Docstoc

Analysis of Personalized Ontology & Emergence of Web Information Gathering

Document Sample
Analysis of Personalized Ontology & Emergence of Web Information Gathering Powered By Docstoc
					   International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)
       Web Site: www.ijettcs.org Email: editor@ijettcs.org, editorijettcs@gmail.com
Volume 1, Issue 2, July – August 2012                                          ISSN 2278-6856




         Analysis of Personalized Ontology &
       Emergence of Web Information Gathering
                                        B. Nirupama1, Vijaya Lakshmi Kakulapati2
                 1,2
                       Department of Computer Science Engineering, Sridevi Women’s College of Engineering, India


                                                                   an emerging need for a standard ontology that will model
Abstract: Ontology is widely used to represent user profiles       user profiles; this standard ontology will facilitate the
as knowledge description personalized web information              communication between applications and serve as
gathering. However the information of user profiles                reference point when profiling functionalities need to be
represents patterns either global or local knowledge base          developed.
information, according to our analysis many models                 Over the past decade growth of information available on
represents global knowledge. In this paper ontology system is      the web gathering useful information from the web has
used to recognize and reasoning over user profiles, world
                                                                   become a challenging issue for users. Web users expect
knowledge base and user instance repositories. This work also
                                                                   more intelligent systems to gather the useful information
compares the analysis of existing system and ontology with
other research areas is more efficient to represent
                                                                   from the large size of web related data sources, user
Keywords: Ontology, user profiles, Image processing,               profiles represent the concept models possessed by users
software Engineering                                               when gathering web information. A concept model is
                                                                   implicitly either local or global analysis method is
                                                                   effective for gathering the global knowledge.
                                                                   Multidimensional ontology mining method specificity for
SECTION I                                                          analyzing the concept specified machine-readable
Introduction: Personalization of information access                documents.
indeed to face considerable growth of data heterogeneity
of the roles and needs to the rapid development of mobile
system becomes important to propose a personalized                 SECTION II
system able to provide user with relevant information              2. Survey on Ontology: Ontology is a extraction and a
need. System must into account the different                       subtask of information extraction is a type of information
characteristics of the user and all contextual situations          retrieval is automatically extract structured information
that influence his behavior during his interaction with            from unstructured relevant concepts and relations from a
information system. A generic model of profile access              given data sets from ontology. It retrieves data based on
according to which the personalization system is                   the local or global does not consider on the primary key
articulated based mainly on profiles context user’s                gathers data based on the user name in local profile if two
preferences. Profiles are knowledge containers context             persons have same name it will retrieve both the
defines a set of parameters that characterize the                  information. For capturing the user information needs
environment of the system user preferences represent the           user profiles were used in web information gathering,
expectations of the user.                                          user profile is a collection of data associated to a specific
Ontology is best the candidate for representing knowledge          personal data associated to a specific user. A profile refers
about users to have a shared understanding between                 to the explicit digital representation of a person’s identity
people or software agents of terms and their relations a           can also consider as the computer representation of a user
controlled vocabulary. Ontologies have been proven and             model. User profiles are categorized into interviewing
effective information means for modeling a user context            semi-interviewing non-interviewing, interviewing profiles
can be very useful tool because they may present an                are considered perfect for user profiles they are acquired
overview of the domain related to a specific area of               by using manual techniques such as questionnaries
interest and used for browsing query refinement, provides          interviewing users and analyzing use classified training
rich semantics for humans to work with required                    sets. Users read each document and gave a positive or
formalism for computers to perform mechanical                      negative advice to the document against a given topic
processing. Ontology is used to model the                          semi-interviewing use profiles are acquired by semi-
user profile has already been proposed in various                  automated techniques with limited user involvement
applications like web search [3], [2] and personal                 usually provides users with a list of categories and ask
information management [1]. However, up to this point,             user for interesting categories example is the web training
ontologies modeling user profiles are application-specific,        set acquisition model introduced by Tao et al which
with each one having been created specifically for a               extracts training sets from the web based on user feedback
particular domain. Taking into account the continuing              categories. Non interviewing techniques do not involve
incorporation of ontologies in new applications, there is

