IRJET - An Intelligent Recommendation for Social Contextual Image using Hybrid Model

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 03 | Mar 2020 www.irjet.net p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.34 | ISO 9001:2008 Certified Journal | Page 4411
An Intelligent Recommendation for Social Contextual Image Using
Hybrid Model
M. Natin Duraishkar1, S. Shwetha2, C. Jameswinsingh3, Mr. Muthurasu4
1,2,3Computer Science and Engineering SRM Institute of Science and Technology Chennai, India
------------------------------------------------------------------------------------------***----------------------------------------------------------------------------------------
Abstract— Image based social networks are among the
most popular social networking services in recent years.
With tremendous images uploaded everyday,
understanding users’ preferences on user-generated
images and making recommendations have become an
urgent need. In fact, many hybrid models have been
proposed to fuse various kinds of side information (e.g.,
image visual representation, social network) and user- item
historical behavior for enhancing recommendation
performance. However, due to the unique characteristics of
the user generated images in social image platforms, the
previous studies failed to capture the complex aspects that
influence users’ preferences in a unified framework.
Moreover, most of these hybrid models relied on
predefined weights in combining different kinds of
information, which usually resulted in sub-optimal
recommendation performance. To this end, in this paper,
we develop a hierarchical attention model for social
contextual image recommendation. In addition to basic
latent user interest modeling in the popular matrix
factorization based recommendation, we identify three key
aspects (i.e., upload history, social influence, and owner
admiration) that affect each user’s latent preferences,
where each aspect summarizes a contextual factor from the
complex relationships between users and images. After
that, we design a hierarchical attention network that
naturally mirrors the hierarchical relationship (elements in
each aspects level, and the aspect level) of users’ latent
interests with the identified key aspects. Specifically, by
taking embeddings from state-of-the-art deep learning
models that are tailored for each kind of data, the
hierarchical attention network could learn to attend
differently to more or less content. Finally, extensive
experimental results on real-world datasets clearly show
the superiority of our proposed model.
Keywords—Image, Recommendation, Rating
I. INTRODUCTION
There is a well-known axiom "an image merits a thousand
words". With regards to online networking, things being
what they are, visual pictures are developing significantly
more fame to draw in clients. Particularly with the
expanding selection of cell phones, clients could without
much of a stretch take qualified pictures also, transfer them
to different social picture stages to share these outwardly
engaging pictures with others. Numerous picture based
social sharing administrations have risen, for example,
Instagram1, Pinterest2 , and Flickr3 . With several millions
of pictures transferred regular, picture suggestion has
become an earnest need to manage the picture over-
burden issue. By giving customized picture
recommendations to every dynamic client in picture
recommender framework, clients gain more fulfillment
for stage flourishing. E.g., as announced by Pinterest,
picture proposal controls over 40% of client
commitment of this social stage .
II. LITERATURE REVIEW
We endorse accept as true with SVD, a believe-
primarily based matrix factorization method for
pointers. Believe SVD integrates more than one
records resources into the recommendation version so
one can reduce the data sacristy and cold begin issues
and their degradation of recommendation
performance. An analysis of social believe facts from 4
actual-world statistics units shows that now not
handiest the explicit but also the implicit have an
impact on of both scores and consider have to be taken
into consideration in a advice version. Believe SVD
consequently builds on top of a today's advice set of
rules, SVD++ (which makes use of the explicit and
implicit impact of rated items), via similarly
incorporating each the explicit and implicit affect of
relied on and trusting customers at the prediction of
gadgets for an active user. The proposed technique is
the primaries to extend SVD++ with social believe
records. Experimental consequences on the 4 statistics
units exhibit that believe SVD achieves better accuracy
than different ten opposite numbers’ advice strategies.
III. PROPOSED SYSTEM
Security safeguarding conventions for joining general
and subjective predicates, while guaranteeing their
rightness. They took an alternate (non-
cryptographic) approach by utilizing off- the-rack
secure processors, cryptographic co- processors.
Accepting the protected coprocessor is a confided in
segment and alter safe, their conventions can stumble
into any number of databases for any discretionary
join tasks. Protection saving information mix.
Coordinating information from numerous sources
has been a long- standing test in the database
network. Procedures, for example, protection saving
information mining guarantees security, yet expect
information has joining has been cultivated. Data mix
techniques are truly hampered by powerlessness to
share the information to be coordinated. This paper

