Machine Learning in Recommender Systems and Information Retrieval

Dear Colleagues,

Trends in many areas of society (care for the elderly, teaching and learning, nutrition and food, etc.) will be of great social and economic importance in the near future. Technological support will become a factor enabling the equal participation of disadvantaged groups in these areas. Explainable recommendation systems empowered by situational awareness and artificial social intelligence will be crucial building blocks of such technologies.

The aim of this Special Issue is to bring the latest scientific and technological advances applicable to explainable recommendation and information retrieval solutions to the next level of socially intelligent, situation-aware systems offered to end users as simple and friendly yet highly effective solutions. Among others, the latest developments in large-scale language models and generative models and artificial social intelligence based on new machine learning and sensing technologies enable the development of ready-to-use services in a real-world environment for the direct benefit of end-users. This Special Issue focuses in particular on the domain-dependent realistic measurement of the impact and effects of these technologies in a real-world environment.

For this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

Recommender system specifics:

• Approaches and algorithms for personalized, situation-aware, and socially intelligent recommender systems;
• Interpretable models for recommendations;
• Explainability and explainable recommendations;
• Privacy and ethical issues.

Recommender systems according to domains

• Recommenders for elderly care and healthcare support;
• Food and healthy living recommendations;
• Recommenders for learning and teaching;
• Recommenders for smart homes;
• Recommenders for industry.

Situation awareness of recommenders and information retrieval

• Situation awareness in recommender systems and information retrieval;
• Machine learning for automatic user context recognition;
• Methodology and procedures for context relevance;
• Methods for latent context generation;
• Conversational recommenders and sequential recommendations.

Sensing and data acquisition, labeling, and experimentation

• Real time data retrieval from sensors (sensors, connection, storage, protection);
• Instruments (questionnaires) for user-related information retrieval in recommender systems;
• Annotation and labeling of data, statistical assignment of labels, reliability, and agreement;
• User in the loop experiments for recommendations and information retrieval.

Social signal processing and recommender systems

• Social signal processing for recommendations and information retrieval;
• Machine learning and statistical modeling for end-user social signals attention, engagement, fatigue, cognitive load, stress, and others;
• Use of user social signals in recommenders.

Measuring the impact of recommendations and explanations

• Measurement of recommender system impact in real world: elderly (independent living, healthy aging), learning and teaching (learning indicators, attention etc.);
• User understanding of explanations, consistency of explanations;
• Context-dependent explanations and dynamic explanations;
• Long-term effects and impacts of recommendations;
• Domain-dependent success metrics of recommendations and explanations;
• Generative models for explainable recommender systems.

I look forward to receiving your contributions.

Prof. Dr. Andrej Košir
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• recommender systems
• information retrieval
• explainable recommender systems
• situation awareness
• sensing and sensors
• evaluation of recommender systems