IRJET- A Literature Review and Classification of Semantic Web Approaches for Web Personalization Research

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 10 | Oct 2019 www.irjet.net p-ISSN: 2395-007
© 2019, IRJET | Impact Factor value: 7.34 | ISO 9001:2008 Certified Journal | Page 307
A Literature Review and Classification of Semantic Web Approaches for
Web Personalization Research
Sahaya Chithra. E1, Dr. S. John Peter2
1Sahaya Chithra.E, Research Scholar, Department of Computer Science, St.Xavier’s college, Tirunelveli, India.
2Dr. John Peter, Associate Professor and Head, Department of Computer Science, St.Xavier’s college,
Tirunelveli, India.
-------------------------------------------------------------------------***------------------------------------------------------------------------
Abstract - Nowadays, the biggest challenge on web is how
to retrieve effectively and efficiently what has been actually
requested. Users need help for searching the relevant
information based on their preferences. Users spend a lot of
time without getting satisfactory results. It can be tedious
and time-consuming. One approach in satisfying the user is
to personalize the information available on the web, called
web Personalization. Web Personalization can be achieved
by recommending web pages to the users, or by filtering web
pages that are of interest to the users. Recommendation
systems are software tools, which support Personalization,
and its main objective is to help the individuals to select the
most promising from the Internet. Semantic web
Personalization can solve the information overload problem,
and its objective is to provide users with what they really
want or need. By considering all the benefits of the web
Personalization, this paper presents the Semantic web for
Personalization, and the classification of Semantic web
approaches used for web Personalization and its related
work in every approach.
Keywords -- Internet, Recommendation Systems,
Semantic web, web Personalization.
1. INTRODUCTION
As of January 2019, there were over 1.94 billion
websites on the Internet. The large volume of information
has made many problems that relate to the increasing
difficulty of searching in organizing, accessing, and
maintaining the relevant information. As the rapid growth
of information load on the internet, personalized
recommendation systems have become crucial tools for
finding users preferences. The most preferable
recommendation in all over the world is Spotify, Hulu,
Netflix, Pandora, Amazon, and Sigchi. Amazon and Netflix
suggest products and movies based on each user’s profile,
previous purchase history, and online behavior. Facebook
and Google news recommend news articles based on user
profiles and behavior. Companies are using recommender
systems because of increasing sales and attracting
customers with a personalized offer as a result of an
enhanced customer’s positive feedback. Recommendations
typically speed up searches and make it easier for
individuals to access own content only, and making
surprised with offers, the users would have never searched
for.
Personalization has been nowadays widely used in
e-commerce as valuable tools for personalizing purchase
recommendations. Personalization is something that every
website or app that provides a reliable interface of a user
must have. It prevents users from wasting time in access to
what they need and encourages efficient search. Various
factors help to acquire the user’s preferences when surfing
the internet. However, today’s searching tools give the
irrelevance information of many searches. Therefore, the
ultimate need nowadays is that of predicting the user needs
in order to improve the usability and user retention of a
website. Semantic web can develop languages for
expressing information in machine-readable form
therefore Semantic web is the most appropriate platform
for realizing Personalization [1].
Second section of this paper provides related work
in the area of web Personalization and then section 3 will
be devoted to survey in the area of web Personalization.
This paper continues in Section 4, which describes the
various Semantic web techniques and its pros and cons for
web Personalization.
2. RELATED WORK
P.Markellou et al., [8] proposed a framework for
personalized E-Learning based on collective usage profiles
and domain ontology. The authors distinguished two stages
online and offline tasks. An Offline task includes ontology
creation, data preparation and usage mining and online
tasks that include the production of recommendations.
Baoyao Zhou et al., [9] proposed a web usage mining
approach for semantic web personalization. Provide a
semantic web personalization needs to challenge the
technical issues on web access activities, convert them into
ontology automatically discover hierarchical relationships
from web access activities, and presume personalized
usage knowledge from the ontology. This approach
combined fuzzy logic into Formal Concept Analysis to mine
client side web usage data for automatic ontology
generation, and then applied fuzzy approximate reasoning
to deduce personalized usage knowledge from the
ontology.
Charbel Obeid Liris et al.,[10] Proposed
recommender system is an assessment tool for students’
vocational strengths and weaknesses, interests and
capabilities. This proposed ontology-based recommender

