Open Access Open Access  Restricted Access Subscription or Fee Access

An Ontological Model for Automated User Profiling

Gaurav Jaglan, Sanjay Kumar Malik, Ashish Khanna

Abstract



The ever-increasing emergence of social media sites and smart electronic devices has contributed to the publication of an enormous amount of data on the Web. Potentially, such huge collection of information allows users to discover anything as per their requirement. However, it is quite difficult or impossible for humans to manage such massive information. This situation also increases considerably redundant as well as substandard information, resulting in a dilution of the quality of information on the web. Thus, the immense variety of results obtained may perplex the users to arrive at the most desirable choices. Semantic Web (SW) as anticipated by Sir Tim Berners Lee, is an advanced web to tackle the limits of the current web and was proposed for providing enhanced structure and linking capabilities to online published data. This will significantly increase the relevance of results produced, by providing a context to the user’s queries, producing user personalized results. In this paper, an attempt has been made to propose a model towards personalization in form of an ontological user profiling algorithm. A case study on social network of an academic institute has been presented and an automated user profiling tool based on java is developed for implementation of the proposed algorithm. An evaluation scheme is also proposed for behaviour modelling. Also, the generated user profile ontology is validated. The key objective of this approach is to automatically generate a machine-processable representation of user’s static and dynamic attributes that can be utilized to incorporate semantics to generate personalized results making the auto-form filling, searching and recommendation results more appropriate.

Keywords


Semantic Web, Personalization, User Profiling, Ontology, RDF, Interest identification, NERL, Linked Data, NLP

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.