Recommender Systems for Sustainability and Social Good

This book constitutes the refereed proceedings of the Second International Workshop on Recommender Systems for Sustainability and Social Good, RecSoGood 2025, held in Prague, Czech Republic, on September 26, 2025.

The 10 full papers and 4 short papers included in this volume were carefully reviewed and selected from 35 submissions. They cover theoretical, methodological, and applied perspectives, emphasizing both the environmental and social dimensions of recommendation technology.

Inhalt

A Holistic View of Sustainability in Multimodal Recommender.- Sustainability Evaluation Metrics for Recommender Systems.- Towards Greener Choices: Decision Information Nudging for Sustainability-Aware Recommender Explanations.- Estimating Product Carbon Footprint via Large Language Models for Sustainable Recommender Systems.- TRUST-MH: Transparent and Responsible User-level Semantic Tagging for Mental Health Assessment.- SERMuse: Speech Emotion Recognition based Music Recommendation.- LLM-based Healthiness? Analyzing the Nutritional Quality of an AI-Generated Recipe Dataset.- Diversified Recommendations of Cultural Activities with Personalized Determinantal Point Processes.- LLM-Powered Recommendations: a Case Study in Renewable Energy Communities.- Mind the Gap: Urban-Rural Disparities in Wheelchair Accessibility for POI Recommendations.- Early Explorations of Recommender Systems for Physical Activity and Wellbeing.- E-Mealio: An LLM-Powered Conversational Agent for Sustainable and Healthy Food Recommendation.- Biases of Algorithmic and Editorial Recommendations in Public Service Media.- PureBiasoMeter: Decoupling Popularity Bias from User Fairness in LLM-Based Recommender Systems.