system aims to identify the student requirements, interests,
preferences, and capabilities to recommend the right major
and university for each one. To support personalization,
this study proposes a recommender system that can be
used to assist students in finding the relevant major and
university, by using the semantic web and machine
learning techniques. The Semantic web is an extension of
the current web, in which information is given in defined
meaning, enabling machines and users to cooperate [24].
Moreover, machines will become able to process and
"understand" the data. Ontology is the backbone of the
Semantic web. Ontology is a recognized and explicit
specification of a shared conceptualization. It consists of
concepts namely entities, attributes, and properties related
to a domain.
Hilal Karaman [11] proposed Hybrid System a
ReMovender, which is a content-based and Collaborative
movie recommendation system. Here collaborative missing
data prediction technique is used to compare the various
users’ interests with content information of movies. Using
ReMovender recommendation system users are requested
to rate movies on a scale from one to five. Collaborate
Filtering predicts the missing ratings data and similarities
from ratings which are given by different users. A Content-
based technique is used to correlate the movies by using a
set of movie information and provide recommendations for
the users.
Gizem Ozturk [12] proposed a hybrid system for
personalizing videos to users, which uses both
collaborative filtering and content-based approaches. By
merging different approaches, it yields more powerful
results than using pure methods individually. In this thesis,
Adsorption algorithm is enriched by the Content-based
approach for providing better suggestions. Besides using
rating archives, video and movie content information are
also used to suggest new items which help to reinforce
recommendations. The system gives better results when
the data is not sparse. That is why results with MovieLens
data is better than YouTube. Ridhika Malik, Kunjana
Vasudev and Udayan Ghose [13] proposed a Human
Resource Semantic web management System (HRSWM)
that enables the organizations to achieve their goals by
transforming disparate, fragmented data into viable
information capable of answering key questions. This study
defines a system which combines the benefits of Resource
Descriptive Framework (RDF) [24] with the high
performance of database management systems and thus
improves the performance in retrieving information at real
time.
Nizar R. Mabroukeh et al., [14] proposed a generic
framework called SemAware that integrates Semantic
information into web usage mining. Semantic information
can be combined into the pattern discovery. A Semantic
distance matrix is used in the fixed sequential pattern
mining algorithm to trim the search space and partially
relieves the algorithm from support counting. A 1st-order
Markov model is used to make the mining process and
enriched with Semantic data. Yao et al., [15] proposed a
framework which acts as an intelligent agent that
dynamically gives the recommended websites for users.
This can be learning from web usage data and users'
behavior and is called as PagePrompter. Like a guide, an
agent supports a user in navigating the website.
PagePrompter can also be used as a tool for understanding
user behaviour, the design of the website, system
performance analyzing, website designer for improving
websites and generating an adaptive website.
Punam Bedi, Harmeet Kaur and Sudeep Marwaha
[16] presented system based on temporal ontologies and
trust network, generates the recommendations across
multiple domains. The similarity measures are taken care
in the form of trust update process. In this Personalization
system, Intuitionistic Fuzzy Sets (IFS) are been used to
capture uncertainty, inherent in the recommendation
process. The tourism domain has a number of subdomains
like air travel, geography, food, entertainment, sports etc. is
taken as a landmark study. Now the case study uses two
domains destination and travel and these can be enhanced
easily for other domains. In this proposed model, the
recommendations are taken from the trustworthy agents
only and the data as well as the methods used to generate
the recommendations are with agents, making the
recommendation process transparent to the users.
3. SEMANTIC WEB FOR PERSONALIZATION
Personalization is defined as “the ability to provide
content and services tailored to individuals based on
knowledge about their preferences and behavior” or “the
use of technology and customer information to tailor
electronic commerce interactions between a business and
each individual customer”[2]. The Semantic web is an
extension of the current web in which information is given
well defined meanings that improved with processable
between machines and users. The purpose of Semantic web
is to dedicate most of tasks and decisions to machines.
Semantic web is used in web Personalization for expressing
information in a machine-readable form.
Wu et al., [3] proposed a general learning services
personalized framework. Semantic technology, ontology to
represent the learning contents and user profile are used in
this framework. Social relationships with trusted friends
are to improve the collaborating filtering algorithm to
recommend personalized learning resources for users.
Experiments showed that the proposed framework is
effective. The experiment system includes 10 courses in
computer field and a total of 3806 learning resources. This
study used Recall and Precision to determine the efficiency
of the proposed framework. This study selected 10 users
and built the user domain profile and the user social
relationship profile for each user using Generating User
Domain Knowledge algorithm and ReRanking algorithm
respectively. Mahendra Thakur and Geetika S. Pandey[4]