Volume 1, Issue 2 July-August 2012                                                                                  Page 225
   International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)
       Web Site: www.ijettcs.org Email: editor@ijettcs.org, editorijettcs@gmail.com
Volume 1, Issue 2, July – August 2012                                          ISSN 2278-6856


users at all but ascertain user interests instead acquire       3.3.Ontology in Software Engineering:Modelling
user profiles by observing user activity and behavior.       ontology is a tedious task always important to
                                                             demonstrate can gain by applying ontologies in software
SECTION III                                                  engineering, the current advent of logic based formalisms
                                                             in the context of the semantic web effort is an important
   3.1. Interaction Between Semantic web and
                                                             factor. Activities by the W3C and others have helped to
Ontology: Semantic web mining aims to combine the
                                                             flesh out standards like RDF or OWL receive increasing
development of semantic web and web mining, web
                                                             attention by tool builders and users. Important factor is
mining extracts information from the content of the pages
                                                             the flexibility of ontologies with information integration
its structure of relationships and users browsing records.
                                                             as a major use case, ontologies are well to combine
Very important portion of semantic web is the ontologies
                                                             information from various sources and infer new factors
represented as a set of concepts and their relevant
                                                             and also the flexibility. Further promoted by the"web"-
interrelations for certain domains of knowledge
                                                             focus of current ontology approaches due to the fact that
Sentiment analysis is opinion mining is responsible for
                                                             software systems also get increasingly web-enabled and
classifying words, texts or documents of opinion and
                                                             must thuscope with data from heterogeneous sources that
works in tagging and their components which indicate if
                                                             may not be known at developmenttime, software
the expression is positive negative or neutral and in the
                                                             engineers seek technologies that can help in this
field of the subjectivity of texts as well.
                                                             situation. Thus,experts in the field like Grady Booch are
Web intelligence is research aimed at exploration of the
                                                             expecting semantic web technology to beone of the next
fundamental interactions between artificial intelligence
                                                             big things in the architecture of web-based applications
advanced engineering and information technology is a
                                                             [40]. Also, theweb makes it easier to share knowledge.
general term referring to new area example such as
                                                             Having URIs as globally unique identifiers,it is easy to
informatics of the brain, IA human level and classics such
                                                             relate one’s ontology to someone else's conceptualization.
as engineering knowledge representation planning
                                                             This     in     turnencourages      interoperability  and
discovery data extraction.
                                                             reuse.Regarding more Software Engineering-specific
   3.2. Image processing Ontology: Ontology widely
                                                             advantages, ontologies makedomain models first order
used for designing high level scene interpretation that
                                                             citizens. While domain models are clearly driving the
provides the primitives and the concepts at the physical
                                                             coreof every software system, their importance in current
level correspond to the effects of the acquisition
                                                             Software Engineering processesdecreases after the
components on the digital image representation analysis
                                                             analysis phase. The core purpose of ontologies is by
of the various components of a standard acquisition
                                                             definition theformal descriptions of a domain and thus
system lighting environment optical system sensor analog
                                                             encourages a broader usage throughout thewhole
to digital converter and storage gives the list of their
                                                             Software Engineering lifecycle.
possible effects example such as sensor optical system can
generate illumination geometry and blur defects on
images.
                                                             SECTION IV
                                                                4.1. Knowledge base:The world knowledge base must
                                                             cover an exhaustive range of topics, since users may come
                                                             from different backgrounds. The structure of the world
                                                             knowledge base used in this research is encoded from the
                                                             LCSH references. The LCSH system contains three types
                                                             of references:
Figure shows the effects generated on image                       1. Broader term- The BT references are for two
representation by various components of a standard image     subjects describing the same topic, but at different levels
acquisition system provides the physical level of the        of abstraction (or specificity). In our model, they are
ontology.                                                    encoded as the is-a relations in the world knowledge base.
                                                                  2. Used-for- The UF references in the LCSH are used
                                                             for many semantic situations, including broadening the
                                                             semantic extent of a subject and describing compound
                                                             subjects and subjects subdivided by other topics. When
                                                             object A is used for an action, becomes a part of that
                                                             action (e.g., “a fork is used for dining”); when A is used
                                                             for another object, B, A becomes a part of B (e.g., “a
Image retrieval results identifies the nine categories of    wheel is used for a car”). These cases can be encoded as
concepts blur, noise, colorimetry, illumination, geometry,   the part-of relations.
photometry, sampling,quantization and storage only                3. Related term- The RT references are for two
primitives that have a genuine manifestation in the input    subjects related in some manner other than by hierarchy.
images should be provided.
Volume 1, Issue 2 July-August 2012                                                                           Page 226
   International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)
       Web Site: www.ijettcs.org Email: editor@ijettcs.org, editorijettcs@gmail.com
Volume 1, Issue 2, July – August 2012                                          ISSN 2278-6856


