A Bayesian Approach for Predicting the Popularity of Tweets

  title={A Bayesian Approach for Predicting the Popularity of Tweets},
  author={Tauhid Zaman and Emily B. Fox and Eric T. Bradlow},
We predict the popularity of short messages called tweets created in the micro-blogging site known as Twitter. We measure the popularity of a tweet by the time-series path of its retweets, which is when people forward the tweet to others. We develop a probabilistic model for the evolution of the retweets using a Bayesian approach, and form predictions using only observations on the retweet times and the local network or "graph" structure of the retweeters. We obtain good step ahead forecasts… 

Twitter Early Prediction of Preferences and Tendencies Based in Neighborhood Behavior

It is concluded that it is possible to reasonably predict the preference of a user retweet or how massive a publication will be, using only the information available during the first 30-60 minutes.

Estimating the Spreading of Viral Threads on Twitter

This model is based on the hypothesis that it is highly probable that a user decides to retweet a tweet if he/she is following either the tweet author, or another retweeter of the tweet, and chooses as main features of a tweet its number of retweets and the number of followers of retweeting users.

Assessing the reTweet proneness of tweets: predictive models for retweeting

Several features extracted from Twitter data have been analyzed to create predictive models, with the aim of predicting the degree of retweeting of tweets, to obtain indications about the probable number of retweets a tweet may obtain from the social network.

An Analysis of Influential Users for Predicting the Popularity of News Tweets

This paper aims to study the impact of influential users who retweet tweets, also called retweeters, and presents simple yet effective measures for predicting the influence of retweeters on the popularity of online news tweets.

Quantitative Prediction of Twitter Message Dissemination: A Machine Learning Approach

There is no global best classifier for the problem of popularity prediction in twitter but depending on the dataset, popularity threshold and the interest, an optimal classifier with a proper set of features for this task can be adopted.

Marked self-exciting point process modelling of information diffusion on Twitter

This paper proposes a model called the Marked Self-Exciting Process with Time-Dependent Excitation Function, or MaSEPTiDE for short, to model the retweeting dynamics and to predict the tweet popularity and applies this model on a large amount of Twitter data.

A model for the Twitter sentiment curve

A model able to reproduce the dynamics of the sentiments of tweets related to specific topics and periods and to provide a prediction of the sentiment of the future posts based on the observed past is presented.

TiDeH: Time-Dependent Hawkes Process for Predicting Retweet Dynamics

This paper model the Twitter system by Time-Dependent Hawkes process (TiDeH), which properly takes into account the circadian nature of the users and the aging of information, and develops a procedure for parameter optimization and for predicting the future profiles of retweet activity at different time resolutions.

Sentiment analysis of the correlation between regular tweets and retweets

This paper proposes a method to calculate the sentiment score for each tweet and each Twitter user, and adopts the correlation coefficient between the sentiment scores of regular tweets and those of retweets to measure the influence.



Predicting Information Spreading in Twitter

A new methodology for predicting the spread of information in a social network based on data of who and what was retweeted and a probabilistic collaborative filter model to predict future retweets is presented.

Bad news travel fast: a content-based analysis of interestingness on Twitter

This paper analyzes a set of high- and low-level content-based features on several large collections of Twitter messages to obtain insights into what makes a message on Twitter worth retweeting and, thus, interesting.

Predicting popular messages in Twitter

It is shown that the method can successfully predict messages which will attract thousands of retweets with good performance and formulate the task into a classification problem and study two of its variants by investigating a wide spectrum of features based on the content of the messages.

The Pulse of News in Social Media: Forecasting Popularity

This paper constructs a multi-dimensional feature space derived from properties of an article and evaluates the efficacy of these features to serve as predictors of online popularity and demonstrates that despite randomness in human behavior, it is possible to predict ranges of popularity on twitter with an overall 84% accuracy.

What is Twitter, a social network or a news media?

This work is the first quantitative study on the entire Twittersphere and information diffusion on it and finds a non-power-law follower distribution, a short effective diameter, and low reciprocity, which all mark a deviation from known characteristics of human social networks.

Want to be Retweeted? Large Scale Analytics on Factors Impacting Retweet in Twitter Network

It is found that, amongst content features, URLs and hashtags have strong relationships with retweetability and the number of followers and followees as well as the age of the account seem to affect retweetability, while, interestingly, thenumber of past tweets does not predict retweetability of a user's tweet.

Measuring User Influence in Twitter: The Million Follower Fallacy

An in-depth comparison of three measures of influence, using a large amount of data collected from Twitter, is presented, suggesting that topological measures such as indegree alone reveals very little about the influence of a user.

Everyone's an influencer: quantifying influence on twitter

It is concluded that word-of-mouth diffusion can only be harnessed reliably by targeting large numbers of potential influencers, thereby capturing average effects and that predictions of which particular user or URL will generate large cascades are relatively unreliable.

Information resonance on Twitter: watching Iran

This paper collected tweets of more than 20 million publicly accessible users on Twitter and analyzed over three million tweets related to the Iranian election posted by around 500K users during June and July of 2009, providing several key insights into the dynamics of information propagation that are special to Twitter.

The structure of online diffusion networks

This work describes the diffusion patterns arising from seven online domains, ranging from communications platforms to networked games to microblogging services, each involving distinct types of content and modes of sharing, and finds strikingly similar patterns across all domains.