proposed a Personalization framework using the Semantic
web. In this study, the visitors’ navigational behavior is
updated with this semantic knowledge to create an
enhanced version of weblogs, Clogs, as well as semantic
document clusters. Clogs are in turn mined to generate
both a set of URI and category-based association rules.
Finally, the recommendation engine uses these rules, along
with the semantic document clusters in order to provide
the final, semantically enhanced set of recommendations to
the end user.
Kruti Jani and Dr.V.M Chavda [5] build and
evaluate Semantics-aware collaborative filtering movie
recommendation system using all the notions and elements
of Linked Open Data. This method collects the user’s
preferences for items, search for a set of similar
preferences by individuals, and infers rating on a particular
item based on the information gathered from neighbors.
Collaborative filtering methods first find the most similar
users to the active user and consider them as a set of the
neighbors of active user and finally predict and provide
suggestions. The goal of the prediction of the target item’s
score is for active user. The members who voted for target
item only have been studied in order to create a set of
neighbors. Standard Pearson correlation criteria are used
to evaluate the dependencies between scoring patterns of
users and active user. When the similarity of all users with
an active user is found then set of neighbors are chosen for
further process. The scores offered for target item by a set
of the neighbors can be predicted. This knowledge can be
applied to design an advanced recommendation system
with the ability to generate more individual and accurate
prediction results.
Honghua Dai and Mobasher [6] proposed a study
that provides an overview of semantic knowledge
approaches on web usage mining and personalization
practices. Semantic knowledge is the only solution to
personalize systems, which is complex objects based on
their underlying properties and attributes. Successful
integration of Semantic knowledge from different sources,
such as the content and the structure of web sites for
Personalization are discussed in this study. Ahu Sieg,
Bamshad Mobasher and Robin Burke [7] proposed a
system which utilizes the user context to personalize
search results by re-ranking the results returned from a
search engine for a given query. This study has presented a
framework for contextual information access using
ontologies and demonstrated that the Semantic knowledge
embedded in an ontology combined with long-term user
profiles can be used to effectively trim the search results
based on users’ choices and likes.
4. METHODS FOR WEB PERSONALIZATION
4.1 Collaborative Filtering System
Collaborative filtering is one of the most successful
and popular methodologies in recommendation systems.
CF technique is used to compute Semantic similarities
between users, if two users are having high Semantic
similarity, the Personalization recommendations has
been made. Collaborative filtering systems can deal bulky
of users and multiple different items. However,
traditional collaborative filtering has some limitations
such as the item sparsity and cold start problem. Lee Jae-
Won, Nam Kwang-Hyun, and Lee Sang-Goo [22] used a
Semantic match with the domain ontology, while the
traditional collaborative filtering uses an exact match to
find similar users. Therefore, this methodology solved the
item sparsity problem by mapping users and items to a
set of concepts, which are the nodes of domain ontology.
When recommending items, the effects of number of
similar users are analysed. By mapping them with
concepts, the item sparsity can be reduced. The precious
of this study is mapping items and users to a set of
concepts that are the nodes of ontology.
4.2. Content-based filtering System
When there is no or only little amount of user data is
available, Content-based filtering is used. Content-based
filtering recommends on basis of the content similarity
between items. The contents may be structured or
unstructured. Therefore, to make similarities between
objects easier the contents should be converted into
structured. The first step in Content-based filtering is to
keep a private profile for each item. Then CB finds the
similarities between the attributes or features of items,
and finally, it recommends the most similar item for an
item. Finding similarities between structured content is
straightforward whereas deciding the features or
attributes of the unstructured item is very difficult.
Content-based Personalization systems recommend items
similar to those a given user has liked in the past. Here
user profile is matched up with preferences and interests,
which are stored in past web surfing. Hilal Karaman [11]
proposed a movie recommendation system named as
ReMovender. This system makes the use of ratings given
by users to movies, demographic data of the users and
content of the movies in order to provide high
recommendations. The feature weights for different set of
individuals and movies are almost universal when this
recommendation system is based on assumption. The
result of this thesis scores 2.28, which is slightly better
than the pure content based, which scores
4.3 Ontology-based System
Ontology based techniques for web Personalization
just considers the domain ontology for Personalization
without considering the context information and
acquaintance information of the user, which may vary with
time. Personalization has made by combining the results
obtained by imposing restrictions with the user model,
which represents individual user interest. Muhammad
Shoaib, Amna Basharat [17] proposed a framework that

