or a social search engine is a type of web search method that determines the relevance of search results by considering the interactions or contributions of users. When applied to web search this user-based approach to relevance is in contrast to established algorithmic or machine-based approaches where relevance is determined by analyzing the text of each document or the link structure of the documents.
Social search takes many forms, ranging from simple shared bookmarks or tagging of content with descriptive labels to more sophisticated approaches that combine human intelligence with computer algorithms.
The Search experience revolve around the outcome of collaborative harvesting, collaborative directories, tag engines, social ranking, commenting on bookmarks, news, images, videos, podcasts and other web pages. Example forms of user input include social bookmarking or direct interaction with the search results such as promoting or demoting results the user feels are more or less relevant to their query.
The term social search began to emerge between 2004 and 2005. The concept of social search can be considered to derive from Google's PageRank algorithm, which assigns importance to web pages based on analysis of the link structure of the web, because PageRank is relying on the collective judgment of webmasters linking to other content on the web. Links, in essence, are positive votes by the webmaster community for their favorite sites.
In 2008, there are a few startup companies that focus on ranking search results according to one's social graph on social networks. Companies in the social search space include Eurekster, Mahalo, Wikia Search, and Me.dium.Com. A story on TechCrunch showed Google potentially adding in a voting mechanism to search results similar to Digg's methodology. This suggests growing interest in how social groups can influence and potentially enhance the ability of algorithm's to find meaningful data for end users.
To date social search engines have not demonstrated measurably improved search results over algorithmic search engines. However, there are potential benefits deriving from the human input qualities of social search.
- Reduced impact of link spam by relying less on link structure of web pages
- Increased relevance because each result has been selected by users
- leverage a network of trusted individuals by providing an indication of whether they thought a particular result was good or bad
- The introduction of 'human judgement' suggests that each web page has been viewed and endorsed by one or more people, and they have concluded it is relevant and worthy of being shared with others using human techniques that go beyond the computer's current ability to analyze a web page.
- Web pages are considered to be relevant from the reader's perspective, rather than the author who desires their content to be viewed, or the web master as they create links.
- More current results. Because a social search engine is constantly getting feedback it is potentially able to display results that are more current or in context with changing information
- Risk of spam. Because users can directly add results to a social search engine there is a risk that some users could insert search spam directly into the search engine. Elimination or prevention of this spam would require the ability to detect the validity of a users' contribution, such as whether it agrees with other trusted users.
- "The Long Tail" of search is a concept that there are so many unique searches conducted that most searches, while valid, are performed very infrequently. A search engine that relied on users filling in all the searches would be at a disadvantage to one that used machines to crawl and index the entire web.