Exploiting Social Networks for Internet Search

Over the last decade, the World Wide Web and Web search engines have fundamentally transformed the way people find and share information. Recently, a new form of publishing and locating information, known as online social networking, has become very popular. While numerous studies have focussed on the hyperlinked structure of the Web and have exploited it for searching content, few studies, if any, have examined the information exchange in online social networks. In the Web, explicit links called hyperlinks between content (typically pages) are the primary tool for structuring information. Hyperlinks are used by authors to embed a page in the Web of related information, by human users to manually browse the Web, and by search engines to crawl the Web to index content, as well as to rank or estimate the relevance of content for a search query. In contrast to the Web, no explicit links exist between the content (typically photos, videos, and blog postings) stored in social networks. Instead, explicit links between users, who generate or publish the content, serve as the primary structuring tool. For example, in social networking sites like MySpace [15], Orkut [17], and Flickr [4], a link from user A to user B usually indicates that A finds the information published by B interesting or relevant, or A implicitly endorses B’s content due to an established social relationship. Such social links enable users to manually browse for information that is likely of interest to them, and could be used by search tools to index and locate information. In this paper, we seek to understand whether these social links can be exploited by search engines to provide better results. This paper makes three contributions: First, we compare the mechanisms for content publication and location in the Web and online social networks. We argue that search techniques could benefit from integrating the different mechanisms used to find relevant content in the Web and social networks. Second, we present results from an experiment in social network-based Web search to support our contention. Third, we outline the research challenges and opportunities in leveraging social networks for future Internet search. The remainder of this paper is organized as follows. In Section 2, we first contrast how content is exchanged in social networks and the Web, and then speculate on the potential of integrating the different search techniques used in these systems. We evaluate the potential of our integrated approach to search using a social networkbased experiment in Section 3. We discuss the research challenges that need to be addressed in order to realize such an integrated search system in Section 4. We present related work in Section 5 and conclude in Section 6.