose a way to utilize different types of UGC in a unified way in recommender systems  We expand an existing dataset by crawling new data, and conduct sufficient experiments on three real-world datasets, which attest the effectiveness of proposed models.
  • 6. Yueshen Xu, WAIM, 2015 Recommendation with UGC in User Side 2015/6/9 Zhejiang University 6  Topic analysis for items through topic modeling  Terms in UGC are combined together to compose the term set W  each item owns an aggregated term list  pLSA/LDA/HDP/nCRP/PAM: all are OK  𝚯 = 𝜽𝒋 (𝜽𝒋 = 𝜃𝒋𝟏, 𝜃𝒋𝟐, … , 𝜃𝒋𝑲, ) is the topic/aspect distribution of document j (i.e., item j)  what we need  User Interest Distribution  Cluster items into groups according to the similarity of their topics (K-Means/GMM/K-Medoid: all are OK)
  • 7. Yueshen Xu, WAIM, 2015 Recommendation with UGC in User Side 2015/6/9 Zhejiang University 7  User Interest Distribution (cont.)  Intuition : find items with similar topics, although they are in different categories: clothes, gadget, book, toy, DVD all about Harry Potter  Aggregate each user’s consumption records on each cluster 𝐶 𝑞 𝑆𝑖𝑚 𝑖, 𝑙 = 𝑃𝐶𝐶, 𝒄𝒐𝒔𝒊𝒏𝒆 𝑜𝑟 𝐾𝐿 𝑑𝑖𝑣𝑒𝑟𝑔𝑒𝑛𝑐𝑒 the weight of 𝑙 as one of user 𝑖’s neighbors: 𝑒𝑖𝑙 𝑖, 𝑙 = 𝑆𝑖𝑚(𝑖,𝑙) 𝑙′∈𝐿(𝑖) 𝑆𝑖𝑚(𝑖,𝑙′)  A novel regularization : user topic regularization (UTR)  𝑚𝑖𝑛 𝑖=1 𝑀 ∥ 𝑈𝑖 − 𝑙∈𝐿(𝑖) 𝑒𝑖𝑙 𝑈𝑙 ∥ 𝐹 2  Intuition: users with similar interested topics tend to have similar latent features user 𝑖 user 𝑙
  • 8. Yueshen Xu, WAIM, 2015 Recommendation with UGC in User Side 2015/6/9 Zhejiang University 8  A new MF model (UTR-MF)  𝑚𝑖𝑛 𝑈,𝑉 𝐿 = 𝑖=1 𝑀 𝑗=1 𝑁 𝐼𝑖𝑗(𝑅𝑖𝑗 − 𝑈𝑖 𝑇 𝑉𝑗)2 + 𝜆 𝑈 2 ∥ 𝑈 ∥ 𝐹 2 + 𝜆 𝑉 2 ∥ 𝑉 ∥ 𝐹 2 + 𝛼 2 𝑖=1 𝑀 ∥ 𝑈𝑖 − 𝑙∈𝐿(𝑖) 𝑒𝑖𝑙 𝑈𝑙 ∥ 𝐹 2  gradient descent/ coordinate descent  Gradient Descent  𝜕𝐿 𝜕𝑈 𝑖 = 𝑗=1 𝑁 𝐼𝑖𝑗(𝑅𝑖𝑗 − 𝑈𝑖 𝑇 𝑉𝑗)(−𝑉𝑗) + 𝜆 𝑈 𝑈𝑖 + 𝛼 𝑈𝑖 − 𝑙∈𝐿 𝑖 𝑒𝑖𝑙 𝑈𝑖 + 𝛼 𝑔∈𝐺(𝑖)(𝑈𝑔 − 𝑙′∈𝐿 𝑔 𝑒 𝑔𝑙′ 𝑈𝑙′) × (−𝑒 𝑔𝑖)  𝜕𝐿 𝜕𝑉 𝑗 = 𝑖=1 𝑀 𝐼𝑖𝑗(𝑅𝑖𝑗 − 𝑈𝑖 𝑇 𝑉𝑗)(−𝑈𝑖) + 𝜆 𝑉 𝑉𝑗  𝐺(𝑖) is a set consisting of those users whose neighborhoods include user 𝑖
  • 9. Yueshen Xu, WAIM, 2015 Recommendation with UGC in Item Side 2015/6/9 9  Intuition for items: similar UGC  similar topic distribution  similar latent feature  𝑆𝑖𝑚 𝑗, ℎ : similarity between item j and h  PCC, cosine or KL divergence  𝑤 𝑗, ℎ = 𝑆𝑖𝑚(𝑗,ℎ) ℎ′∈𝐻(𝑗) 𝑆𝑖𝑚(𝑗,ℎ′)  A novel regularization: item topic regularization (ITR)  𝑚𝑖𝑛 𝑗=1 𝑁 ∥ 𝑉𝑗 − ℎ∈𝐻(𝑗) 𝑤𝑗ℎ 𝑉ℎ ∥ 𝐹 2  A new MF model (ITR-MF): ‒ 𝑚𝑖𝑛 𝑈,𝑉 𝐿 = 𝑖=1 𝑀 𝑗=1 𝑁 𝐼𝑖𝑗(𝑅𝑖𝑗 − 𝑈𝑖 𝑇 𝑉𝑗)2 + 𝜆 𝑈 2 ∥ 𝑈 ∥ 𝐹 2 + 𝜆 𝑉 2 ∥ 𝑉 ∥ 𝐹 2 + 𝛼 2 𝑗=1 𝑁 ∥ 𝑉𝑗 − ℎ∈𝐻(𝑗) 𝑤𝑗ℎ 𝑉ℎ ∥ 𝐹 2  A natural combination: UTR + ITR  gradient descent/coordinate descent
  • 10. Yueshen Xu, WAIM, 2015 Experiment and Evaluation 2015/6/9 Zhejiang University 10  Real-world dataset  Movielens (social tag + rating)  Last.fm (expanded, social tag + rating)  Yelp (review + rating)  Evaluation Metric: RMSE and MAE  Compared baseline models: UserCF, ItemCF, PMF, TF-IDF MF, CTR  In social tag case:
  • 11. Yueshen Xu, WAIM, 2015 Experiment and Evaluation 2015/6/9 Zhejiang University 11  Experimental results (cont.)  UTR-MF and ITR-MF outperform other baselines in all cases  A detailed example, in Last.fm dataset, ITR-MF achieves 14% improvement than PMF and 8% improvement than CTR  ITR-MF behaves better than UTR-MF: a user’s preference is harder to infer. The main reason is probably that a user’s preference can change dynamically
  • 12. Yueshen Xu, WAIM, 2015 Experiment and Evaluation 2015/6/9 Zhejiang University 12  Experimental results (cont.)  in review case  the improvement is similar to that in the social tag case  UTR-MF and ITR-MF outperform other baselines in all cases  ITR-MF behaves better than UTR-MF: a user’s preference is harder to infer  The improvements are significant according to the paired t-test (𝑝 < 0.001)  For more details, please refer to our paper
