[CFP] 4th Workshop on Group Modeling, Adaptation and Personalization (GMAP) @UMAP 2025

*** Apologies for cross postings ***

GMAP Workshop @UMAP 2025 - CALL FOR PAPERS - *** DEADLINE APRIL, 9 ***
---------------------------------------------------------------------------------------------------------------------------
4th Workshop on Group Modeling, Adaptation and Personalization (GMAP@UMAP 2025) co-located with UMAP 2025 (https://www.um.org/umap2025/ <https://www.um.org/umap2024/>), June 16-19, 2024 | New York City, New York (United States) 
  
Web: https://sites.google.com/view/gmap2025/ <https://sites.google.com/view/gmap2025/> 
Submission: https://easychair.org/my/conference?conf=umap2025 <https://easychair.org/my/conference?conf=umap2025> (select "GMAP - 4th Workshop on Group Modeling, Adaptation and Personalization”)
For any information: f.barile@maastrichtuniversity.nl <mailto:f.barile@maastrichtuniversity.nl> , adelic@etf.unsa.ba <mailto:adelic@etf.unsa.ba>
 
=========
ABSTRACT
=========
While most existing HCI and decision-support systems are designed to support single users, there are scenarios where these systems should consider the needs of groups. In these cases, specific challenges have to be addressed. Collective factors - such as interpersonal relationships, group mood, and emotional contagion - play a crucial role in group dynamics. Still, they are often ill-defined and absent from systems’ modeling. Furthermore, producing fair, privacy-protecting, and explainable recommendations is a notorious challenge of group recommender systems. The potential of large language models to enhance explainability and tackle these challenges is still under-explored. Lastly, the problem of defining a comprehensive evaluation methodology that covers the particularities of group recommender systems is a long-standing issue in the field. 

The 4th Workshop on Group Modeling, Adaptation and Personalization (GMAP) aims to bring together a community of researchers from multiple disciplines, including Psychology, Computer Science, and Organizational Behavior. In this workshop, researchers have the opportunity to share research and ideas, fostering a vibrant and inclusive community and creating opportunities for networking and collaboration. Such communities will contribute to advancing our understanding of group modeling, adaptation and personalization, identifying key challenges and opportunities, and developing a shared research agenda to guide future works in the field.


======
TOPICS
======
Topics of interests include but are not limited to:
 
Group Modeling.
- Going beyond standard aggregation strategies, by incorporating adaptable user and group profiles as the group advances towards their choice. 
- How to ensure that preferences of each user (group member) are appropriately taken into consideration when creating group recommendations? 
- How to adapt such recommendations to the user's changing preferences, if any? 
- What are the appropriate aggregation methods for user profiles given a contextual situation setting?

Group Recommender Systems and Group decision-making support.
- How can we best help groups reach acceptable joint decisions, when the system supports discussion or several rounds of suggestions?
- How to decide the appropriate time and format of the suggestion?
- How large language models can be used to support the group decision-making process?

Adaptive team formation systems. 
- How to design systems and algorithms that adapt their team formation decisions to the involved users' suggestions?
- How to ascertain that workers can efficiently explore the very large space of potential collaborators, and form work alliances that are optimal for themselves but also for each (creative) task? 
- How to develop modeling approaches that afford users personal liberty and flexibility (e.g. in selecting their teammates), while maintaining appropriate collaboration and work conduct standards (e.g. in avoiding workplace discrimination)?

Explainability. 
- How can the reasoning of a Group Recommender System be made more transparent and interpretable to group members, so that the trust in a system as well as willingness to accept recommendations is increased? 
- How large language models can be applied to improve the explainability of a GRSys?
- How to assist online crowd workers to interpret the team formation algorithm's decisions? How to assist them comprehend the impact that their own input to the algorithm has, in the context of several decision interconnections?

Adaptability. 
- When a GRSys serves as a decision-support tool within a conversational system, how can this system be made more adaptable to (i) group dynamics, (ii) contextual situations, (iii) moods and emotions in the group, (iv) desired privacy levels, (v) diversity and specificity of preferences in different ``sub-domains'', etc.?

Privacy.
- What are the limitations of existing approaches for implementing privacy in GRSys, and how to overcome these limitations? What are the trade-offs that must be made between privacy and explainability?

Fairness. 
- What are the potential trade-offs between fairness and other performance metrics, such as accuracy and personalization? How can these trade-offs be balanced to improve the overall performance?

Evaluation. 
- How to address the limitations in existing data sets?
- How to define a “valid” set of baselines considering different dimensions and features of a Group Recommender System being evaluated? 
- How to define a well-generalising evaluation framework that covers particularities of various GRSSys goals that will yield reproducible outputs?
- What are the best practices to adopt while evaluating GRSys online?

LLM Applications.
- How can we employ LLMs to obtain a natural interaction with group members allowing effective and user-friendly preference elicitation? 
- How can we use LLMs to produce privacy-preserving explanations? 
- How can LLMs help in adapting recommendations to specific contexts, considering feedback received from users?


============
SUBMISSIONS
============
We encourage the submission of original and novel contributions and make the distinction between two types of submissions (ACM double-column format; figures, tables, proofs, appendixes, acknowledgments, and any other content count toward the page limit):
 
(A) Short Papers (4 pages at most + references);
(B) Long Papers (8 pages at most + references);
 
Submission site: https://easychair.org/my/conference?conf=umap2025 <https://easychair.org/my/conference?conf=umap2025> (select "GMAP - 4th Workshop on Group Modeling, Adaptation and Personalization” within the EasyChair submission form)

All submitted papers will be evaluated by at least two members of the program committee, based on originality, significance, relevance and technical quality. The review process will be single-blind (Authors' names and affiliations can be included in the submission). All accepted papers will be published by ACM within the UMAP 2025 adjunct proceedings and will be available via the ACM Digital Library. At least one author of each accepted paper must register for the workshop and present the paper there.
 
 
================
IMPORTANT DATES
================
- Paper submission: April 9, 2025
- Notification to authors: April 28, 2025
- Workshop papers camera-ready deadline (TAPS system): May 5, 2025
- Workshop Date: June 16-19, 2025 (TBD)

Deadlines refer to 23:59 in the AoE (Anywhere on Earth) time zone.
 
=============
ORGANIZATION
=============
Francesco Barile -  Maastricht University, The Netherlands
Amra Delić - University of Sarajevo, Bosnia and Herzegovina
Ladislav Peska  - Charles University, Czechia
Isabella Saccardi -  Utrecht University, The Netherlands
Cedric Waterschoot - Maastricht University, The Netherlands