Predicting popular messages in Twitter

By Liangjie Hong, Ovidiu Dan, Brian D. Davison. The Web Conference, 2011

610 citations recorded by the source corpus.

Subfields: Information Systems, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/c822b5219bfcdb0758d9876f4a7b2ebaad4c143c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Statistical and Nonlinear Physics

Citations in the corpus

The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter (2014, background): “Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 175–185, Baltimore, Maryland, USA, June 23-25 2014. c©2014 Association for Computational Linguistics”
Predictive Analysis on Twitter: Techniques and Applications (2018, methodology): “In Twitter data analysis, the processing phase includes natural language processing using techniques such as TF-IDF, word2vec, stemming, lemmatization, eliminating words with a rare occurrence, and tokenizing.”
SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity (2015, background): “Online social networking services, such as Facebook, Youtube, and Twitter, allow their users to post and share content in the form of posts, images, and videos [9, 17, 21, 30].”
News Sharing in Social Media: A Review of Current Research on News Sharing Users, Content, and Networks (2015, neutral): “…et al., 2010; Ferrara, Interdonato, & Tagarelli, 2014; Horan, 2013), number of followers or friends (e.g., Bakshy, Hofman, Mason, & Watts, 2011; Hong, Dan, & Davison, 2011; Wu et al., 2011), and news and content preferences (e.g., Hermida, Fletcher, Korell, & Logan, 2012; Himelboim, Hansen, &…”
Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey (2017, neutral): “They collected a dataset that includes 2,541,178 users and 10,612,601 messages and demonstrated that this method can identify messages which will attract thousands of retweets [55].”
Modeling and Predicting Popularity Dynamics via Reinforced Poisson Processes (2014, background): “…stories on Digg gain their popularity by striving for views or votes [22]; papers increase their visibility by competing for citations from new papers [24]; tweets or Hash-tags in Twitter become more popular as being retweeted [12] and so do webpages as being attached by incoming hyper-links [20].”
Bad news travel fast: a content-based analysis of interestingness on Twitter (2011, methodology): “[6] use retweets as a measure of popularity and apply machine learning techniques to predict how often new messages will be retweeted.”
Predicting Responses to Microblog Posts (2012, background): “The task of predicting responses in social networks has been investigated previously: Hong et al. (2011) focused on predicting responses for highly popular items, Rowe et al. (2011) targeted the prediction of conversations and their length and Suh et al. (2010) predicted retweets.”
Social media big data analytics: A survey (2019, neutral): “Micro-blogs have become a major source of information for users (Hong, Dan, & Davison, 2011).”
What makes an image popular? (2014, background): “While most of the work has focused on predicting popularity of text content, such as messages or tweets on Twitter [42, 20], and some recent works on video popularity [43, 49, 38], signiﬁ-cantly less eﬀort has been expended in prediction of image popularity.”
Searching microblogs: coping with sparsity and document quality (2011, positive): “Hong et al. [7] use retweets as a measure of popularity and apply machine learning techniques to predict how often new messages”
Context-aware Image Tweet Modelling and Recommendation (2016, background): “We first describe the four strategies that construct contexts from different data sources (cf. Figure 2), and then discuss the rules to fuse the contexts which help to improve text quality and save the acquisition cost.”
Topic Modeling Using Latent Dirichlet allocation (2021, background): “[51] 2011 10,612,601 messages and 2,541,178 users/LDA To predict how quickly message will becomes breaking news”
Examining a hate speech corpus for hate speech detection and popularity prediction (2018, methodology): “Similarly, Hong et al. (2011) predict the number of retweets, using binary and multi-class classiﬁers.”
Twitter's Glass Ceiling: The Effect of Perceived Gender on Online Visibility (2016, background): “The number of followers is the most basic measure of visibility, as it reflects the size of one’s audience (Hong, Dan, and Davison 2011).”
Can cascades be predicted? (2014, methodology): “Other features of the root node have also been studied, such as the number of prior retweets of a user’s posts [5, 16], and how many Twitter lists a user was included in [26].”