When Personalization Is Not an Option: An In-The-Wild Study on Persuasive News Recommendation

Aiming at granting wide access to their contents, online information providers often choose not to have registered users, and therefore must give up personalization. In this paper, we focus on the case of non-personalized news recommender systems, and explore persuasive techniques that can, nonetheless, be used to enhance recommendation presentation, with the aim of capturing the user’s interest on suggested items leveraging the way news is perceived. We present the results of two evaluations “in the wild”, carried out in the context of a real online magazine and based on data from 16,134 and 20,933 user sessions, respectively, where we empirically assessed the effectiveness of persuasion strategies which exploit logical fallacies and other techniques. Logical fallacies are inferential schemes known since antiquity that, even if formally invalid, appear as plausible and are therefore psychologically persuasive. In particular, our evaluations allowed us to compare three persuasive scenarios based on the Argumentum Ad Populum fallacy, on a modified version of the Argumentum ad Populum fallacy (Group-Ad Populum), and on no fallacy (neutral condition), respectively. Moreover, we studied the effects of the Accent Fallacy (in its visual variant), and of positive vs. negative Framing.

[1]  Kyung Hyan Yoo,et al.  The Influence of Perceived Credibility on Preferences for Recommender Systems as Sources of Advice , 2008, J. Inf. Technol. Tour..

[2]  J. Cacioppo,et al.  Personal involvement as a determinant of argument based persuasion , 1981 .

[3]  Francesca Rossi,et al.  AI4People—An Ethical Framework for a Good AI Society: Opportunities, Risks, Principles, and Recommendations , 2018, Minds and Machines.

[4]  Harri Oinas-Kukkonen,et al.  Influencing Individually: Fusing Personalization and Persuasion , 2012, TIIS.

[5]  Arie Dijkstra,et al.  Personalization and perceived personal relevance in computer-tailored persuasion in smoking cessation. , 2012, British journal of health psychology.

[6]  Jan vom Brocke,et al.  Digital nudging , 2018, Commun. ACM.

[7]  Boris E. R. de Ruyter,et al.  Adaptive Persuasive Systems: A Study of Tailored Persuasive Text Messages to Reduce Snacking , 2012, TIIS.

[8]  Julita Vassileva,et al.  Modeling the efficacy of persuasive strategies for different gamer types in serious games for health , 2014, User Modeling and User-Adapted Interaction.

[9]  Mark Rosenstein,et al.  Recommending and evaluating choices in a virtual community of use , 1995, CHI '95.

[10]  Sean M. McNee,et al.  Being accurate is not enough: how accuracy metrics have hurt recommender systems , 2006, CHI Extended Abstracts.

[11]  Yvonne Rogers,et al.  Interaction design gone wild: striving for wild theory , 2011, INTR.

[12]  Blair T. Johnson.  Effects of Outcome-Relevant Involvement and Prior Information on Persuasion , 1994 .

[13]  Rita Orji,et al.  Personalized Persuasion to Promote Positive Work Attitudes in Public Workplaces , 2019, UMAP.

[14]  Boris E. R. de Ruyter,et al.  Personalizing persuasive technologies: Explicit and implicit personalization using persuasion profiles , 2015, Int. J. Hum. Comput. Stud..

[15]  E. Berscheid,et al.  What is beautiful is good. , 1972, Journal of personality and social psychology.

[16]  Sharad Goel,et al.  The Effect of Recommendations on Network Structure , 2016, WWW.

[17]  John Riedl,et al.  Explaining collaborative filtering recommendations , 2000, CSCW '00.

[18]  Jules Polonetsky,et al.  To Track or 'Do Not Track': Advancing Transparency and Individual Control in Online Behavioral Advertising , 2011 .

[19]  Judith Masthoff,et al.  Designing and Evaluating Explanations for Recommender Systems , 2011, Recommender Systems Handbook.

[20]  Peter Brusilovsky,et al.  Adaptive Navigation Support , 2007, The Adaptive Web.

[21]  Matthew J. Salganik,et al.  Experimental Study of Inequality and Unpredictability in an Artificial Cultural Market , 2006, Science.

[22]  Gaby G. Dagher,et al.  Product recommendation system for small online retailers using association rules mining , 2014, Proceedings of the 2014 International Conference on Innovative Design and Manufacturing (ICIDM).

[23]  Sneha Khatwani,et al.  Building Personalized and Non Personalized recommendation systems , 2016, 2016 International Conference on Automatic Control and Dynamic Optimization Techniques (ICACDOT).

[24]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[25]  K. Shimizu.  Prospect theory, behavioral theory, and the threat-rigidity thesis: Combinative effects on organizational decisions to divest formerly acquired units , 2007 .

[26]  Haiyi Zhu,et al.  To Switch or Not To Switch , 2014 .

[27]  Kiemute Oyibo,et al.  Personalization of Persuasive Technology in Higher Education , 2019, UMAP.

[28]  Debajyoti Mukhopadhyay,et al.  A Product Recommendation System Using Vector Space Model and Association Rule , 2008, 2008 International Conference on Information Technology.

[29]  Timothy B. Palmer,et al.  Decoupling risk taking from income stream uncertainty: a holistic model of risk , 1999 .

[30]  Mario Cataldi,et al.  The 10 million follower fallacy: audience size does not prove domain-influence on Twitter , 2014, Knowledge and Information Systems.

[31]  John Riedl,et al.  Recommender systems in e-commerce , 1999, EC '99.

[32]  James D. Hollan,et al.  Edit wear and read wear , 1992, CHI.

[33]  Jennifer Healey,et al.  Personalizing with Human Cognitive Biases , 2019, UMAP.

[34]  J. Beniger.  Personalization of Mass Media and the Growth of Pseudo-Community , 1987 .

[35]  A. Tversky,et al.  The framing of decisions and the psychology of choice. , 1981, Science.

[36]  Klaus G. Grunert,et al.  Visual Biases in Decision Making , 2018, Applied Economic Perspectives and Policy.

[37]  B. J. Fogg,et al.  What makes Web sites credible?: a report on a large quantitative study , 2001, CHI.

[38]  Ayhan Demiriz,et al.  Enhancing Product Recommender Systems on Sparse Binary Data , 2004, Data Mining and Knowledge Discovery.