spreads out a security system for information
coordination. Measure Of Data They Collected. Convey
Better Services. Information Sharing Services between
Organizations. In this paper, we develop a different
leveled thought model for social pertinent picture
proposal. Despite fundamental inert customer interest
showing in the standard system factorization based
recommendation, we perceive three key edges (i.e., move
history, social effect, furthermore, owner concession)
that impact each customer's lethargic tendencies, where
each edge traces a consistent factor from the complex
associations among customers and pictures.
IV. ARCHITECTURE DIAGRAM
V. MODULE DESCRIPTION
1) User Interface Design
This is the main module of our venture. The significant
job for the client is to move login window to client
window. This module has made for the security reason. In
this login page we need to enter login client id and secret
key. It will check username and secret word is coordinate
or not (substantial client id and legitimate secret key). In
the event that we enter any invalid username or secret
phrase we can't go into login window to client window it
will shows mistake message. So we are keeping from
unapproved client going into the login window to client
window. It will give a decent security to our venture. So
server contain client id and secret key server additionally
check the confirmation of the client. It well improves the
security and keeping from unapproved client goes into the
system. In our undertaking we are utilizing JSP for making
structure. Here we approve the login client and server
verification.
Figure 1 User Interface Design
2) Admin Upload Image
In this application admin will directly login to this
application, so the images only uploaded by admin
only. Admin will responsible for the actions taken
under this application.
Figure 2 Admin Upload Image
3) User Login & View Image
In this part registered user will login and they can
view the all images uploaded by admin. Users work is
to recommend some other user to view the images
uploaded by admin. For this they have to register to
this application.
Figure 3 Login & View Image
4) Give Friend Request
User must send requests in this module for the user
already registered here. To do this, they must enter
their friend name and search for it. If they have
registered, the user information will be shown
otherwise it will show null record.

Figure 4 Give Friend Request
VI. CONCLUSION
In this paper, we have proposed a progressive mindful
social logical model of HASC for social relevant picture
suggestion. In particular, notwithstanding client
enthusiasm demonstrating, we have distinguished three
social relevant perspectives that impact a client's
inclination to a picture from heterogeneous information:
the transfer history angle, the social impact viewpoint,
and the proprietor profound respect angle. We planned a
progressive consideration arrange that normally
reflected the various leveled relationship of clients'
advantage given the three distinguished perspectives.
Meanwhile, by encouraging the information inserting
from rich heterogeneous information sources, the
progressive consideration systems could figure out how
to go to contrastingly to pretty much significant
substance. Broad examinations on genuine world
datasets obviously showed that our proposed HASC
model reliably outflanks different condition of-the art
baselines for picture suggestion.
VII. ACKNOWLEDGEMENT
We would like to express our gratitude to our guide, Mr.
Muthurasu, who guided us throughout this project. We
would also like to thank our friends and family who
supported us and offered deep insight into the study. We
wish to acknowledge the help provided by the technical
and support staff in the Computer Science department of
SRM Institute of Science and Technology. We would also
like to show our deep appreciation to our supervisors who
helped us to finalize our project.
REFERENCES
[1] FlickrStatistics.
https://expandedramblings.com/index.php/ flickr-
stats/, 2017. [Online; accessed 20-Jan-2018].
[2] G. Adomavicius and A. Tuzhilin. Toward the next
generation of recommender systems: A survey of the
state-of-the-art and possible extensions. TKDE,
17(6):734–749, 2005.
[3] Anagnostopoulos, R. Kumar, and M. Mahdian.
Influence and correlation in social networks. In
KDD, pages 7–15. ACM, 2008.
[4] D. Bahdanau, K. Cho, and Y. Bengio. Neural
machine translation by jointly learning to align
and translate. In ICLR, 2015.
[5] J. Chen, H. Zhang, X. He, L. Nie, W. Liu, and T.-S.
Chua. Attentive collaborative filtering: Multimedia
recommendation with item- and component-level
attention. In SIGIR, pages 335–344. ACM,2017.
[6] T. Chen, X. He, and M.-Y. Kan. Context-aware image
tweet modelling and recommendation. In MM,
pages 1018–1027. ACM,2016.
[7] T.-S. Chua, J. Tang, R. Hong, H. Li, Z. Luo, and Y.
Zheng. Nus- wide: a real-world web image
database from national university of singapore. In
MM, page 48. ACM, 2009.
[8] P. Cui, X. Wang, J. Pei, and W. Zhu. A survey on
network embedding. TKDE,2018.
[9] S. Deng, L. Huang, G. Xu, X. Wu, and Z. Wu. On deep
learning for trust-aware recommendations in
social networks. TNNLSS, 28(5):1164–1177, 2017.
[10] L. Gatys, A. S. Ecker, and M. Bethge. Texture
synthesis using convolutional neural networks. In
NIPS, pages 262–270, 2015.
[11] L. A. Gatys, A. S. Ecker, and M. Bethge. Image style
transfer using convolutional neural networks. In
CVPR, pages 2414–2423, 2016.
[12] L. A. Gatys, A. S. Ecker, M. Bethge, A. Hertzmann,
and E. Shecht- man. Controlling perceptual factors
in neural style transfer. In CVPR, pages 3985–
3993, 2017.
[13] G. Guo, J. Zhang, and N. Yorke-Smith. A novel
recommendation model regularized with user trust
and item ratings. TKDE, 28(7):1607–1620, 2016.
[14] R. He, C. Fang, Z. Wang, and J. McAuley. Vista: a
visually, socially, and temporally-aware model for
artistic recommendation. In Recsys, pages 309–316.
ACM, 2016.
[15] R. He and J. McAuley. Vbpr: Visual bayesian
personalized ranking from implicit feedback. In
AAAI, pages 144–150, 2016.
[16] X. He, Z. He, J. Song, Z. Liu, Y.-G. Jiang, and T.-S. Chua.
Nais: Neu- ral attentive item similarity model for
recommendation. TKDE, 2018.

