You are on page 1of 5

IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES, VOLUME 4, ISSUE 2, JULY /2017

ISSN (ONLINE): 2394-8442

PRODUCT RECOMMENDATION ON SOCIAL MEDIA WITH


USING UNIFIED MATRIX ALGORITHM
B.LAKSHMIDEVI1 AND M.SHANMUGHAM2
[1, 2]
Christ College of Engineering and Technology, Pondicherry, India
[1]
lakshmi02devi@gmail.com, [2] arunmca01@gmail.com

ABSTRACT.

With the boom of social media, it is a very popular trend for people to share what they are doing with
friends across various social networking platforms. I have a vast amount of descriptions, comments, and ratings for
local service. The information is valuable for new users to judge whether the services meet their requirement before
partaking. I propose a user service rating prediction approach by exploring social user rating behaviors. My opinion
the rating behavior in recommender system could be embodied in these 1)when user rated the item,2)what the rating
is 3) what the item is, 4) what the user interest that I could dig from his/her rating records is, 5) how the user rating
behavior diffuses among his/her social friends. I propose a concept of the rating schedule to represent user rating
behaviors. I propose the factor of interpersonal rating behavior diffusion to deep understand user rating behaviors.
User personal interest, interpersonal interest, interpersonal rating behavior similarity, interpersonal rating behavior
diffusion into a unified matrix factorized framework.

Index TermsData mining, recommender system, social networks, social user behaviour.

1. INTRODUCTION
Despite all the potential advantages of formal performance appraisal, there are also potential drawbacks. It has been noted that determining the
relationship between individual job performance and organizational performance can be a difficult task. Generally, there are two overarching
problems from which several complications spawn. One of the problem with formal performance appraisals is there can detrimental effects to
the organization involved if the appraisals are not used appropriately.

2. PROBLEM DEFINITION
Despite all the potential advantages of formal performance appraisal, there are also potential drawbacks. It has been noted that determining the
relationship between individual job performance and organizational performance can be a difficult task. Ineffective if the performance appraisals
system does bot correspond with the organizational culture and system. Infrequent feedback if the primary goal of the process is to identify and
resolve performance issues, executing the process annually is silly. A quality assessment/control program anywhere else in the business would
operate in the real time. At the very minimum, formal feedback needs to be given quarterly. Lack of accountability - managers are not measured
or held accountable for providing accurate feedback. Dont assess actual performance most of the assessment that mangers complete focuses
on the person, including characterizations of their personal traits.

3. EXISTING SYSTEM
Despite all the potential advantages of formal performance appraisal, there are also potential drawbacks. It has been noted that
determining the relationship between individual job performance and organizational performance can be a difficult task. Generally, there are two
overarching problems from which several complications spawn. One of the problems with formal performance appraisal is there can detrimental
effects to the organization involved if the appraisals are not used appropriately.

To Cite This Article: B.LAKSHMIDEVI AND M.SHANMUGHAM,. PRODUCT RECOMMENDATION


ON SOCIAL MEDIA WITH USING UNIFIED MATRIX ALGORITHM. Journal for Advanced
Research in Applied Sciences ;Pages: 78-82
79. B.LAKSHMIDEVI AND M.SHANMUGHAM,. PRODUCT RECOMMENDATION ON SOCIAL MEDIA WITH
USING UNIFIED MATRIX ALGORITHM. Journal for Advanced Research in Applied Sciences; Pages: 78-82

4. PROPOSED SYSTEM
In Employee Appraisal Exposure System provided to overcome the existing system problems of the performance appraisal. It provides an
effective result for user to evaluate the performance appraisal of the employee.
The following are the problems resolved by the proposed system.

Ineffective if the performance appraisals system does not correspond with the organizational culture and system.
Infrequent feedback.
Lack of accountability.
Dont assess actual performance.

MODULES PURPOSE AND DESCRIPTIONS

Post product
Recommend product
Rank product
Write review

5. CONCLUSION
In this project, we propose user-service rating prediction approach by exploring user rating behaviors with considering four social
network factors: user personal interest(related to user and the items topic) interpersonal interest similarity (related to user interest), interpersonal
rating behavior similarity(related to users rating habits), and interpersonal rating behavior diffusion (related to users behavior diffusions). A
concept of the rating schedule is proposed to represent user daily rating behavior. The similarity between user rating schedules is utilized to
represent interpersonal rating behavior similarity. The factor of interpersonal rating behavior diffusion is proposed to deep understand users
rating behaviors. I explore the users social circle, and split the social network into three components, direct friends, mutual friends, and the
indirect friends, to deep understand social users rating behavior diffusions.

FUTURE ENHANCEMENTS

I propose a concept of the rating schedule to represent user daily rating behavior. We leverage the similarity between user rating
schedules to represent interpersonal rating behavior similarity. Unsuitable for real life applications because of the increased computational and
communication costs. The proposed system three factors interpersonal interest similarity interpersonal rating behavior similarity, and
interpersonal rating behavior diffusion together to directly constrain user latent features which can reduce the time complexity.

SCREEN SHOTS

USER HISTORY

NEW USER
80. B.LAKSHMIDEVI AND M.SHANMUGHAM,. PRODUCT RECOMMENDATION ON SOCIAL MEDIA WITH
USING UNIFIED MATRIX ALGORITHM. Journal for Advanced Research in Applied Sciences; Pages: 78-82

HOME PAGE

Description: This Module is searching for Home page on posted friends.

