On the relation between message sentiment and its virality on social media

被引：39
作者：
Tsugawa S. [1 ]
Ohsaki H. [2 ]
机构：
[1] Faculty of Engineering, Information and Systems, University of Tsukuba, 1-1-1 Tennodai, Tsukuba, 305-8573, Ibaraki
[2] School of Science and Technology, Kwansei Gakuin University, Sanda
来源：
Social Network Analysis and Mining | 2017年 / 7卷 / 1期
关键词：
Information diffusion; Retweet; Sentiment; Social media; Twitter;
D O I：
10.1007/s13278-017-0439-0
中图分类号：
学科分类号：
摘要：
We investigate the relation between the sentiment of a message on social media and its virality, defined as the volume and speed of message diffusion. We analyze 4.1 million messages (tweets) obtained from Twitter. Although factors affecting message diffusion on social media have been studied previously, we focus on message sentiment and reveal how the polarity of message sentiment affects its virality. The virality of a message is characterized by the number of message repostings (retweets) and the time elapsed from the original posting of a message to its Nth reposting (N-retweet time). Through extensive analysis using the 4.1 million tweets and their retweets in 1 week, we discover that negative messages are likely to be reposted more rapidly and frequently than positive and neutral messages. Specifically, the reposting volume of negative messages is 20–60% higher than that of positive and neutral messages, and negative messages spread 25% faster than positive and neutral messages when the diffusion volume is quite high. We also perform longitudinal analysis of message diffusion observed over 1 year and find that recurrent diffusion of negative messages is less frequent than that of positive and neutral messages. Moreover, we present a simple message diffusion model that can reproduce the characteristics of message diffusion observed in this paper. © 2017, Springer-Verlag Wien.
引用
收藏
相关论文
共 37 条
  • [1] Agarwal A., Xie B., Vovsha I., Rambow O., Passonneau R., Sentiment analysis of Twitter data. In: Proceedings of the workshop on languages in social media (LSM’11), (2011)
  • [2] Bakshy E., Hofman J.M., Mason W.A., Watts D.J., Everyone’s an influencer: quantifying influence on Twitter. In: Proceedings of the 4th ACM international conference on web search and data mining (WSDM’11), (2011)
  • [3] Bakshy E., Rosenn I., Marlow C., Adamic L., The role of social networks in information diffusion. In: Proceedings of the 21st international conference on world wide web (’12), (2012)
  • [4] Barbosa L., Feng J., Robust sentiment detection on Twitter from biased and noisy data. In: Proceedings of the 23rd international conference on computational linguistics (COLING’10), (2010)
  • [5] Baumeister R.F., Bratslavsky E., Bad is stronger than good, Rev Gen Psychol, 5, 4, pp. 323-370, (2001)
  • [6] Blei D., Ng A., Jordan M., Latent Dirichlet allocation, J Mach Learn Res, 3, pp. 993l-1022, (2003)
  • [7] Budak C., Agrawal D., ElAbbadi A., Limiting the spread of misinformation in social networks. In: Proceedings of the 20th international conference on world wide web (’11), (2011)
  • [8] Cheng J., Adamic L., Dow P.A., Kleinberg J.M., Leskovec J., Can cascades be predicted? In: Proceedings of the 23rd international conference on world wide web (’14), (2014)
  • [9] Cheng J., Adamic L.A., Kleinberg J., Leskovec J., Do cascades recur? In: Proceedings of the 25th international conference on world wide web (’16), (2016)
  • [10] De Domenico M., Lima A., Mougel P., Musolesi M., The anatomy of a scientific rumor, Sci Rep, 3, pp. 2980:1-2980:9, (2013)
1234