[17] X. He, L. Liao, H. Zhang, L. Nie, X. Hu, and T.-S. Chua.
Neural collaborative filtering. In WWW, pages 173–
182, 2017.
[18] B. Hu, C. Shi, W. X. Zhao, and P. S. Yu. Leveraging meta-
path based context for top-n recommendation with a
neural co- attention model. In SIGKDD, pages 1531–
1540. ACM, 2018.
[19] L. Itti, C. Koch, and E. Niebur. A model of saliency-
based visual attention for rapid scene analysis. PAMI,
20(11):1254–1259, 1998.
[20] M. Jamali and M. Ester. A matrix factorization
technique with trust propagation for recommendation
in social networks. In RecSys, pages 135–142. ACM,
2010.
[21] M. Jiang, P. Cui, F. Wang, W. Zhu, and S. Yang. Scalable
recommendation with social contextual information.
TKDE, 26(11):2789– 2802, 2014.
[22] T. N. Kipf and M. Welling. Semi-supervised
classification with graph convolutional networks. In
ICLR, 2017.
[23] Y. Koren. Factorization meets the neighborhood: a
multifaceted collaborative filtering model. In KDD,
pages 426–434. ACM, 2008.
[24] Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet
classification with deep convolutional neural
networks. In NIPS, pages 1097–1105, 2012.
[25] Lei, D. Liu, W. Li, Z.-J. Zha, and H. Li. Comparative deep
learning of hybrid representations for image
recommendations. In CVPR, pages 2545–2553, 2016.
[26] J. Li, M.-T. Luong, and D. Jurafsky. A hierarchical neural
autoen- coder for paragraphs and documents.
arXiv:1506.01057, 2015.
[27] D. C. Liu, S. Rogers, R. Shiau, D. Kislyuk, K. C. Ma, Z.
Zhong,
[28] J. Liu, and Y. Jing. Related pins at pinterest: The
evolution of a real-world recommender system. In
WWW, pages 583–592, 2017.
[29] Q. Liu, Y. Zeng, R. Mokhosi, and H. Zhang. Stamp: short-
term attention/memory priority model for session-
based recommendation. In SIGKDD, pages 1831–
1839. ACM, 2018.
[30] P. Loyola, C. Liu, and Y. Hirate. Modeling user session
and intent with an attention-based encoder-decoder
architecture. In RecSys, pages 147–151. ACM, 2017.
[31] H. Ma, D. Zhou, C. Liu, M. R. Lyu, and I. King.
Recommender systems with social regularization. In
WSDM, pages 287–296. ACM, 2011.
[32] Mnih and R. R. Salakhutdinov. Probabilistic matrix
factorization. In NIPS, pages 1257–1264, 2008.
[33] W. Niu, J. Caverlee, and H. Lu. Neural personalized
ranking for image recommendation. In WSDM,
pages 423–431. ACM, 2018.
[34] W. Pan and Z. Ming. Collaborative
recommendation with multi- class preference
context. IEEE Intelligent Systems, 32(2):45–51,
2017.
[35] B. Perozzi, R. Al-Rfou, and S. Skiena. Deepwalk:
Online learning of social representations. In KDD,
pages 701–710. ACM, 2014.
[36] X. Qian, H. Feng, G. Zhao, and T. Mei. Personalized
recommendation combining user interest and
social circle. TKDE, 26(7):1763– 1777, 2014.
[37] S. Rendle. Factorization machines with libfm. TIST,
3(3):57, 2012.
[38] S. Rendle, C. Freudenthaler, Z. Gantner, and L.
Schmidt-Thieme. Bpr: Bayesian personalized
ranking from implicit feedback. In UAI, pages 452–
461. AUAI Press, 2009.
[39] S. Seo, J. Huang, H. Yang, and Y. Liu. Interpretable
convolutional neural networks with dual local and
global attention for review rating prediction. In
Recsys, pages 297–305. ACM, 2017.
[40] K. Simonyan and A. Zisserman. Very deep
convolutional networks for large-scale image
recognition. In ICLR, 2015.
[41] P. Sun, L. Wu, and M. Wang. Attentive recurrent
social recommendation. In SIGIR, pages 185–194.
ACM, 2018.
[42] J. Tang, M. Qu, M. Wang, M. Zhang, J. Yan, and
Q. Mei. Line: Large-scale information network
embedding. In WWW, pages 1067–1077, 2015.
[43] J. Tang, X. Shu, G.-J. Qi, Z. Li, M. Wang, S. Yan, and R.
Jain. Tri- clustered tensor completion for social-
aware image tag refinement. PAMI, 39(8):1662–
1674, 2017.
[44] Y. Tay, A. T. Luu, and S. C. Hui. Multi-pointer co-
attention networks for recommendation. In
SIGKDD, pages 2309–2318. ACM, 2018.
[45] P. Velickovic, G. Cucurull, A. Casanova, A. Romero,
P. Lio, and
[46] Y. Bengio. Graph attention networks. In ICLR,
2018.

