What do we mean by "Search in Social Media"?


Jeremy and I have been busy preparing for the Search in Social Media (SSM2010) workshop. We thought we would start at the beginning and ask what people understood by the term “search in social media.” Workshops often spend a bunch of time on definitions, and we thought we’d jump in early. We’ve talked about social search before, but that was without reference to social media.

We think the phrase ‘search in social media’ has been used to refer to both the information being searched, and to the process for doing so. The information is standard user-generated content — tweets, blog posts, comment threads, tags, etc. The process, however, seems less well understood.

What is a social search process? The term may be used to refer to group personalization, of the heystaks variety. It can be used to refer to the sharing of results with one’s social network via Twitter, Facebook, or other SNSs. Finally, it is also used to describe distributed question answering , a la Aardvark. Of course these processes can be applied to both social media and more traditional content.

Search in Social Media: Information vs. Process

This table defines the four quadrants that can be populated with familiar (and esoteric) examples:

  1. (top-left) Aardvark, Yahoo! Answers
  2. (top-right) Facebook Search, Google Social
  3. (bottom-left) iSpy, Groupization
  4. (bottom-right) Traditional search

This way of looking at social search emphasizes people’s behavior, but it also has implications for the kinds of information needs that can be met effectively, and of course for the underlying indexing and retrieval technology. Of course many existing systems do not fall cleanly into these cells. LinkedIn, for example, can probably be used in modes 1, 2, and 3. Nonetheless, we think considering how people approach the tools and what kinds of information needs they have can lead to a clearer understanding of the technical and design issues that implementers face.

It will be interesting to see how these ideas will be transformed by the discussion at the workshop. In any case, having a language with which to talk about phenomena is a prerequisite to articulating a research agenda, particularly in a young and multi-disciplinary field.


  1. […] you to take a look at our framework and comment or critique where necessary.  Here’s the link to Gene’s writeup: We think the phrase ’search in social media’ has been used to refer to both the information […]

  2. […] 2010 workshop. (For other commentary, see Daniel Tunkelang’’s post and our pre-workshop comments.) Hillary asked several important questions, that break out into two main topics: what and how can […]

Comments are closed.