Filter unwanted messages from walls and blocking non legitimate users in osn

8
International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print), ISSN 0976 - 6375(Online), Volume 6, Issue 5, May (2015), pp. 47-54© IAEME 47 FILTER UNWANTED MESSAGES FROM WALLS AND BLOCKING NON-LEGITIMATE USERS IN OSN Pallavi Shinde 1 , Prof. Vishal Mogal 2 1,2 Department of Computer Engineering, RMD Sinhgad School of Engineering, Warje, Pune-58, India Savitribai Phule Pune University, ABSTRACT In recent years, on-line Social Networks (OSNs) became a crucial part of daily life. Users build particular networks to represent their social relationships. Users are able to upload and share information associated to their personal lives. The privacy risks of such behaviour are typically unnoticed. Nowadays OSNs give little or no support to stop unwanted messages on user walls. For that purpose, a new system is designed to permit OSN users to have a direct control on the messages posted on their walls. This can be achieved through a flexible rule based system, that allows users to customise the filtering criteria to be applied to their walls, and a Machine Learning (ML) primarily based soft classifier mechanically labelling messages in support of content based filtering. The system make use of a ML soft classifier to enforce customizable content-dependent Filtering Rules (FRs). And also the flexibility of the system in terms of filtering choices is increased through the management of Blacklists. Filtered wall is a system to filter undesired messages from OSN walls. This system approach decides when user should be inserted into a black list. The proposed system offers security to the On-line Social Networks. Keywords: Online Social Network (OSN), Machine Learning, Information Filtering, Content- based Filtering. 1. INTRODUCTION Today’s life is totally based on Internet. Now a days people cannot imagine life without Internet. Information and communication technology plays vital role in today’s online networked society. It has affected the online interaction between different users. Online Social networks (OSNs) provide platform to meet different users and share information with them. Communication on these web sites involves exchange of different content like text, image, audio and video. A social network include personal messaging, blogs, chat facility, photos sharing facility and other ways to share text and multimedia content. A wall may be a section in online site user profile where others can post INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY (IJCET) ISSN 0976 – 6367(Print) ISSN 0976 – 6375(Online) Volume 6, Issue 5, May (2015), pp. 47-54 © IAEME: www.iaeme.com/IJCET.asp Journal Impact Factor (2015): 8.9958 (Calculated by GISI) www.jifactor.com IJCET © I A E M E

Transcript of Filter unwanted messages from walls and blocking non legitimate users in osn

Page 1: Filter unwanted messages from walls and blocking non legitimate users in osn

International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print),

ISSN 0976 - 6375(Online), Volume 6, Issue 5, May (2015), pp. 47-54© IAEME

47

FILTER UNWANTED MESSAGES FROM WALLS AND

BLOCKING NON-LEGITIMATE USERS IN OSN

Pallavi Shinde1, Prof. Vishal Mogal

2

1,2Department of Computer Engineering,

RMD Sinhgad School of Engineering, Warje, Pune-58, India

Savitribai Phule Pune University,

ABSTRACT

In recent years, on-line Social Networks (OSNs) became a crucial part of daily life. Users

build particular networks to represent their social relationships. Users are able to upload and share

information associated to their personal lives. The privacy risks of such behaviour are typically

unnoticed. Nowadays OSNs give little or no support to stop unwanted messages on user walls. For

that purpose, a new system is designed to permit OSN users to have a direct control on the messages

posted on their walls. This can be achieved through a flexible rule based system, that allows users to

customise the filtering criteria to be applied to their walls, and a Machine Learning (ML) primarily

based soft classifier mechanically labelling messages in support of content based filtering. The

system make use of a ML soft classifier to enforce customizable content-dependent Filtering Rules

(FRs). And also the flexibility of the system in terms of filtering choices is increased through the

management of Blacklists. Filtered wall is a system to filter undesired messages from OSN walls.

This system approach decides when user should be inserted into a black list. The proposed system

offers security to the On-line Social Networks.

Keywords: Online Social Network (OSN), Machine Learning, Information Filtering, Content- based

Filtering.