They are encoded as the related-to relations in our world    fact that only users know their interests and preferences
knowledge base.                                              perfectly. Baseline Model demonstrated the non-
   4.2. Ontology Learning Environment: The subjects of       interviewing user profiles, a user’s interests and
user interest are extracted from the WKB via user            preferences are described by a set of weighted subjects
interaction. A tool called Ontology Learning                 learned from the user’s browsing history. These subjects
Environment (OLE) is developed to assist users with such     are specified with the semantic relations of superclass and
interaction. Regarding a topic, the interesting subjects     subclass in ontology. When an OBIWAN agent receives
consist of two sets: positive subjects are the concepts      the search results for a given topic, it filters and re-ranks
relevant to the information need, and negative subjects      the results based on their semantic similarity with the
are the concepts resolving paradoxical or ambiguous          subjects. The similar documents are awarded and re-
interpretation of the information need. Thus, for a given    ranked higher on the result list. Web modelwas the
topic, the OLE provides users with a set of candidates to    implementation of typical semi interviewing user profiles.
identify positive and negative subjects. These candidate     It acquired user profiles from the web by employing a web
subjects are extracted from the WKB. Who are not fed         search engine. The feature terms referred to the
back as either positive or negative from the user, become    interesting concepts of the topic. The noisy terms referred
the neutral subjects to the given topic.                     to the paradoxical or ambiguous concepts with
   4.3. Ontology mining: Ontology mining discovers           disadvantages such as the using web documents for
interesting and on-topic knowledge from the concepts,        training sets has one severe drawback: web information
semantic relations, and instances in ontology. Ontology      has much noise and uncertainties. As a result, the web
mining method is introduced: Specificity and                 user profiles were satisfactory in terms of recall, but weak
Exhaustively. Specificity (denoted spe) describes a          in terms of precision. There was no negative training set
subject’s focus on a given topic. Exhaustively (denoted      generated by this model compare to this, world
exh) restricts a subject’s semantic space dealing with the   knowledge and a user’s local instance repository (LIR)
topic. This method aims to investigate the subjects and      are used in the proposed model. An LIR is a user’s
the strength of their associations in ontology. In User      personal collection of information items. From a world
Local Instance Repository, User background knowledge         knowledge base, we construct personalized ontologies by
can be discovered from user local information collections,   adopting user feedback on interesting knowledge. A
such as a user’s stored documents, browsed web pages,        multidimensional ontology mining method, Specificity
and composed/received emails.                                and Exhaustively, is also introduced in the proposed
                                                             model for analyzing concepts specified in ontologies. The
Algorithm to be applied is given below                       users’ LIRs are then used to discover background
                                                             knowledge and to populate the personalized ontologies.
                                                             Proposed analysis have benefits Compared with the
                                                             TREC model, the Ontology model had better recall but
                                                             relatively weaker precision performance. The Ontology
                                                             model discovered user background knowledge from user
                                                             local instance repositories, rather than documents read
                                                             and judged by users. Thus, the Ontology user profiles
                                                             were not as precise as the TREC user profiles.The
                                                             Ontology profiles had broad topic coverage. The
                                                             substantial coverage of possibly-related topics was gained
                                                             from the use of the WKB and the large number of
                                                             training documents. Compared to the web data used by
                                                             the web model, the LIRs used by the Ontology model
                                                             were controlled and contained less uncertainties.
                                                             Additionally, a large number of uncertainties were
                                                             eliminated when user background knowledge was
                                                             discovered. As a result, the user profiles acquired by the
SECTION V                                                    Ontology model performed better than the web model.
5. Comparative Study:The TREC model was used to
demonstrate the interviewing user profiles, which            SECTION VI
reflected user concept models perfectly. For each topic,     6. CONCLUSION
TREC users were given a set of documents to read and         The proposed ontology system provides a solution to
judged each as relevant or non-relevant to the topic. The    emphasizing global or local knowledge in a
TREC user profiles perfectly reflected the users’ personal   computational model and applied to the design of web
interests, as the relevant judgments were provided by the    information gathering systems. The model also has
same people who created the topics as well, following the    extensive contributions to thefields of Information

Volume 1, Issue 2 July-August 2012                                                                            Page 227
   International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)
       Web Site: www.ijettcs.org Email: editor@ijettcs.org, editorijettcs@gmail.com
Volume 1, Issue 2, July – August 2012                                          ISSN 2278-6856


