Open AccessPredict Individual Retweet Behavior Based on Multi-feature
Author(s) -
Chunjia Wang,
Yongquan Fan,
Yajun Du,
Zefen Sun
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/790/1/012046
Subject(s) - computer science , social media , task (project management) , feature (linguistics) , process (computing) , social network (sociolinguistics) , user information , information retrieval , world wide web , artificial intelligence , data science , information system , engineering , linguistics , philosophy , electrical engineering , operating system , systems engineering
With the rapid development of social media, more and more people get information from social media. The retweet prediction task helps to study the process of information dissemination on social media. Previous methods take into account text features and ignore user’s sentiments and interests. The history tweets tweeted by the user not only reflect the user’s sentiments that the user tends to express on social media, but also shows the user’s interests. In this work, we used a deep learning method to extract features from user profiles, user history, user network, target tweet, then we used these features to predict whether a tweet will be retweeted by a user. Experimental results on dataset show that the proposed model can effectively predict the retweet behavior of users.