A multi-level matching approach applied to a semantic based dating site

Thumbnail Image



Journal Title

Journal ISSN

Volume Title


University of New Brunswick


Online dating or internet dating has become more common, more convenient and a quicker medium for people to find potential matches for developing different types of relationships such as personal, romantic, or sexual, than searching for partners in conventional ways. A common parameter across studies of human partner selection has been the physical attractiveness of individuals. In many past studies it has been predicted that, in making a realistic social choice, an individual would choose a partner similar in socially desirable traits like education level, income level and other credentials. Users may seek out online dating websites as a means of finding potential partners more quickly. Producing a set of matches for a person that he/she will find suitable is one of the major challenges in the online dating industry. Users enter information about themselves that is then used to identify other users as potential matches. However, many users become frustrated because they deem the list of potential matches unsuitable. This leads to customers cancelling their memberships and giving the websites poor reviews. This report addresses how the use of leading-edge semantic web technologies can provide better matches for dating in a more efficient and convenient way. These techniques consider more than just parameter based criteria (e.g. females between the age of 21 and 26); information provided is used not only to eliminate unsuitable matches but also to infer additional properties of the user that will be used in the matching process.