Program and Proceedings

Proceedings

Proceedings of the workshop are available at the following link:
http://ceur-ws.org/Vol-3534

SPONSORED BY: CEUR-WS.org

Mon, Sept 18th, 2023
ROOM 327 – Also Online on the RecSys Virtual Hub

Singapore – (GTM+8)
9:30-9:45Opening
Session Chair: Marco Polignano
Session 1: Conversational
Recsys & Explanations
Session Chair: Marco de Gemmis
9:45-10:00Joyce Zhou, Thorsten Joachims. GPT as a Baseline for Recommendation Explanation Texts“
10:00-10:15
Itallo Silva, Alan Said, Leandro Balby Marinho and Martijn Willemsen. “Leveraging Large Language Models for Recommendation and Explanation“
10:15-10:30Sebastian Lubos, Thi Ngoc Trang Tran, Seda Polat Erdeniz, Merfat El Mansi, Alexander Felfernig, Manfred Wundara and Gerhard Leitner. “Concentrating on the Impact: Consequence-based Explanations in Recommender Systems“
10:30-11:15Coffee Break
Session 2: Preference Elicitation & Explanations Session Chair: Giovanni Semeraro
11:15-11:35Alain Starke, Ayoub El Majjodi, Mehdi Elahi and Christoph Trattner. “The Interplay between Food Knowledge, Nudges, and Preference Elicitation Methods Determines the Evaluation of a Recipe Recommender System“
11:35-11:55Maxwell Szymanski, Cristina Conati, Vero Vanden Abeele and Katrien Verbert. “Designing and Personalising Hybrid Multi-Modal Health Explanations for Lay Users“
11:55-14:00Lunch Break
Session 3: Decision Making Session Chair: Pasquale Lops
14:00-14:20Ahtsham Manzoor, Wanling Cai and Dietmar Jannach. “Factors Influencing the Perceived Meaningfulness of System Responses in Conversational Recommendation“
14:20-14:35Alain Starke, Kimia Emami, Andrea Makarová and Bruce Ferwerda. “Using Visual and Linguistic Framing to Support Sustainable Decisions in an Online Store“
14:35-15:10#Keynote by Marko Tkalcic: “From Amateur Musicianship to Computational Predictors of Media Consumption Experiences
15:10-15:20Closing

Online presentations will be available through the RecSys Virtual Hub (https://www.recsyshub.org/)

Invited Talk

Prof. Marko Tkalčič

Faculty of Mathematics, Natural Sciences and Information Technologies (FAMNIT) at the University of Primorska in Koper, Slovenia

Slides: Download

From Amateur Musicianship to Computational Predictors of Media Consumption Experiences

Mon, Sept 18th, 2023
ROOM 327 – Also Online on the RecSys Virtual Hub

Abstract: Majority of user modelling for recommender system uses behavioural data. Behaviour (implicit data) is only part of the knowledge about users in recommender systems. Cognitive and affective models are important, too. In this talk I will show how the usage of psychology-inspired models can lead to improvements of recommender systems.

Bio: Marko Tkalcic is associate professor at the Faculty of Mathematics, Natural Sciences and Information Technologies (FAMNIT) at the University of Primorska in Koper, Slovenia. He aims at improving personalized services (e.g. recommender systems) through the usage of psychological models in personalization algorithms. To achieve this, he uses diverse research methodologies, including data mining, machine learning, and user studies.