Recent research has shown that explanations serve as an important means to increase transparency in group recommendations while also increasing users' privacy concerns. However, it is currently unclear what personal and contextual factors affect users' privacy concerns about various types of personal information. This paper studies the effect of users' personality traits and preference scenarios-having a majority or minority preference-on their privacy concerns regarding location and emotion information. To create natural scenarios of group decision-making where users can control the amount of information disclosed, we develop TouryBot, a chat-bot agent that generates natural language explanations to help group members explain their arguments for suggestions to the group in the tourism domain. We conducted a user study in which we instructed 541 participants to convince the group to either visit or skip a recommended place. Our results show that users generally have a larger concern regarding the disclosure of emotion compared to location information. However, we found no evidence that personality traits or preference scenarios affect privacy concerns in our task. Further analyses revealed that task design (i.e., the pressure on users to convince the group) had an effect on participants' emotion-related privacy concerns. Our study also highlights the utility of providing users with the option of partial disclosure of personal information, which appeared to be popular among the participants.

Explanations can help users to better understand why items have been recommended. Additionally, explanations for group recommender systems need to consider further goals than single-user recommender systems. For example, we need to balance group members' need for privacy with their need for transparency, since a transparent explanation might pose a privacy hazard. In an online experiment with real groups (n=114 participants: 38 groups of size 3), we seek to understand which factors influence people's privacy concerns when a single explanation is presented to a group in the tourism domain. In particular, we study the direct effects of three factors on privacy concern: a) group members' personality (using the ĝ€ Big Five' personality traits), b) specific preference scenarios (i.e., having minority or majority preferences compared to two other group members), c) the type of relationship they have in the group (i.e., loosely coupled heterogeneous, versus tightly coupled homogeneous). We find that for personality two traits, Extroversion, and Agreeableness, each significantly affects the privacy concern. Moreover, having the minority or majority preferences in the group, as well as the type of relationship people have in the group, have a strong and significant influence on participants' privacy concern. These results suggest that explanations presented to groups need to be adapted to all three factors (personality, type of relationship, and preference scenario) when considering the privacy concern of users.

As part of the main program of the 2019 ACM Recommender System Conference, the Late-Breaking Results ofers a unique opportunity to share with the community the latest ideas related to recommender systems. This year, we received 42 submissions for the track, out of which 13 were accepted, resulting in a acceptance rate of 31%.

In this position paper we present the scenario of making interventions for increasing the classical music concert-going behaviour of end users. Within the FP7 Phenicx project we are developing a personalized persuasive system that attempts at changing the concert-going behaviour of users. The system is based on the theory of planned behaviour user model for predicting whether a user will attend a concert or not. Our goal is to develop a machine learning algorithm that will extract the user model parameters unobtrusively from the micro-blogs of the users. We plan to perform a user study to build the training dataset and to test the system on real users within the project.