Group Recommender Systems aim to support groups in making collective decisions, and research has consistently shown that the more we understand about group members and their interactions, the better support such systems can provide. In this work, we propose a conceptual framework for modeling group dynamics from group chat interactions, with a particular focus on decision-making scenarios. The framework is designed to support the development of intelligent agents that provide advanced forms of decision support to groups. It consists of modular, loosely coupled components that process and analyze textual and multimedia content, which is shared in group interactions, to extract user preferences, emotional states, interpersonal relationships, and behavioral patterns. By incorporating sentiment analysis, summarization, dialogue state tracking, and conflict resolution profiling, the framework captures both individual and collective aspects of group behavior. Unlike existing approaches, our model is intended to operate dynamically and adaptively during live group interactions, offering a novel foundation for group recommender and decision support systems.

Understanding how students perceive and utilize Large Language Models (LLMs) and how these interactions relate to their learning behavior and individual differences is crucial for optimizing educational process and outcomes. This paper introduces a novel dataset comprising weekly self-reported data from students in an introductory programming course, i.e., students’ AI tool usage, perceived difficulty of weekly subject areas, personality traits, preferred learning styles, and general attitudes toward AI. We present a descriptive overview of the collected data and conduct a correlation analysis to gain first insights into the students’ individual differences and their learning outcomes, frequency of AI tools usage, as well as their attitudes toward AI. The findings reveal that while individual student characteristics did not show significant correlations with final performance or frequency of AI tool usage, the combination of students’ expectations for success and their perceived value of the task (constructs of expectancy theory) were significantly associated with both course outcomes and how often they used the AI tool. Additionally, motivational factors may be the key to fostering positive attitudes toward AI, while personality traits, particularly those related to negative emotionality, may play a more significant role in shaping resistance. This initial analysis lays the groundwork for future investigations on the prospects of AI in support of the students’ learning process.

Group recommender systems (GRSys) focus on the challenges of recommending to groups of users with possibly contradicting needs and preferences. Methodologically, we distinguish between approaches aiming to aggregate preferences of group members and aggregating per-user recommendations. In early GRSys research, this methodological duality did not affect the connected research objectives and evaluation methodology much. However, nowadays, we witness a gradual rift in the research induced by both algorithm classes. In this work, based on a survey of 110 recent GRSys papers, we aim to quantify this rift along several aspects, including involved communities, evaluation datasets, objectives, and baselines. We showcase how little both subtrees have in common nowadays and discuss missed opportunities this rift causes. In conclusion, we also highlight novel research avenues that may contribute towards bridging the rift to the benefit of both research areas.

Group Recommender Systems (GRSys) are designed to recommend items that address the needs of groups of people. Compared to individual users, groups are dynamic entities where interpersonal relationships, group dynamics, emotional contagion, etc., substantially affect the group’s needs. Nevertheless, these characteristics are often poorly defined or overlooked in system modeling. The fourth GMAP workshop brought together a community of scholars focused on group modeling, adaptation, and personalization. The event was dedicated to exploring the challenges and opportunities of supporting collective decision-making, fostering interdisciplinary dialogue, and forging new collaborations. The four presented papers covered a diverse range of topics: (i) an exploratory analysis of LLM applications to group meeting transcripts, (ii) an extensive review of the growing methodological divide in group recommender systems, (iii) a novel application of group modeling for personalizing public displays, and (iv) a detailed examination of prompt design for group recommendations using LLMs.

Adaptive and personalized systems have become pervasive technologies, gradually playing an increasingly important role in our daily lives. Indeed, we are now accustomed to interacting with algorithms that leverage the power of Language Models (LLMs) to assist us in various scenarios, from services suggesting music or movies to personal assistants proactively supporting us in complex decision-making tasks. As these technologies continue to shape our everyday experiences, ensuring that the internal mechanisms guiding these algorithms are transparent and comprehensible becomes imperative. The EU General Data Protection Regulation (GDPR) recognizes the users’ right to explanation when confronted with intelligent systems, highlighting the significance of this aspect. Regrettably, current research often prioritizes the maximization of personalization strategy effectiveness, such as recommendation accuracy, at the expense of model explainability. To address this concern, the workshop aims to provide a platform for in-depth discussions on challenges, problems, and innovative research approaches in the field. The workshop specifically focuses on investigating the role of transparency and explainability in recent methodologies for constructing user models and developing personalized and adaptive systems.