Retrieval, web Intelligence, RecommendationSystems,
and Information Systems and reviews the ontology with                            B.Nirupama      pursuing      M.Tech
software engineering, image processing retrieval                                 Computer Science Engineering from
compares with previous model. Our work extends, will                             Sridevi    Women’s      college   of
investigate the methods thatgenerate user local instance                         Engineering   B.Tech     Information
repositories to match therepresentation of a global                              Technolgy from JayaPrakesh Narayana
knowledge base. The presentwork assumes that all user                            College of Engineering. Her research
local instance repositories havecontent-based descriptors     areas include Data mining Cloud Computing.
referring to the subjects, however,a large volume of
documents existing on the web maynot have such content-                        Vijayalakshmi Kakulapati Ph.D
based descriptors.                                                             M.Tech currently she is the Head of
                                                                               the Deaprtment of Computer Science
REFERENCE                                                                      Engineering and having 20years of
                                                                               Academic Experience. Her research
[1] V. Katifori,, A. Poggi,. M. Scannapieco, T. Catarci, &                     areas includes Information Retrieval
     Y. Ioannidis (2005). OntoPIM: how to rely on a           Systems, Web Mining, Operating Systems, Unix
     personal ontology for Personal Information               Administration, attended National Conference and
     Management. In Proc. of the 1st Workshop on The          published more than 15 International Journals and life
     Semantic Desktop.                                        member of various technical bodies like IEEE ACM CSI
                                                              ISTE.
[2] S. Lawrence, (2000). Context in web search. IEEE
     Data Engineering Bulletin, 23(3):25-32
[3] J. Trajkova, S. Gauch, Improving Ontology-based
     User Profiles, Proc. of RIAO 2004, University of
     Avignon (Vaucluse), France, April 26-28, 2004, pp.
     380-389
[4] Amato G., Staraccia U., “User profile modellin and
     applications to digital libraries”, Proceedings of the
     3rd European Conference on Research and avanced
     technology for digital libraries, p. 184-187, 1999.
[5] Bouzeghoub M., Kostadinov D., L’art et définition
     d’un modèle flexible de profils, Actes de la 2ème
     conférence en personnalisation de l’information :
     aperçu de l’état de recherche d’informations et
     applications CORIA’2005, Grenoble, France, 2005
[6] C. Hudelot, N. Maillot, and M. Thonnat. Symbol
     Grounding for Semantic Image Interpretation: From
     Image Data to Semantics. In IEEE Int. Workshop on
     Semantic Knowledge in Computer Vision (ICCV),
     pages 1–8, Beijing, China, 2005.
[7] J. Hunter. Adding Multimedia to the Semantic Web –
     Building an MPEG-7 Ontology. In Int. Semantic
     Web Working Symposium (SWWS), pages 261–281,
     Stanford, CA, 2001.
[8] Oberle, D.: Semantic Management of Middleware,
     Volume I of The Semantic Web and Beyond
     Springer, New York (2006)
[9] Mayank, V., Kositsyna, N., Austin, M.: Requirements
     Engineering and the Semantic Web, Part II.
     Representation, Management, and Validation of
     Requirements and System-Level Architectures.
     Technical Report. TR 2004-14, University of
     Maryland (2004)
[10] Decker, B., Rech, J., Ras, E., Klein, B., Hoecht, C.:
     Selforganized Reuse of SoftwareEngineering
     Knowledge supported by Semantic Wikis. In: Proc. of
     Workshop on SemanticWeb Enabled Software
     Engineering (SWESE). November (2005)
Volume 1, Issue 2 July-August 2012                                                                         Page 228

				
DOCUMENT INFO
Description: International Journal of Emerging Trends & Technology in Computer Science (IJETTCS) is an online Journal in English published bimonthly for scientists, Engineers and Research Scholars involved in computer science, Information Technology and its applications to publish high quality and refereed papers. Papers reporting original research and innovative applications from all parts of the world are welcome. Papers for publication in the IJETTCS are selected through rigid peer review to ensure originality, timeliness, relevance and readability. The aim of IJETTCS is to publish peer reviewed research and review articles in rapidly developing field of computer science engineering and technology. This journal is an online journal having full access to the research and review paper. The journal also seeks clearly written survey and review articles from experts in the field, to promote intuitive understanding of the state-of-the-art and application trends. The journal aims to cover the latest outstanding developments in the field of Computer Science and engineering Technology.