1. INTRODUCTION

Today’s life is totally based on Internet. Now a days people cannot imagine life without

Internet. Information and communication technology plays vital role in today’s online networked

society. It has affected the online interaction between different users. Online Social networks (OSNs)

provide platform to meet different users and share information with them. Communication on these

web sites involves exchange of different content like text, image, audio and video. A social network

include personal messaging, blogs, chat facility, photos sharing facility and other ways to share text

and multimedia content. A wall may be a section in online site user profile where others can post

INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING &

TECHNOLOGY (IJCET)

ISSN 0976 – 6367(Print)

ISSN 0976 – 6375(Online)

Volume 6, Issue 5, May (2015), pp. 47-54

© IAEME: www.iaeme.com/IJCET.asp

Journal Impact Factor (2015): 8.9958 (Calculated by GISI)

www.jifactor.com

IJCET

© I A E M E

Page 2: Filter unwanted messages from walls and blocking non legitimate users in osn

International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print),

ISSN 0976 - 6375(Online), Volume 6, Issue 5, May (2015), pp. 47-54© IAEME

48

messages. This OSN wall is a public writing space so others can view what has been written on wall.

So, in online sites there is possibility of posting illegal or undesirable messages on wall which is

visible to others too. There is a requirement to develop a lot of security techniques for different

communication technologies, particularly online social networks. Networking sites provide very

little support to prevent unwanted messages on user walls. Consider for example, facebook permits

users to state who is authorized and who is not authorized to insert messages in their walls i.e.

friends, friends of a friend (FOAF) or defined group of friends.

But there is no any content based preference for messages like sports, politics etc no matter of

the user who post them [8]. So it is impossible to prevent undesired messages. So, with the shortage

of classification or filtering tools, the user receives all messages posted by the users he or she

follows. So disadvantages of existing system are as follows-

LIMITATIONS OF EXISTING SYSTEM

1. However, no content-based preferences are supported and therefore it is not possible to prevent

undesired messages. No matter user who post them.

2. Providing this service is not only a matter of using previously defined web content mining

techniques for a different application, rather it requires to design ad-hoc classification

strategies.

SYSTEM ARCHITECTURE OF EXISTING SYSTEM

Fig. 1: System Architecture of Existing System

Page 3: Filter unwanted messages from walls and blocking non legitimate users in osn

International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print),

ISSN 0976 - 6375(Online), Volume 6, Issue 5, May (2015), pp. 47-54© IAEME

49

So, to control this type of activity and prevent the unwanted messages which are written on user’s

wall we can implement filtering rules (FR) in our system. Also, Black List (BL) will maintain in this

system. In most cases, the user receives a noisy stream of updates from other users.

Our main aim behind this research is to filter unwanted messages from user wall in order to

improve the security and efficiency. The main idea of proposed system is to support for content

based preferences. We utilize the machine learning text categorization techniques based soft

classifier automatically labelling messages with the help of content based filtering. To classify the

text for labelling messages by using the short text classifier (STC). Short text classifier are

concentrated in the extraction and selection of a set of characterizing features.

So, in proposed mechanism, a user can specify what contents should not be displayed on

his/her wall, by specifying a set of filtering rules. FRs are permitted to specify filtering conditions

based on user profiles. In addition, system provides the support for user defined blacklist means list

of users that are temporarily prevented to post any kind of messages on user wall. We have using the

wordNet dictionary in our project which gives the synonyms of a particular word. By using the

wordNet dictionary we have increased the robustness of the system.

2. LITURATURE SURVEY

Our related work has using content-based filtering and policy based personalization to filter

unwanted contents in user’s space.

Content-based filtering

In content based filtering, each user is assumed to operate independently. As a result, a

content-based filtering system selects information items based on the correlation between the content

of the items and the user preferences [1, 8].

P.W. Foltz and S.T. Dumais [1] presented information retrieval (IR) techniques. There is no

any individual based filtering. In our approach, we have used information filtering (IF). Information

retrieval is very closely related to to information filtering. User preferences in information filtering

typically represent long term interest. While queries in information retrieval tend to represent short

term interest. Information filtering is typically applied to stream of incoming data, while in

information retrieval, changes in databases do not occur often. Filtering involves process of

removing information from stream, while IR involves process of finding information in that stream.

