Conversational Information Retrieval (CIR) has garnered increasing research interest in recent years, especially with the rise of conversational agents powered by generative AI methods. Most research in CIR within the information retrieval (IR) community has concentrated on the complex interactive processes between users and CIR systems. However, there has been less focus on modeling the user within these interactions. This workshop aims to gather perspectives and proposals on user modeling in CIR, particularly in relation to algorithm design, personalization, and methods for simulating and evaluating these models.

The workshop's purpose is to provide a platform for discussing user-centric approaches to conversational information retrieval. The central theme of the workshop is user modeling, with discussions spanning various aspects such as personalization, conversation modeling, user simulations, and the evaluation of CIR systems.

The workshop will be a half-day event, featuring keynote presentations that will either offer in-depth analyses or broad perspectives on conversational information retrieval. The program includes an invited keynote speaker and presentations of accepted papers. Participants will also engage in break-out discussion groups focused on the main research topics and themes that emerge from the contributions. The event will conclude with a panel discussion that integrates the insights from the presented work.

Following the UM-CIR Workshop at SIGIR-AP 2024, a special workshop will be held the next day at the National Institute of Informatics (NII) in Tokyo, Japan. This event will continue to explore the core themes of UM-CIR, while also extending the discussion to emerging trends in conversational information retrieval. It offers participants another chance to delve into cutting-edge research and engage in in-depth discussions. For further details, visit ET-CIR Workshop. The results of the workshops will be published in the SIGIR Forum.

Submission Guidelines

Authors are invited to submit original, unpublished research papers that are not being considered for publication in any other forum. Manuscripts should be submitted electronically in PDF format.

Submissions of papers must be at least 2 pages and at most 9 pages (including figures, tables, proofs, appendixes, acknowledgements, and any content except references) in length, with unlimited pages for references. Submissions of papers must be in English, in PDF format, in the current ACM two-column conference format. Suitable LaTeX, Word, and Overleaf templates are available from the ACM Website (use the “sigconf” proceedings template for LaTeX and the Interim Template for Word). Authors may choose to submit their research papers to both the SIGIR-AP conference and the NII Workshop.

All submissions must be original, not previously published or accepted, and not currently under review by another journal or conference. The program committee will review the manuscripts based on their technical soundness and relevance to the workshop's targeted community. The review process will be double-blind, so authors must anonymize their names and any identifying information in the manuscript.

List of Topics

We encourage submissions that relate (but are not limited) to the following themes and topics:

• Personalization
  • New methods for modelling users in CIR (personalization)
  • Modelling user emotion
  • Mining and modelling users
  • User knowledge representation and extraction
  • Datasets: new source, new way to collect
  • Introducing personalization
  • Focusing on specialized user groups and personalities, for example, psychologically affected users
• Modelling Conversation
  • Alignment between current user modelling and the real user in CIR
  • Modelling user and user behaviour
  • Conversational Knowledge extraction and representation
  • Other theoretical models and foundations of user-centric modelling of CIR.
• User Simulation
  • User simulation of CIR
  • Dataset for user simulation of CIR
  • Other theoretical models and foundations of user simulation of CIR.
• Evaluation
  • User-centered evaluation of CIR
  • User studies, user engagement
  • System-oriented evaluation of CIR
  • Simulated Evaluation of CIR
  • Metrics to measure the effectiveness of CIR
  • Data sets, Test collection, Resources
  • Other theoretical models and foundations of user-centric evaluation of CIR.

Committees

Organizing Committee

• Praveen Acharya, Dublin City University, Ireland
• Gareth J. F Jones, Dublin City University, Ireland
• Xiao Fu, University College London, UK
• Aldo Lipani, University College London, UK
• Fabio Crestani, Universitá della Svizzera Italiana, Switzerland
• Noriko Kando, National Institute of Informatics, Japan

Submit paper to

• SIGIR-AP Workshop
• NII Workshop

Publication

We plan on publishing the proceedings at CEUR-WS.org.

Venue

The conference will be Co-located with SIGIR-AP: 2^nd International ACM SIGIR Conference on Information Retrieval in the Asia Pacific December 9-12, 2024, in Tokyo, Japan

Contact

All questions about submissions should be emailed to umcir.workshop@gmail.com