  • 13. Yueshen Xu, WAIM, 2015 Conclusion  Conclusion  We demonstrate that different types of UGC can be integrated into the MF model in a unified way  User preferences and item features can be learned from UGC text  Our two novel regularization terms are effective to model user preferences and item features  Our two MF-extended models can achieve large improvements  Future Work  Study other types of UGC, such as tweet and blog, to learn user preferences and influential events in SNS 2015/6/9 Zhejiang University 13
  • 14. Yueshen Xu, WAIM, 2015 Reference [1] Adomavicius, G. and Tuzhilin, A.: Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. In: IEEE TKDE, 17(6):734-749 (2005) [2] Aggarwal, C.C. and Zhai, C.: Mining Text Data. In: Springer, New York (2012) [3] Bischo, K., Firan, C.S., Nejdl, W., and Paiu, R.: Can all tags be used for search?In: ACM CIKM, pp. 193-202 (2008) [4] Blei, D.M., Ng, A. Y., and Jordan, M. I.: Latent dirichlet allocation. In: JMLR,3:993-1022 (2003) [5] Cantador, I., Brusilovsky, P., and Ku ik, T.: HetRec workshop. In: ACM RecSys,New York, USA (2011) [6] Chen, C., Zheng, X., Wang, Y., Hong, F. and Lin, Z.: Context-Aware Collaborative Topic Regression with Social Matrix Factorization for Recommender Systems. In: AAAI, pp. 9-15 (2014) [7] Fang, Y. and Si, L.: Matrix co-factorization for recommendation with rich side information and implicit feedback. In: HetRec (workshop of RecSys), pp. 65-69 (2011) [8] Griths, T. L. and Steyvers, M.: Finding Scientific Topics. In: PNAS (2004) [9] Koren, Y., Bell, R., and Volinsky, C.: Matrix factorization techniques for recommender systems. In: Computer, 42(8):30-37 (2009) [10] Liang, H., Xu, Y., Li, Y., Nayak, R., and Tao, X.: Connecting users and items with weighted tags for personalized item recommendations. In: Hypertext, pp.51-60(2010) [11] Liu, X. and Aberer, K.: SoCo: a social network aided context-aware recommendersystem. In: WWW, pp. 781-802 (2013) [12] Ma, H., Zhou, D., Liu, C., Lyu, M.R., and King, I.: Recommender systems with social regularization. In: ACM WSDM, pp. 287-296 (2011) 2015/6/9 Zhejiang University 14
  • 15. Yueshen Xu, WAIM, 2015 Reference [13] McAuley, J.J. and Leskovec, J.: Hidden factors and hidden topics: understanding rating dimensions with review text. In: ACM RecSys, pp. 165-172 (2013) [14] Moens, M.-F., Li, J. and Chua, T.-S. : Mining User Generated Content. In: Chapman and Hall/CRC (2014) [15] Pandora. Music genome project. In: http://www.pandora.com/about/mgp [16] Purushotham, S. and Liu, Y.: Collaborative topic regression with social matrix factorization for recommendation systems. In: IEEE ICML, pp. 759-766 (2012) [17] Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., and Riedl, J.: Grouplens: An open architecture for collaborative filtering of netnews. In: CSCW, pp. 175-186 (1994) [18] Rovi. Recommendations api version 2.0. In: http://proddoc.rovicorp.com/mashery/index.php/Recommendations [19] Salakhutdinov, R. and Mnih, A.: Probabilistic matrix factorization. In: NIPS [20] Sarwar, B., Karypis, G., Konstan, J., and Reidl, J.: Item-based collaborative tering recommendation algorithm. In: WWW, pp. 285-295 (2001) [21] Wang, C. and Blei, D.M.: Collaborative topic modeling for recommending scientic articles. In: ACM SIGKDD, pp. 448-456 (2011) [22] Yang, X., Steck, H., and Liu, Y.: Circle-based recommendation in online social networks. In: ACM SIGKDD, pp. 1267-1275 (2012) [23] Zhang, Y., Lai, G., Zhang, M., Zhang, Y., Liu, Y. and Ma, S.: Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. In: ACM SIGIR, pp. 83-92 (2014) 2015/6/9 Zhejiang University 15
  • 16. Yueshen Xu, WAIM, 2015 Thank you! Q&A 2015/6/9 16Zhejiang University