Persuasive Recommender Systems - Keynote Markus Zanker Abstract Free University of Recommender Systems (RS) have become indispensable Bozen-Bolzano tools to support users when confronted with large collec- 39100 Bozen-Bolzano, Italy tions. They focus the attention of users on a subset of items mzanker@unibz.it out of a variety of choices. Therefore RS are inherently persuasive online tools trying to pair users with items that might constitute a better match with their preferences than those choices the users might know already or they could detect on their own without the help of virtual guides. The goal of this talk is therefore to explore the range of influen- tial cues and aspects that have been shown to influence the opinions of users and discuss avenues for further re- search. Outline Persuasion is generally seen as the intended inducing of another person to believe something, to do something or to change attitudes, mood and behavior (compare for instance to [4]). Persuasion obviously takes place via communication and argumentation, but not only. The Elaboration Likelihood Model (ELM) [3] has been proposed to explain these per- suasion effects of messages. It principally identifies a main Copyright is held by the author/owner(s). route towards persuasion that depends on the character- EICS’16, June 21-24, 2016, Bruxelles, Belgium. istics of the message itself, i.e. the quality and strength of an argument as a main determinant of persuasion effects. However, in addition there is also consistent empirical ev- idence that there is a peripheral route towards persuasion 1 that depends on various sender and receiver characteris- References tics. For instance, the willingness and conceptual ability of [1] Ulrike Gretzel and Daniel Fesenmaier. 2006. "Persua- the receiver to scrutinize the argument of a message has a sion in Recommender Systems". International Journal moderating effect on the persuasion, i.e. enhanced scrutiny of Electronic Commerce 11 (2006), 81–100. Issue 2. of a "strong" message makes the persuasion effect even [2] Dietmar Jannach, Markus Zanker, Mouzhi Ge, and stronger while an inhibited ability to scrutinize would have a Marian Groening. 2000. Recommender Systems in weakening effect. Furthermore, additional peripheral cues Computer Science and Information Systems - a Land- such as characteristics of the source of communication like scape of Research. In 13th International Conference its credibility or its attractiveness of appearance also have on Electronic Commerce and Web Technologies (EC- an effect on the strength and direction of the induced atti- Web). Springer, Vienna, Austria, 76–87. tude change. In the context of recommendation systems [3] Richard E. Petty and John T. Caccioppo. 1986. "The Gretzel & Fesenmaier [1], for instance, pointed out that the Elaboration Likelihood Model of Persuasion". Ad- way the user’s preferences are elicited has not only an ef- vances in Experimental Social Psychology 19 (1986), fect on how users perceive the process but also influences 123–205. their perception of the fit between their preferences and the [4] Oliviero Stock. 2015. "A (Persuasive?) Speech on recommendations. Thus persuasion happens side by side Automated Persuasion". Keynote at 9th ACM Confer- with recommendation. In Yoo et al. [6] we structured these ence on Recommender Systems. (September 2015). peripheral clues in the context of product recommendations "https:www.youtube.comwatch?v=JXn_SIZ8v5w". that may have an influence on the users’ perception of the [5] Erich Teppan and Markus Zanker. 2015. "Decision recommendation systems and its proposals into the type Biases in Recommender Systems". Journal of Internet of the RS, factors related to the preference elicitation, the Commerce 14 (2015), 255–275. Issue 2. process and the output and aspects concerning the embod- [6] K.-H. Yoo., U. Gretzel, and M. Zanker. 2013. Persua- iment of a recommendation agent. By primarily focusing on sive Recommender Systems - Conceptual Background accuracy a lot of recommender systems research ignores and Implications. Springer, New York. these appearance and interaction dependent aspects of a [7] Markus Zanker. 2012. The influence of knowledgeable RS [2]. explanations on users’ perception of a recommender system. In Proceedings of the 2012 ACM Conference This talk therefore gives an overview on the impact of per- on Recommender Systems. ACM, Dublin, Ireland, suasive traits in the interaction with recommendation sys- 269–272. tems [6] as well as focuses on opportunities for further re- [8] Markus Zanker and Martin Schoberegger. 2014. An search such as explanations of recommendations [7], the empirical study on the persuasiveness of fact-based impact of different design variants of these explanations explanations for recommender systems. In Joint Work- such as their style of presentation [8] or the application of shop on Interfaces and Human Decision Making in decision phenomena like decoy or framing effects and their Recommender Systems held in conjunction with the interaction effects [5]. 8th ACM Conference on Recommender Systems. Fos- ter City, USA, 33–36. 2