How A/B testing changes the dynamics of information spreading on a social network (2405.01165v1)
Abstract: A/B testing methodology is generally performed by private companies to increase user engagement and satisfaction about online features. Their usage is far from being transparent and may undermine user autonomy (e.g. polarizing individual opinions, mis- and dis- information spreading). For our analysis we leverage a crucial case study dataset (i.e. Upworthy) where news headlines were allocated to users and reshuffled for optimizing clicks. Our centre of focus is to determine how and under which conditions A/B testing affects the distribution of content on the collective level, specifically on different social network structures. In order to achieve that, we set up an agent-based model reproducing social interaction and an individual decision-making model. Our preliminary results indicate that A/B testing has a substantial influence on the qualitative dynamics of information dissemination on a social network. Moreover, our modeling framework promisingly embeds conjecturing policy (e.g. nudging, boosting) interventions.
- Blom, J. N. and K. R. Hansen (2015). Click bait: Forward-reference as lure in online news headlines. Journal of Pragmatics 76, 87 – 100.
- Misleading online content: Recognizing clickbait as ”false news”. In Proceedings of the 2015 ACM on Workshop on Multimodal Deception Detection, WMDD ’15, New York, NY, USA, pp. 15–19. Association for Computing Machinery.
- Sentiment analysis and social cognition engine (seance): An automatic tool for sentiment, social cognition, and social-order analysis. Behavior research methods 49(3), 803–821.
- Frasco, M. (2018). The power of bayesian a/b testing.
- Market stability with machine learning agents. Available at SSRN 3374666.
- Democratizing online controlled experiments at booking. com. arXiv preprint arXiv:1710.08217.
- Seven rules of thumb for web site experimenters. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 1857–1866.
- Citizens versus the internet: Confronting digital challenges with cognitive tools. Psychological Science in the Public Interest 21(3), 103–156.
- Effective headlines of newspaper articles in a digital environment. Digital Journalism 5(10), 1300–1314.
- Metalearners for estimating heterogeneous treatment effects using machine learning. Proceedings of the national academy of sciences 116(10), 4156–4165.
- How behavioural sciences can promote truth, autonomy and democratic discourse online. Nature Human Behaviour, 1–8.
- The upworthy research archive: A time series of 32,488 experiments in us advocacy.
- Asking questions of the upworthy research archive.
- Miller, E. (2015). Formulas for bayesian a/b testing.
- Pariser, E. (2011). The filter bubble: How the new personalized web is changing what we read and how we think. Penguin.
- The clickbait challenge 2017: Towards a regression model for clickbait strength. arXiv preprint arXiv:1812.10847.
- Rubin, D. B. (1974). Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of educational Psychology 66(5), 688.
- Safran, N. (2013). Data insights into the headlines readers click. Moz, July 13, 5.
- From infrastructure to culture: A/b testing challenges in large scale social networks. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2227–2236.
- Boost clickbait detection based on user behavior analysis. In L. Chen, C. S. Jensen, C. Shahabi, X. Yang, and X. Lian (Eds.), Web and Big Data, Cham, pp. 73–80. Springer International Publishing.