BibTeX Entry

  author	= {Comarela, Giovanni and Crovella, Mark and Almeida, Virg{\'i}lio and Benevenuto, Fabr{\'i}cio},
  title		= {Understanding Factors that Affect Response Rates in Twitter},
  booktitle	= {Proceedings of ACM Hypertext},
  year		= {2012},
  month		= jun,
  address	= {Milwaukee, WI},
  URL		= {},
  abstract	= {In information networks where users send messages to one another, the issue of information overload naturally arises: Which are the most important messages? In this paper we study the problem of predicting the importance of messages in Twitter. That is, we seek to order messages so that when presented to the user, the messages most likely to be retweeted or responded to are presented first. For efficiency and simplicity, we do this without examining the content of messages. We approach this problem in two stages. First, we perform an extensive characterization of a very large Twitter data set which includes all users, social relations, and messages posted from the beginning of the service up to August 2009. We show evidence that information overload is present: users sometimes have to search through hundreds of messages to find those that are important. Next, by inspecting user activity over time, we construct a simple on-off model of user behavior that allows us to infer when a user is actively using Twitter. We then identify factors that influence user response or retweet probability: previous responses to the same tweeter, the tweeter's sending rate, and the age of the tweet. In our second stage, we show that these factors can be used to improve the ordering of tweets as presented to the user. We explore two methods from machine learning for ranking tweets: a Naive Bayes predictor, and a Support Vector Machine classifier. We show that it is possible to reorder tweets to increase the fraction of replied or retweeted messages appearing in the first p positions in the list by as much as 50-60\%.}