In a decision-making scenario, one group member may need, independently from the other members, to choose an item, e.g., a restaurant, that will be experienced by the group. In a prior research on restaurant recommendation, we have identified two primary tasks of such an organizer of a lunch/dinner event, who is in charge of selecting a proper restaurant for the group: anticipating the other group members’ preferences, to properly enter these preferences in the recommender system, and reconciling incompatible preferences, if they arise in the elicitation phase. To support the first task, we augmented a group recommender system with a machine learning model that predicts group members’ food preferences, about dishes that can be consumed in the restaurant, based on other available information about the members (demographics and preferred cuisine). However, in a user study, we found that supporting functionality to be not effective in improving the quality of the choices made by the organizer. In this paper, we investigate the causes of this poor performance. We analyze the possibility that the poor performance may relate to: the deployed ML models used for food preference prediction, the amount of data about food preferences used for training the ML model, and the complexity of the preference anticipation task. The results of our experiments suggest that neither the ML model nor the scarcity of the preference data is responsible for the observed poor value of the implemented preference recalling function. While a user study seems to confirm the impossibility of accurately predicting food preferences from the considered user’s characteristics (demographics and preferred cuisine).

While most recommender systems cater to individual users’ needs, there are numerous situations where these systems are needed to meet groups’ demands. These systems are broadly labelled as Group Recommender Systems (GRSys). Traits like interpersonal relationships, group mood, and emotional contagion are essential to fulfilling the group’s needs. However, the group’s characteristics are frequently ill-defined and dynamic and are typically absent from systems modeling. Moreover, GRSys must maneuver between the needs of the group and the individuals when opinions differ and can contradict each other. The third edition of GMAP proposes consolidating a community of scholars interested in group modeling, adaptation, and personalization. Through the workshop, researchers continue their examination of the difficulties and possibilities of creating efficient procedures and instruments to facilitate collective decision-making. GMAP 2024 offered this unique opportunity to gather scholars from different fields to enrich discussions over GRSys’ research. The workshop also allowed attendees to strengthen their networks and establish new connections conducive to cutting-edge collaborative research.

In everyday life, we make decisions in groups about a variety of issues. In group decision-making, group members discuss options, exchange preferences and opinions, and make a common decision. Decision support systems and group recommender systems facilitate this process by enabling preference elicitation, generating recommendations, and supporting the process. We are here interested in building a conversational system, namely, a chat app, enhanced with an AI agent supporting the group decision-making process. To design the system, rather than solely relying on our assumptions, we took one step back and conducted a comprehensive focus group study. This approach has allowed us to gain original insights into the specific needs and preferences of the future end-users, i.e., group members, ensuring that our system design aligns more closely with their requirements. The focus group study involved fourteen participants in three group compositions: friends, families, and couples. Our findings reveal that most of the group members define a good choice as one that maximizes overall satisfaction without leaving any member dissatisfied. Dealing with competing group members emerged as a primary concern, with study participants requesting specific help from the AI agent to address this challenge. Participants identified personality and group structure as crucial characteristics for the AI agent to properly operate, though some expressed privacy concerns. Lastly, participants expected an AI agent to provide private interactions with individual members, proactively guide discussions when necessary, continually analyze group interactions, and tailor support to those interactions.

This study scrutinizes five years of Sarajevo’s Air Quality Index (AQI) data using diverse machine learning models — Fourier autoregressive integrated moving average (Fourier ARIMA), Prophet, and Long short-term memory (LSTM)—to forecast AQI levels. Focusing on various prediction frames, we evaluate model performances and identify optimal strategies for different temporal granularities. Our research unveils subtle insights into each model’s efficacy, shedding light on their strengths and limitations in predicting AQI across varied timeframes. This research presents a robust framework for automatic optimization of AQI predictions, emphasizing the influence of temporal granularity on prediction accuracy, automatically selecting the most efficient models and parameters. These insights hold significant implications for data-driven decision-making in urban air quality control, paving the way for proactive and targeted interventions to improve air quality in Sarajevo and similar urban environments.

Messaging apps, such as Telegram and WhatsApp, are routinely used to communicate, chat and make decisions. Group Recommender Systems (GRSs) have been introduced as self standing tools to support group interactions and decision-making. We present here a TelegramBot, named CHARM, that supports groups to make a decision on an arbitrary topic by leveraging GRSs techniques. CHARM helps elicit the group members’ preferences, ranks the items that the members have suggested to be considered, provides a summary of the current status of the discussion, and finally recommends a fair choice. A focus group study has revealed that the designed functionality includes features that users expect to find in a bot aimed at supporting group decision-making.