RecTemp: Temporal Reasoning in Recommender
Systems Workshop

The RecTemp 2024 workshop is dedicated to the exploration and advancement of temporal dynamics in recommender systems. This specialized workshop seeks to spotlight the pivotal role that temporal data plays in enhancing the accuracy and relevance of recommendations across diverse applications, from digital media to e-commerce, and beyond.

As the digital landscape evolves, so too does the complexity of user interactions and behaviors, which are increasingly influenced by various temporal factors. Traditional recommender systems that overlook these dynamic elements may fail to capture the full spectrum of user preferences that change over time. Therefore, understanding and integrating these temporal dimensions is crucial for developing more sophisticated, responsive, and personalized recommendation technologies.

RecTemp 2024 invites the global community of researchers, industry professionals, and academics to contribute their insights and research on how temporal reasoning can be effectively incorporated into recommender systems. By bringing together a wide range of perspectives, the workshop aims to foster a rich dialogue about the state-of-the-art methodologies, challenges, and innovations in this field. Participants will have the opportunity to present their findings, discuss theoretical and practical challenges, share novel approaches, and explore future directions for temporal reasoning in recommender systems.

We look forward to your contributions and to an engaging exchange of ideas that will push the boundaries of current recommender system capabilities and pave the way for new advancements. 

Key discussion topics include:

• Case studies highlighting the critical role of temporal factors.

• Methods for integrating temporal data into recommendation algorithms.

• Strategies for comprehensive data integration.

• Utilization of diverse data sources, including catalogs and usage logs.

• Solutions to the cold-start problem using temporal data insights.

• Enhancing personalization and group recommendations with temporal analysis.

• Exploring cross-domain temporal patterns for broader insights.

• Enriching temporal data with side information to improve recommendations.

• Exploring the impact of temporal aspects on the application of LLMs in recommender systems.

Submission Types and Guidelines

• Long papers ­ 6-8 pages + references.

• Short pages: 4 pages + references.

• Position/Demo papers: 2 pages + references.

1. Note that the references do not count towards page limits. 

2. Papers that exceed the page limits or formatting guidelines will be returned without review. 

3. Submissions should be single-blinded, i.e. authors names should be included in the submissions.

4. Papers must be formatted using the ACM Standard SIGCONF templates (two-column conference format).

5. Demos need to provide links to the systems presented. 

6. Work that has already been published should not be submitted unless it introduces a significant addition to the previously published work.

7. An international panel of experts will review all submissions.