What's in a hashtag?: content based prediction of the spread of ideas in microblogging communities

By Oren Tsur, Ari Rappoport. 2012

483 citations recorded by the source corpus.

Subfields: Information Systems, Statistical and Nonlinear Physics

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

Accelerated Attributed Network Embedding (2017, methodology): “Social science theories like homophily [23, 24] and social influence [38] suggest that node attributes are highly correlated with network structure, i.”
CrisisLex: A Lexicon for Collecting and Filtering Microblogged Communications in Crises (2014, background): “Hashtags are topical markers for tweets (Tsur and Rappoport 2012), used to learn about events and join the conversation (Starbird and Palen 2011).”
Bots increase exposure to negative and inflammatory content in online social systems (2018, unknown): “Hashtags are strings of characters starting with the hash (#) character and representing the main semantic content of a tweet (36).”
Vital nodes identification in complex networks (2016, background): “While if the two volunteers spreading different messages, the comparison cannot be completely fair since the prevalence of a message is very sensitive to its content [378, 379, 380].”
DeepHawkes: Bridging the Gap between Prediction and Understanding of Information Cascades (2017, background): “Feature-based approaches generally consider the popularity prediction task as a regression problem [2, 3, 13–15] or a classification problem [4, 5, 16].”
A temporal model of text periodicities using Gaussian Processes (2013, methodology): “We also remove duplicate tweets (retweets and tweets that had the same ﬁrst 6 content tokens) because they likely represent duplicate content, automated messages or spam which would bias the dataset, as also stated by Tsur and Rappoport (2012).”
Can cascades be predicted? (2014, methodology): “On Twitter, tweet content and in particular, hashtags, are used to generate content features [23, 30], and identify topics affecting retweet likelihood [26].”
Characterizing the Propagation of Situational Information in Social Media During COVID-19 Epidemic: A Case Study on Weibo (2020, background): “Content features mainly contain the following: whether URL/Hashtag is contained, the publishing timing of the content, and the content’s length have been recognized to positively affect the reposted amount of social media content [18]–[20].”
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”
Label Informed Attributed Network Embedding (2017, background): “For instance, Tsur and Rappoport [40] advanced the prediction of spread of ideas by analyzing both social graph topology and content.”
Topological Recurrent Neural Network for Diffusion Prediction (2017, background): “They often rely on explicitly engineering useful features to predict the activation probability of a node, such as network structure and temporal information [4], user nodes’ social roles [11], diffusion content [12] and user nodes’ interactions [13].”
No country for old members: user lifecycle and linguistic change in online communities (2013, background): “More recent studies have shown that similar mechanisms are at work in online communities, revealing the emergence of linguistic norms in e-mail [35], Twitter [7, 19, 20, 38, 45] and internet forums [8, 14].”
DeepCas: An End-to-end Predictor of Information Cascades (2016, methodology): “We use the mean squared error (MSE) to evaluate the accuracy of predictions, which is a common choice for regression tasks and used in previous work of cascade prediction [35, 43, 22].”