Policy based personalization

Policy based personalization is applicable in many different contexts. It adapts a service in

specific context according user defined policies. In online social networking sites user oriented

policies can define how communication between two parties or more can be handled. The policy

based personalization system is focuses on Twitter. It assigns a category to each tweet and shows

only those tweet to the user which are of his interest [2, 8]. Policy based personalization represent the

ability of the user to filter wall messages according to filtering criteria suggested by him.

B. Sriram, D. Fuhry, E. Demir, H. Ferhatosmanoglu, and M. Demirbas [2], this paper

describes classification of tweets into general but important categorizes by using the author

information and features within tweet. But our approach permits setting of FRs according to a variety

of criteria and classify the text to predefined set of classes like sports, politics etc.

L. Fang and K. LeFevre [3], this paper is related to privacy control but no facility for

stopping anyone for posting something on wall. Our approach can stop posting particular categories

as per user’s choice.

Page 4: Filter unwanted messages from walls and blocking non legitimate users in osn

International Journal of Computer Engineering and Technology (IJCET), ISSN 0976

ISSN 0976 - 6375(Online), Volume 6, Issue 5, May (2015), pp.

Fong, P.W.L., Anwar, M.M., Zhao, Z.

based, history based. So that it is time consuming.

policy based personalization.

3. METHODOLOGY

The section is divided into following parts.

1) The first section shows the basic idea behind the approach.

2) The second section proposes an algorithm to filter out unwanted messages.

3.1 System Architecture

3.2 Algorithm

1. Post the message.

2. Load the model file in application.

3. Create instance for each category.

4. Classify the message and get the relevance of entered message with each category.

5. Checks for blocking/filtering criteria according

6. If message follows any of the condition then message gets filtered out.

7. Identify the number of attempts over or not.

8. If attempts get over then find the number of days user account

International Journal of Computer Engineering and Technology (IJCET), ISSN 0976

6375(Online), Volume 6, Issue 5, May (2015), pp. 47-54© IAEME

50

Fong, P.W.L., Anwar, M.M., Zhao, Z. [4], this paper describes policies such as topology

. So that it is time consuming. Our approach presents content based filte

The section is divided into following parts.

The first section shows the basic idea behind the approach.

The second section proposes an algorithm to filter out unwanted messages.

Fig.2: System Architecture

Load the model file in application.

Create instance for each category.

Classify the message and get the relevance of entered message with each category.

ng/filtering criteria according to message category, gender,

If message follows any of the condition then message gets filtered out.

Identify the number of attempts over or not.

If attempts get over then find the number of days user account needs to be blocked.

International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print),

© IAEME

his paper describes policies such as topology

Our approach presents content based filtering and

The second section proposes an algorithm to filter out unwanted messages.

Classify the message and get the relevance of entered message with each category.

gender, age, threshold.

needs to be blocked.

Page 5: Filter unwanted messages from walls and blocking non legitimate users in osn

International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print),

ISSN 0976 - 6375(Online), Volume 6, Issue 5, May (2015), pp. 47-54© IAEME

51

9. Block the user temporarily for blocking duration.

10. If the user is blocked temporarily by its n/2 friends then block the user permanently.

11. If message not belonging to the blocking criteria then post the message on the OSN wall.

4. RESULTS

4.1 Input Dataset Post enter by the user is the input data. We have used arff file (Attribute Relationship File

Format). This file contains messages categories as other, politics, bollywood, sports, vulgar,

violence.

4.2 Outcomes

Following snapshots are showing results for practical work done. User name P’s profile as

shown below. Like facebook, our OSN also has options as news feed, requests, friends, find friends,

friend of friend. Also our OSN has options like filtered posts, filter rules.

Fig. 3: User Profile of OSN

In filter rule option, user can set the categories which he/she doesn’t want to display on

his/her profile. User can also set threshold, gender, age etc. Threshold is used for blocking purpose.

Page 6: Filter unwanted messages from walls and blocking non legitimate users in osn

International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print),

ISSN 0976 - 6375(Online), Volume 6, Issue 5, May (2015), pp. 47-54© IAEME

52

Fig. 4: Filter Rules of OSN

Below snapshot shows that, user name Komal doesn’t want sport category message but some

of her friend post the sport category. So message has popped as sports category is blocked.

