Good Friends, Bad News - Affect and Virality in Twitter

By Lars Kai Hansen, Adam Arvidsson, Finn Årup Nielsen, Elanor Colleoni, M. Etter. arXiv.org, 2011

411 citations recorded by the source corpus.

The link between affect, defined as the capacity for sentimental arousal on the part of a message, and virality, defined as the probability that it be sent along, is of significant theoretical and practical importance, e.g. for viral marketing. The basic measure of virality in Twitter is the probability of retweet and we are interested in which dimensions of the content of a tweet leads to retweeting. We hypothesize that negative news content is more likely to be retweeted, while for non-news tweets positive sentiments support virality. To test the hypothesis we analyze three corpora: A complete sample of tweets about the COP15 climate summit, a random sample of tweets, and a general text corpus including news. The latter allows us to train a classifier that can distinguish tweets that carry news and non-news information. We present evidence that negative sentiment enhances virality in the news segment, but not in the non-news segment. Our findings may be summarized ‘If you want to be cited: Sweet talk your friends or serve bad news to the public’.

Subfields: Communication, Sociology and Political Science, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/f7827478275f38b8800be1dbaf9555eda7c1e2ac

How researchers see this paper

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

In Communication

In Sociology and Political Science

In Statistical and Nonlinear Physics

Citations in the corpus

The MAD Model of Moral Contagion: The Role of Motivation, Attention, and Design in the Spread of Moralized Content Online (2019, positive): “For instance, the same design features on Twitter that allowed people to organize protests to support the growth of democracy in authoritarian regimes (McGarty, Thomas, Lala, Smith, & Bliuc, 2014) also allowed misinformation and conspiracy theories to flourish (Lazer et al., 2018).”
Sarcasm as Contrast between a Positive Sentiment and Negative Situation (2013, background): “The AFINN sentiment lexicon designed for microblogs (Nielsen, 2011; Hansen et al., 2011) contains 2,477 manually labeled words and phrases with integer values ranging from -5 (negativity) to 5 (positivity).”
Machine Learning-Based Sentiment Analysis for Twitter Accounts (2018, methodology): “Two lexicons [51,52] were combined for the sentiment analysis of tweets.”
A New ANEW: Evaluation of a Word List for Sentiment Analysis in Microblogs (2011, methodology): “Although we have used it for sentiment analysis on Twitter data [5] we have not yet validated it.”
Social Media for Socially Responsible Firms: Analysis of Fortune 500’s Twitter Profiles and their CSR/CSIR Ratings (2013, background): “Others report that positive emotion drives diffusion for general contents, while negative emotion promotes diffusion for news contents (Hansen et al. 2011).”
Emotions and Information Diffusion in Social Media—Sentiment of Microblogs and Sharing Behavior (2013, background): “[28], have shown that negative sentiment may enhance virality more than positive sentiment, but only in the domain of news, whereas in some other nonnews domains, the opposite even may hold.”
The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter (2014, background): “(Table 8) Prior work has found that including positive or negative sentiment increases message propagation (Milkman and Berger, 2012; Godes et al., 2005; Heath et al., 2001; Hansen et al., 2011).”