Recent Advances in Information Retrieval and Recommendation Systems

Dear Colleagues,

Data mining and machine learning have revolutionised many scientific fields. In information retrieval, systems can search the web, act as question-answering systems, work as personal assistants, work with chatbots, and search digital libraries.

Information retrieval systems can act as rankers, a typical task they share with recommendation systems. The two fields also share the ability to search efficiently and possibly in a personalised way in large corpora, knowledge bases, heterogeneous sources, content and digital libraries. Both compete in the same application areas. Both can advance with the integration of external knowledge, leading to knowledge-based systems.

Furthermore, the novel techniques of deep learning neural networks and transformers can advance both systems even more drastically, making them more similar and leading to convergence into a unique system type. 

This Special Issue addresses the above topics as well as the following topics:

• The convergence of information retrieval and recommendation systems;
• The architecture, the technology, the algorithms for searching, digesting, transforming, filtering, learning on massive data;
• Real-time and online data processing and analysis;
• Heterogeneous and multimedia content;
• Pipelines and integration of machine learning tasks in the system;
• Bias in data and its impact on system results;
• Knowledge integration in the system;
• Integration of context in question answering;
• Personalisation and consideration of the user;
• Privacy and robustness of the system;
• Explainability of the system and its results;
• Accountability of the pipeline;
• Applications.

Dr. Rosa Meo
Dr. Luca Cagliero
Guest Editors

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. Applied Sciences 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.

• recommendation systems
• information retrieval
• transformers
• deep neural networks
• bias
• privacy preserving
• accountability
• knowledge integration
• context aware
• personalized system

Title: An Information retrieval system on tenders, economic operators
Authors: Ishrat Fatima; Roberto Nai; Gabriele Morina; Rosa Meo; Paolo Pasteris
Affiliation: Department of Computer Science, University of Torino, C.so Svizzera 185, 10149 Torino, Italy

Title: Perceived Usefulness of a Mandatory Information System
Author: Fridkin
Highlights: Perceived Ease of Use: Significantly and positively influences Perceived Usefulness. Perceived Usefulness: Significantly and positively affects Symbolic Adoption. Supervisor Influence: Significantly and positively impacts Perceived Usefulness. Mediating Relationships: The relationship between Perceived Ease of Use and Symbolic Adoption is fully mediated by Perceived Usefulness. The relationship between Supervisor Influence and Symbolic Adoption is also fully mediated by Perceived Usefulness.

Title: Emotion-driven music and IoT devices for collaborative exer-games
Authors: Pedro Álvarez
Affiliation: Computer Science and Systems Engineering Department, Engineering Research Institute of Aragon (I3A), University of Zaragoza, 50018 Zaragoza, Spain
Abstract: Exer-games are interactive experiences in which the participants make a set of physical exercises in order to achieve a goal. Some of these games have a collaborative nature, so that the actions and achievements of a participant produce immediate effects in the experience of the others. Music is a stimuli that can be integrated in these games to influence in players' emotions and, as consequence, in the actions that they take. In this paper, a cloud-based framework of music services for enhancing collaborative exer-games is presented. These services provide functionality to make personalised music recommendations based on the emotions that the player is feeling during the game. This functionality requires to combine machine learning algorithms and Internet of Things (IoT) devices for determining the emotional response that songs produce on the listeners and players' emotions. The use of a large-scale architecture for retrieving and processing music information allows to integrate the framework with one of the most popular commercial music providers. The final solution contributes to enhance the personalization level of these games through the emotional dimension of music and, therefore, to create more motivating and effective experiences.