Fig. 5: Sports category blocked

Below snapshot shows that, sport category message had been posted 3 times, and threshold

was set as 0.7. Therefore, user got message as “You are blocked for another 5 days.”

Page 7: Filter unwanted messages from walls and blocking non legitimate users in osn

International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print),

ISSN 0976 - 6375(Online), Volume 6, Issue 5, May (2015), pp. 47-54© IAEME

53

Fig. 6: Temporary Blocking of User

Permanent blocking of user is shown in below snapshot.

Fig. 7: Permanent blocking of user

Page 8: Filter unwanted messages from walls and blocking non legitimate users in osn

International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print),

ISSN 0976 - 6375(Online), Volume 6, Issue 5, May (2015), pp. 47-54© IAEME

54

5. CONCLUSION

This paper describes our work to provide unwanted message filtering for social networks. We

have given a system to filter undesired messages from OSN walls. This system approach decides

when user should be inserted into a black list. The system GUI and a set of tools which make

blacklists and filter rules specifications more easy and simple. We have used the wordNet dictionary

in our project which gives the synonyms of a particular word. By using the wordNet dictionary we

have increased the robustness of the system. We would prefer to remark that the system proposed

during this paper represents simply the core set of functionalities required to produce a sophisticated

tool for OSN message filtering.

REFERENCES

1. P.W. Foltz and S.T. Dumais, Personalized Information Delivery: An Analysis of Information

Filtering Methods, Comm. ACM, vol. 35, no. 12, pp. 51-60, 1992.

2. B. Sriram, D. Fuhry, E. Demir, H. Ferhatosmanoglu, and M. Demirbas, “Short Text

Classification in Twitter to Improve Information Filtering,” Proc. 33rd Int’l ACM SIGIR Conf.

Research and Development in Information Retrieval (SIGIR ’10), pp. 841-842, 2010.

3. Fang, L., LeFevre, K., Privacy wizards for social networking sites; In: WWW 10: Proceedings

of the 19th international conference on World Wide Web, pp. 351360. ACM, NewYork, NY,

USA, 2010.

4. Fong, P.W.L., Anwar, M.M., Zhao, Z., A privacy preservation model for facebook-style social

network systems; In: Proceedings of 14th European Symposium on Research in Computer

Security (ESORICS), pp. 303320, 2009.

5. F. Sebastiani, Machine Learning in Automated Text Categorization, ACM Computing Surveys,

vol. 34, no. 1, pp. 1-47, 2002.

6. M. Vanetti, E. Binaghi, B. Carminati, M. Carullo, and E. Ferrari, Content- Based Filtering in

On-Line Social Networks, Proc. ECML/PKDD Workshop Privacy and Security Issues in Data

Mining and Machine Learning( PSDML 10), 2010.

7. M. Chau and H. Chen, A Machine Learning Approach to Web Page Filtering Using Content

and Structure Analysis, Decision Support Systems, vol. 44, no. 2, pp. 482-494, 2008.

8. Marco Vanetti, Elisabetta Binaghi, Elena Ferrari, Barbara Carminati, and Moreno Carullo, “A

System to Filter Unwanted Messages from OSN User Walls”, IEEE Transactions On

Knowledge And Data Engineering, Vol. 25, No. 2, February 2013.

9. Mrs. L.Rajeswari and Dr.S.S.Dhenakaran, “Page Access Coefficient Algorithm For

Information Filtering In Social Network” International journal of Computer Engineering &

Technology (IJCET), Volume 4, Issue 3, 2013, pp. 60 - 69, ISSN Print: 0976 – 6367, ISSN

Online: 0976 – 6375.

10. Muhanad A. Al-Khalisy and Dr.Haider K. Hoomod, “Posn: Private Information Protection In

Online Social Networks” International journal of Computer Engineering & Technology

(IJCET), Volume 4, Issue 2, 2013, pp. 340 - 355, ISSN Print: 0976 – 6367, ISSN Online: 0976

– 6375.

11. Mr. Yogesh P Murumkar and Prof. Yogesh B. Gurav, “Sampling Online Social Networks

Using Outlier Indexing” International journal of Computer Engineering & Technology

(IJCET), Volume 5, Issue 6, 2014, pp. 11 - 18, ISSN Print: 0976 – 6367, ISSN Online: 0976 –

6375.