supports the creation of Semantic users and resources
profiles in order to map the user's personal and research
interests in an ontological format. These relations are used
to deliver knowledge including research articles,
researchers, and research groups of related fields, about
user's interests on the social web in order to create users
personalization. The users' are required to keep an updated
users profile. The ontology allows storing of the user,
group, posts, and events profile in machine processable
format. In order to enable automatically personalization
feature this research illustrated the need for ontological
data representation followed by ontology structure for
Social network data.
Ontologies offer a way to cope with these
heterogeneous representations of web resources. These
comprise the backbone of the Semantic web and appear as
a promising technology for implementing in particular e-
Learning applications. The reason ontologies are becoming
so popular is due to what they promise: “a share and
common understanding of a domain that can be
communicated between people and application systems”
[18].
4.4 Context-based Personalization
These techniques use the user preferences along
with context information of the user for personalizing the
user request. In this Context-based system, users’ result
may fluctuate depends upon the request which the user has
given. Context-based Context awareness computes a broad
range of contextual attributes such as the user’s activities,
current positions, and surrounding environments. The
Contexts are user profile, user activity, and user search
history. Jongyi Hong et al., [19] propose an agent-based
framework for providing personalized services using
context history on context-aware computing. The proposed
framework consists of data gathering layer, context
management layer, preference management layer and
application layer for providing the personalized services
based on the users' preferences. The prototype was
implemented according to each layer. The system that
offers each user with the personalized services under the
same context was displayed using PDA. This research
suggests the basic direction for the provision of the
personalized services on context-aware computing and
utilization of context history. In that, it indicated the need
or usability of context history that was not considered in
the previous researches. Additionally, this research can be
the basic direction of design and the guidelines of
development for the context-aware computing system.
However, the prototype was not completely implemented
according to the proposed framework because the
surveyed data is used instead of real sensor data due to the
constraints of tools and time. Also, the protection of
personal information or privacy needs to be considered.
4.5 Trust-based Personalization
The techniques exploit the user acquaintance
information to personalize the recommendations or search.
Trust based Personalization system is based on the concept
that acquaintances may share similar preferences. Trust-
based Personalization techniques explore an area which is
not covered in both ontology-based Personalization
techniques and context-based Personalization techniques
and may provide some interesting recommendations which
may not be provided by the prior techniques. FOAF (Friend
of a Friend) is used to make a trust for Semantic web
Personalization. FOAF is used to identify a person browsing
habits in the website. Personalization is performed by
sending user FOAF information every time a user sends the
request to the server this is done by extending the HTTP
Get method to include the parameters that point to the URL
of the user FOAF file. Carminati Barbara, Ferrari Elena, and
Perego Andrea [20] proposed a web based social network
where members are able not only to specify labels, but
also to rate existing labels. Both labels and ratings are
then used to assess the trustworthiness of resources’
descriptions and to enforce web access Personalization.
FOAF profiles can be signed to grant their authenticity, and
thus they can be effectively used as certified credentials.
Trust computation is a feature which is supported by some
online communities, mainly in order to refine
recommendations. This study it supports just four
descriptors (i.e., trustworthiness, vendor reliability,
privacy, and child safety), and it does not give users the
possibility of expressing their disagreement with claims
made by other users. Moreover, differently from our
proposal, explicit trust policies or trust relationships are
not supported, in that the trustworthiness of rating authors
is computed by the system itself.
4.6 Rule-based Personalization
These techniques use rules to extract
Personalization information. Here web usage data in the
form of logs are used to infer the rule and make
recommendations based on the matched patterns.
Designing the rule leads sometimes, updating the rule
made difficulty. Otherwise even the only little bit of web
usage data is enough for Rule-based systems comparing
other Personalization systems. Initially, a set of rules are
designed and used to make personalized
recommendations. From the session, user activities and
characteristics of other users which are stored in web
usage model are observed and using these available facets ,
Personalization is carried out. Barla Michal, Tvarozek
Michal, and Bielikov Maria [21] described a user modeling
approach based on automated acquisition of user
behaviour and its successive rule-based evaluation and
transformation into an ontological user model. A novel
method of automated user modeling for adaptive Semantic
web-based systems proposed based on comprehensive logs
of user actions with Semantics and a rule formalism