PRODUCT RECOMMEND BY FRIENDS

RECOMMEND PRODUCT

Description: This Modules is Used for sharing to recommend the product of user rating.

WRITE REVIEWS

Description: This module is used for Product reviews and feedback product from the user reviews. Coding
81. B.LAKSHMIDEVI AND M.SHANMUGHAM,. PRODUCT RECOMMENDATION ON SOCIAL MEDIA WITH
USING UNIFIED MATRIX ALGORITHM. Journal for Advanced Research in Applied Sciences; Pages: 78-82

Rank update.aspx:

using System;
usingSystem.Collections;
using System.Configuration;
using System.Data;
using System.Linq;
using System.Web;
usingSystem.Web.Security;
using System.Web.UI;
usingSystem.Web.UI.HtmlControls;
using System.Web.UI.WebControls;
usingSystem.Web.UI.WebControls.WebParts;
usingSystem.Xml.Linq;

publicpartialclassDefault2 : System.Web.UI.Page
{
sqldbiodb = newsqldbio();

protectedvoidPage_Load(object sender, EventArgs e)


{
stringuserid = null;
if (Session["userid"] == null)
{
Response.Redirect("Default.aspx");
}
else
{
userid = Session["userid"].ToString();
// lbl_user.Text = userid;
Labellbl_user = this.Master.FindControl("lbl_user") asLabel;
lbl_user.Text = userid;
}

inttotpost = db.GetLastPostIDOfUser(userid);
lbl_userpost.Text = "Posts: " + totpost;

publicvoiduploadtoserver()
{
if (IsPostBack)
{
BooleanfileOK = false;
String path = Server.MapPath("~/images/UploadedImages/");

if (FileUpload1.HasFile)
{
StringfileExtension = System.IO.Path.GetExtension(FileUpload1.FileName).ToLower();
String[] allowedExtensions = { ".gif", ".png", ".jpeg", ".jpg" };
for (int i = 0; i <allowedExtensions.Length; i++)
{
if (fileExtension == allowedExtensions[i])
{
fileOK = true;
}
}
}

if (fileOK)
{
try
{
FileUpload1.PostedFile.SaveAs(path + FileUpload1.FileName);
// db.MessageBox(this,"File uploaded!");
}
catch (Exception ex)
{
82. B.LAKSHMIDEVI AND M.SHANMUGHAM,. PRODUCT RECOMMENDATION ON SOCIAL MEDIA WITH
USING UNIFIED MATRIX ALGORITHM. Journal for Advanced Research in Applied Sciences; Pages: 78-82

db.MessageBox(this, "File could not be uploaded.");


}
}

else
{
db.MessageBox(this, "Cannot accept files of this type.");
}
}
}

REFERENCES
[1] G. Salton, A. Wong, and C.-S.Yang, A vector space model forautomatic indexing, Commun. ACM, vol. 18, no. 11, pp. 613620,1975.
[2] Y. Xi-Wei, Feature extension for short text, in Proc. 3rd Int. Symp.Comput. Sci. Comput. Technol., 2010, pp. 338341.
[3] X. Hu, L. Tang, and H. Liu, Enhancing accessibility of microblogging messages using semantic knowledge, in Proc. 20th ACM Int.Conf.
Inf. Knowl. Manag.,, 2011, pp. 24652468.
[4] D. Ramage, S. T. Dumais, and D. J. Liebling, Characterizingmicroblogs with topic models, in Proc. 4th Int. Conf. Weblogs Social Media,
2010, pp. 130137.
[5] O. Jin, N. N. Liu, K. Zhao, Y. Yu, and Q. Yang, Transferring topical knowledge from auxiliary long texts for short text clustering,in Proc.
20th ACM Int. Conf. Inf. Knowl. Manag., 2011, pp. 775784.
[6] Q. Diao, J. Jiang, F. Zhu, and E.-P.Lim, Finding bursty topics from microblogs, in Proc. 50th Annu.Meet.Assoc.Comput.Linguistics:Long
Papers-Vol. 1., 2012, pp. 536544.
[7] L. Deng, A tutorial survey of architectures, algorithms, and applications for deep learning, APSIPA Trans. Signal Inf. Process.,vol. 3, p.
e2, 2014.
[8] G. Hinton and R. Salakhutdinov, Reducing the dimensionality of data with neural networks, Sci., vol. 313, no. 5786, pp. 504507,Jul.
2006.
[9] R. Salakhutdinov and G. Hinton, Semantic hashing, Int. J.Approx. Reasoning, vol. 50, no. 7, pp. 969978, Jul. 2009.

ACKNOWLEDGEMENTS

I thank my HOD Mr.P.Rajapandian, M.C.A., M.Phil,.M.C.S.I (Department of Computer Applications) to help us for creating this paper with his
sincere guidance and Technical Expertise in the field of communication. The help of my guide Mr.M.Shanmugam, MCA (Departmentof
Computer applications), Christ College of Engineering& Technology is really immense and once again I thank her for her great motivation. I
thank Christ College of Engineering& Technology to provide me such a standard educational environment so that I am able to understand the
minute concepts in the field of Engineering.

Ms. B.Lakshmidevi: Currently pursuing Master of Computer Applicationsin Christ College of engineering
and technology.Her area of interest is web designing and software development.

Mr.M.Shanmugham,Senior Assistant Professor in Mca from Christ college of engineering and Technology.He
is research interests include authentication, software security, usability, and network security

You might also like