Conversation retrieval from Social Media

by on 13/04/11 at 7:29 am

Next week Matteo is going to Dublin for the annual European Conference on Information Retrieval (ECIR). We are presenting a demo of our Conversation retrieval system for Social Media and Social Network Sites. While the addition of Social aspect to traditional online searches has been around for some times we are following a different approach. So far social search used what we can define as an ego-centric approach that means that informational objects around the web get somehow recommended by your online contacts.
We are doing something different. We are moving from online search aimed at retrieving information toward what we call a conversational search. This means that the object of our search is no longer a single information but a set of messages and users that can be described (and ranked) according to many social aspects.

Therefore some of the ranking criteria that can be used are:
Text relevance, User centrality (e.g., degree, page rank, audience), Message popularity (e.g., retweets, likes, sharing), Timeliness (i.e., distance from a given timestamp), Length (i.e., number of messages), Density (i.e., emotions and interest).

We’ve done some blind comparison between our system (tuned with different ranking parameters) and Google on some Friendfeed conversations searches. Users were asked to judge (according to their personal interest) a set of Friendfeed conversations about a specific topic. Here you can see the results (Google is green, The other two are our system with the ranking based on popularity [purple] and density [blue]), higher values mean higher a better judgement on results showed by the search system.

Comments are closed.