designed to support potentially elaborate navigational
patterns. An inference agent was designed a and
implemented which was driven by a rule formalism
capturing interesting patterns of user-system interaction.
All knowledge the agent requires in order to process the
log of events and update the user model is stored in these
rules, thus making the agent highly configurable and
reusable.
4.7 Hybrid Recommendation System
HRS… means combination of content based filtering,
collaborative filtering or any other filtering. Innar et al.,
[23] have presented the design and methods used in the
SMART MUSEUM platform, employing adaptive and privacy
preserving user profiling. They described recommendation
system relies on combining a Semantics/ontology based
approach with a data mining/statistics based approach.
Gizem Ozturk [12] proposed hybrid video recommendation
system. Collaborative filtering algorithm makes
recommendations with relating similarities between users.
Sparsity and cold start problem occur in pure collaborative
filtering. In order to overcome these problems, content
based filtering is added. Content-based filtering uses the
idea of suggesting similar items that match user
preferences. In order to use content-based filtering, first,
the base recommendation list is updated by removing weak
recommendations. Following this, item similarities of the
remaining list are calculated and new items are added to
make the final recommendations. Thus, collaborative
recommendations are empowered considering item
similarities. Therefore, the developed hybrid system
combines both collaborative and content-based approaches
to produce suggestions that are more effective.
5. CONCLUSIONS
Semantic web Personalization system for web
search, which not only gives user a set of personalized
pages, but also gives user a list of domains the user may be
interested in. Thus, the user can switch to diverse interests
when the user is surfing on the web for information.
Besides, the system focuses on the domains that the user is
interested in, and will not waste lots of time on searching
the information in the irrelevant domains.
Here this study presented the classification of
Semantic web approaches for web Personalization.
Semantic web incorporates machine-processable
information to support user preferences in their task.
When Personalization is applied to the Semantic web it
recommends many advantages when compared to the
traditional web. Semantic web combines Semantics with
the unstructured data on the web so that intelligent
techniques can be applied to get results that are more
proficient. Personalization based Recommendation system
is becoming increasingly popular because of social
networking and Semantic web has a great potential for
exploring new dimensions for Trust-based Personalization.
REFERENCES
[1] Brusilovsky P., Kobsa A., Nejdl W., The Adaptive web:
Methods and Strategies of web Personalization, LNCS 4321.
Springer, 2007.
[2] G. Adomavicius, A. Tuzhilin,”Personalization techniques:
a process-oriented perspective, Communications of the
ACM 48 (10) (2005) 83–90.
[3] Chanle Wu, Jiyian Wu, Yibo Chen†, Ming Xie, Xiaojun
Guo, Weichen Xiong, “Personalized Learning Service
Framework Based on Semantic Web Technologies”, IEEE
©2011, 978-1-4244-9763-8/11/$26.00
[4] Mahendra Thakur , Geetika S. Pandey,” Performance
Based Novel Techniques for Semantic web Mining”, IJCSI
International Journal of Computer Science Issues, Vol. 9,
Issue 1, No 1, January 2012 . ISSN (Online): 1694-0814
[5] Kruti Jani and Dr.V.M Chavda ,” Personalizing Movie
Recommendation Using Semantic Contents in Collaborative
Filtering”, International Global Journal for Research
analysis , Volume-5, Issue-9, September - 2016 • ISSN No
2277 – 8160
[6] Honghua Dai, and B. Mobasher, Integrating Semantic
Knowledge with web Usage Mining for Personalization’,
Information Systems Journal, 2009, 1-28.
[7] Ahu Sieg, Bamshad Mobasher, Robin Burke “Learning
Ontology-Based User – Profiles: A Semantic Approach to
Personalized web Search” IEEE Int. Informatics Bulletin,
Nov 2007.
[8] P. Markellou, I. Mousourouli, S. Spiros, and A.Tsakalidis
(Greece) 2005. Using Semantic web Mining Technologies
for Personalied ELearning Experiences, Proceeding (461)
web-based Education.
[9] Baoyao Zhou1, Siu Cheung Hui, and Alvis C. M. Fong
2006 web Usage Mining for Semantic web Personalization.
[10] Charbel Obeid Liris, Inaya Lahoud, Hicham El Khoury
and Pierre-Antoine Champin Liris,” Ontology-based
Recommender System in Higher Education”, WWW ’18
Companion April 23-27, 2018, Lyon, France.© 2018 IW3C2
(International World Wide Web Conference Committee)
ACM ISBN 978-1-4503-5640-4/18/04.
[11] Hilal Karaman ,“ A Content Based Movie
Recommendation System Empowered By Collaborative
Missing Data Prediction”, Master Thesis, The Graduate
School Of Natural And Applied Sciences Of Middle East
Technical University, June 2010.
[12] Gizem Ozturk ,“A Hybrid Video Recommendation
System Based On A Graph-Based Algorithm”, Master thesis,
Computer Engineering Department, Middle East Technical
University. September 2010.

