Exploring area-specific microblogger social networks

Abstract

Social networks can be used to find people who share similar interests or people who have knowledge in a specific domain. Using social networks to share knowledge is a very efficient way of reaching information. Current social networking tools provide many ways to search people with similar interests. However, they are either based on keyword search or ranking users based on popularity. Keyword search is limited to information explicitly declared by users such as name, location, marital status, interests etc. Since users often do not declare their interest areas or the content they contribute is not aligned with the area of interest they declare, it is usually a time consuming task to locate those who are of interest. User ranking methods, on the other hand, hides users who provide valuable information but not so popular. In this study we propose a model for determining the area of interests of users based on their contributions. In other words, we examine what they contribute rather than what they declare about themselves. The idea is that their value depends on what they contribute. Areas of interests are determined based on the co-occurrence of related words in user contributions. In addition, we explore communities of different interests, based on the common context different people use in their contributions. In order to put some semantic grounding to what we have found as interest areas, we map the content we extracted from the users‟ contributions to other resources such as DBpedia[84], Wikipedia[82] and Google[83]. We show that interest areas of people can be extracted from the dynamic content they provide. Besides, common interest networks of users can be generated by implementing our model. Furthermore, we can also generate networks of words which provide us a way to put semantics into the search queries instead of solely keyword based inquiries.