Social media has become ubiquitous. Tweets and other user-generated content have become so abundant that better tools for information organization are needed in order to fully exploit their potential richness.
"Social curation" has recently emerged as a promising new framework for organizing and adding value to social media, complementing the traditional methods of algorithmic search and aggregation. While social curation services are gaining popularity, little academic research has studied the phenomenon.
In this work, we
- characterize the curation phenomenon:The first corpus analysis of microblog curation, which reveals that curated lists are supervised corpora for analyzing microblog messages.
- Develop assistive technology for curators:A recommendation system that suggests new content given partially curated lists.
AutoTogetter: Prototype of assistive system for curators
Given a partially curated list, it retrieves and aggregates related tweets with tweets in the list as queries, and ranks these tweets according to the relevance. In this video, we tried to create stories as to social journalizm from ICWSM tweet messages with the help of our system.