[13] Ridhika Malik, Kunjana Vasudev and Udayan
Ghose,”Semantic web Mining and its application in Human
Resource Management”, IJCSMS International Journal of
Computer Science & Management Studies, Vol. 11, Issue 02,
August (2011) ISSN (Online): 2231 –5268
[14] Nizar R. Mabroukeh and Christie I,”Using Domain
Ontology for Semantic web Usage Mining and Next Page
Prediction,. Ezeife CIKM’09, pg 2–6.
[15] Y.Y. Yao, H.J. Hamilton, and Xuewei Wang, “An
Intelligent Agent for web Navigation Created Using Data
Mining”, Volume 27 Issue 3, Pages 59 - 74. PagePrompter
2008.
[16] Punam Bedi, Harmeet Kaur, Sudeep Marwaha,” Trust
based Recommender System for the Semantic Web”, IJCAI-
07. 2677-2682
[17] Muhammad Shoaib, Amna Basharat ,“Ontology based
Knowledge Representation and Semantic Profiling In
Personalized Semantic Social Networking Framework”,
IEEE ©2010,978-1-4244-5540-9/10/$26.00
[18] J. Davies, D. Fensel, & F. van Harmelen, Introduction,
Towards the Semantic Web, Ontology- Driven Knowledge
Managament, John Wiley & Sons, 2003, 1-9.
[19] Hong Jongyi,-Ho Suh A, Eui , Kim Junyoung ,and Kim
Suyeon, “Context-aware system for proactive personalized
service based on context history”, ,Expert Systems with
Applications Elsevier 36 (2009) 7448–7457.
[20] Carminati Barbara, Ferrari Elena, and Perego Andrea,”
Combining social networks and Semantic web technologies
for personalizing web access, collaborative computing:
networking, applications and worksharing” Lecture Notes
of the Institute for Computer Sciences, Social Informatics
and Telecommunications Engineering, Volume 10. ISBN
978-3-642-03353-7. Springer Berlin Heidelberg, (2009), p.
126
[21] Barla Michal, Tvaroˇzek Michal,and Bielikov M´Aria “A,
Rule-based user characteristics acquisition from logs with
Semantics for personalized web-based systems” Computing
and Informatics, Vol. 28, (Sep-22 2009). 399–427
[22]Lee Jae-Won, Nam Kwang-Hyun, and Lee Sang-
Goo,”Semantics based collaborative filtering", Springer-
Verlag Berlin Heidelberg Software Engineering, Artificial
Intelligence,( 2009),201–208.
[23] Innar, Ruotsalo Tuukka, Tammet Tanel and Kuusik
Alar, “Personalized context-aware recommendations in
smartmuseum:combining Semantics with statistics” ,in
proceedings of Third internal conference on Advances in
Semantic processing,IEEE (2009) , 50 – 55.Penelope
[24] RDF, http://www.w3.org/RDF/, 01.06.2009

IRJET- A Literature Review and Classification of Semantic Web Approaches for Web Personalization Research

Recommended

More Related Content

What's hot (20)

Similar to IRJET- A Literature Review and Classification of Semantic Web Approaches for Web Personalization Research (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET- A Literature Review and Classification of Semantic Web Approaches for Web Personalization Research