Predicting the popularity of online content

By Gábor Szabó, Bernardo A. Huberman. Communications of the ACM, 2008

1,128 citations recorded by the source corpus.

Early patterns of Digg diggs and YouTube views reflect long-term user interest.

Subfields: Computer Networks and Communications, Sociology and Political Science, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/1d287f70305f3127ed9901e3efcbbef1ab2cea1f

How researchers see this paper

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

In Computer Networks and Communications

In Sociology and Political Science

In Statistical and Nonlinear Physics

Citations in the corpus

Modeling Interestingness with Deep Neural Networks (2014, neutral): “There are many systems that identify popular content in the Web or recommend content (e.g., Bandari et al. 2012; Lerman and Hogg 2010; Szabo and Huberman 2010), which is closely re-lated to the highlighting task.”
The Pulse of News in Social Media: Forecasting Popularity (2012, background): “(Szab´o and Huberman 2010) found that eventual popularity of items posted on youtube and digg has a strong correlation with their early popularity; (Lee, Moon, and Salamatian 2010) and (Tatar et al. 2011) predict the popularity of a discussion thread using features based on early measurements of…”
Can cascades be predicted? (2014, background): “, timek) were shown to be the most important features in predicting thread length on Facebook [4], and are a primary mechanism in predicting online content popularity [29].”
Something’s Brewing! Early Prediction of Controversy-causing Posts from Discussion Features (2019, background): “…2011; Tatar et al., 2011; Backstrom et al., 2013; He et al., 2014; Zhang et al., 2018b) , or eventual post article score (Rangwala and Jamali, 2010; Szabo and Huberman, 2010), ; but all where, like us , the paradigm is early detection No, only info available at the item’s creation (Dori-Hacohen…”
The emergence of network media logic in political communication: A theoretical approach (2015, background): “Szabo and Huberman (2010) demonstrate that the viral quality of an information item is derived at an early stage (in one case two hours after the upload).”
Understanding the Impact of Opinion Leaders’ Characteristics on Online Group Knowledge-Sharing Engagement from In-Group and Out-Group Perspectives: Evidence from a Chinese Online Knowledge-Sharing Community (2019, background): “Moreover, from the perspective of information diffusion, the intensity of group influence on outside users is usually assessed through the number of infected nodes, the probability of infection, and infected targets [88,89].”
DeepHawkes: Bridging the Gap between Prediction and Understanding of Information Cascades (2017, methodology): “We extract the mean time between each retweet [5], the cumulative popularity [2] and incremental popularity [3] every 10 minutes for Sina Weibo and every 3 months for APS.”
Virality Prediction and Community Structure in Social Networks (2013, background): “Existing research has attempted to characterize viral memes in terms of message content [22], temporal variation [16, 24], inﬂuential users [19, 28], ﬁnite user attention [18, 21], and local neighborhood structure [10].”
Viral Video Style: A Closer Look at Viral Videos on YouTube (2014, methodology): “The baseline methods were selected based on two considerations: (1) the methods cover both the well known [13] and the state-of-the-art methods [15, 11]; (2) the comparison between them helps to isolate the contribution of diﬀerent components.”
4chan and /b/: An Analysis of Anonymity and Ephemerality in a Large Online Community (2011, background): “Szabo and Huberman (2010) found that Digg has about 7,100 “threads” each day (1.”
Smart Cities: A Survey on Data Management, Security, and Enabling Technologies (2017, background): “Though accurate prediction models [356], [357] can estimate the popularity of services, service providers may”
Graph Representation Learning via Multi-task Knowledge Distillation (2019, methodology): “Graph structured data are ubiquitous in application domains of machine learning, such as social networks [14, 7], chemistry [17], and biology [16, 1].”
Circadian Patterns of Wikipedia Editorial Activity: A Demographic Analysis (2011, background): “…records (calls [1] and text messages [2]) and web-based societies and media (web-pages [3], movie, news and status sharing sites e.g., YouTube.com [4], digg.com [5] and twitter.com [6]) have opened very interesting insights into features of collective and cooperative dynamics of human systems.”
Chic or Social: Visual Popularity Analysis in Online Fashion Networks (2014, background): “Work in this direction has mainly looked into early social reaction to content and the prediction of popularity growth in videos [5, 16, 14, 3, 4], news [10, 18], and discussion forums [9].”