[47] D. Wang, P. Cui, and W. Zhu. Structural deep network
embedding. In KDD, pages 1225–1234. ACM, 2016.
[48] S. Wang, Y. Wang, J. Tang, K. Shu, S. Ranganath, and H.
Liu. What your images reveal: Exploiting visual
contents for point-of-interest recommendation. In
WWW, pages 391–400, 2017.
[49] L. Wu, Y. Ge, Q. Liu, E. Chen, R. Hong, J. Du,and
M. Wang. Modeling the evolution of users’ preferences
and social links in social networking services. TKDE,
29(6):1240–1253, 2017.
[50] L. Wu, P. Sun, R. Hong, Y. Ge, and M. Wang.
Collaborative neural social recommendation. TSMC:
Systems, 2019.
[51] J. Xiao, H. Ye, X. He, H. Zhang, F. Wu, and T.-S. Chua.
Attentional factorization machines: Learning the
weight of feature interactions via attention networks.
In IJCAI, pages 3119–3125.
[52] K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R.
Salakhudinov,
[53] R. Zemel, and Y. Bengio. Show, attend and tell: Neural
image caption generation with visual attention. In
ICML, pages 2048– 2057, 2015.
[54] Z. Yang, D. Yang, C. Dyer, X. He, A. J. Smola, and E. H.
Hovy. Hierarchical attention networks for document
classification. In HLT-NAACL, pages 1480–1489, 2016.
[55] F. Zhang, N. J. Yuan, D. Lian, X. Xie, and W.-Y. Ma.
Collaborative knowledge base embedding for
recommender systems. In KDD, pages 353–362. ACM,
2016.
[56] Q. Zhang, J. Wang, H. Huang, X. Huang, and Y. Gong.
Hashtag recommendation for multimodal microblog
using co-attention network. In IJCAI, pages 3420–3426,
2017.
[57] S. Zhang, L. Yao, A. Sun, and Y. Tay. Deep learning based
recommender system: A survey and new perspectives.
CSUR, 52(1):5, 2019.
[58] S. Zhang, L. Yao, and X. Xu. Autosvd++: An efficient
hybrid collaborative filtering model via contractive
auto-encoders. In SIGIR, pages 957– 960. ACM, 2017.
[59] Z. Zhao, H. Lu, D. Cai, X. He, and Y. Zhuang.User
preference learning for online social recommendation.
TKDE, 28(9):2522– 2534, 2016.

IRJET - An Intelligent Recommendation for Social Contextual Image using Hybrid Model

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to IRJET - An Intelligent Recommendation for Social Contextual Image using Hybrid Model

Similar to IRJET - An Intelligent Recommendation for Social Contextual Image using Hybrid Model (20)

More from IRJET Journal

More from IRJET Journal (20)

Recently uploaded

Recently uploaded (20)

IRJET - An Intelligent Recommendation for Social Contextual Image using Hybrid Model