We are pleased to invite you to contribute to the 15th ACM Conference on Recommender Systems (RecSys 2021), the premier venue for research on the foundations and applications of recommendation technologies. The upcoming RecSys conference will be held from September 27th to October 1st 2021. The conference will be held in Amsterdam, Netherlands, with an inclusive format that accommodates remote attendance. The conference will continue RecSys’ practice of connecting the research and practitioner communities to exchange ideas, frame problems, and share solutions. All accepted papers will be published by ACM.
We invite submissions of original research on all aspects of recommender systems, including contributions to algorithms ranging from collaborative filtering to knowledge-based reasoning or deep learning, contributions to design ranging from studies of human preferences and decision-making to novel interaction design, contributions to systems including practical issues of scale and deployment, and contributions through applications that bring forward the lessons of innovative applications across various domains from e-commerce to education to social connections. We welcome new research on recommendation technologies coming from diverse communities ranging from psychology to mathematics. In particular, we care as much about the human and economic impact of these systems as we care about their underlying algorithms.
Topics of interest for RecSys 2021 include but are not limited to (alphabetically ordered):
Algorithm scalability, performance, and implementations
Bias, fairness, bubbles and ethics of recommender systems
Case studies of real-world implementations
Conversational and natural language recommender systems
Cross-domain recommendation
Economic models and consequences of recommender systems
Interfaces for recommender systems
Novel approaches to recommendation, including voice, VR/AR, etc.
Preference elicitation
Privacy and security
Socially- and context-aware recommender systems
Systems challenges such as scalability, data quality, and performance
User studies
Authors will be asked to assign a selection of predefined custom tags to describe their paper in the submission system. Tags can be assigned to indicate algorithms, interfaces, automated or user-centric evaluations, for example. Reviewers will also report their expertise over these tags, and the information will be used in review assignments.
Authors of main track research papers will also be asked to specify whether their work includes a component which is suitable for demonstration, which may be used to select some regular papers for additional presentation alongside other papers in the demo track. In case of acceptance in the main track, authors will be contacted by the Demos chairs to consider the inclusion of their work in the Demos track. Authors of rejected papers that have a demo component will have the opportunity to submit their demo as an independent submission, following the Demos call for participation.
We also point authors to the industry track for discussion of field experiences, deployments, users studies (etc.) that do not follow the framework of regular papers, or align with the reviewing guidelines below. A separate track is also included for late-breaking results papers; this track is intended for preliminary work, mainly focused on fostering discussions with other members of the RecSys community.
Reviewing Process
Reviewers will evaluate papers based on their significance, originality, rigor, and contribution to the field. In view of the RecSys conference goal of advancing the field, reviewers are also asked to consider the replicability of reported research. Replicability is to be assessed in the context of the work itself — we recognize that a set of customer interviews (for example) may not be shareable, but the interview scripts can be provided as may be response coding protocols. Sharing of data sets and code is encouraged, and authors presenting work that was tested on proprietary data may wish to include a secondary analysis on a public or shareable data set.
Papers that are out of scope, incomplete, or lack sufficient evidence to support the basic claims, may be rejected without full review.
This year we will include a short clarification phase, during which authors will be given a chance to submit a very brief response (i.e., up to 1000 characters) to address factual errors in reviews; clarifications may be considered during the discussion phase.
Submission Guidelines
Papers should report on substantial contributions of lasting value. The maximum length is 14 pages (excluding references) in the new single-column format. We encourage papers of any length up to 14 pages; reviewers will be asked to comment on whether the length is appropriate for the contribution. Shorter papers should generally report on advances that can be described, set into context, and evaluated concisely; they are not “work-in-progress” reports but rather complete reports on a smaller or simpler-to-describe but complete research work. Longer papers should reflect more complex innovations or studies and should have a thorough discussion of related work. Each accepted paper will be included in the conference proceedings and presented at the conference. We expect the review process to be highly selective: the acceptance rate for the past few years was about 20%.
All submissions and reviews will be handled electronically. Papers must be submitted to PCS by 23:59, AoE (Anywhere on Earth) on May 4th, 2021.
Formatting
ACM’s archival publication format separates content from presentation in the Digital Library to enhance accessibility and improve the flexibility and resiliency of our publications. Following the ACM publication workflow, all authors should submit manuscripts for review in a single-column format. Instructions for Word and LaTeX authors are given below:
Microsoft Word: Write your paper using the Submission Template (Review Submission Format). Follow the embedded instructions to apply the paragraph styles to your various text elements. The text is in single-column format at this stage and no additional formatting is required at this point.
LaTeX: Please use the latest version of the Primary Article Template – LaTeX to create your submission. You must use the “manuscript” option with the \documentclass[manuscript]{acmart} command to generate the output in a single-column format which is required for review. Please see the LaTeX documentation and ACM’s LaTeX best practices guide for further instructions. To ensure 100% compatibility with The ACM Publishing System (TAPS), please restrict the use of packages to the whitelist of approved LaTeX packages.
A document with some frequently asked questions can be found here.
Authors are strongly encouraged to provide “alt text” (alternative text) for floats (images, tables, etc.) in their content so that readers with disabilities can be given descriptive information for these floats that are important to the work. The descriptive text will be displayed in place of a float if the float cannot be loaded. This benefits the author as well as it broadens the reader base for the author’s work. Moreover, the alt text provides in-depth float descriptions to search engine crawlers, which helps to properly index these floats. Additionally, authors should follow the ACM Accessibility Recommendations for Publishing in Color and SIG ACCESS guidelines on describing figures.
Should you have any questions or issues going through the instructions above, please contact support at for both LaTeX and Microsoft Word inquiries.
Accepted papers will be later submitted to ACM’s new production platform where authors will be able to review PDF and HTML output formats before publication.
Anonymity
The peer review process is double-blind (i.e., anonymized). This means that all submissions must not include information identifying the authors or their organization. Specifically, do not include the authors’ names and affiliations, refer to your previous work in the third person (e.g., “McAuley and Konstan (2021) recommended that RecSys submissions be anonymized by referring to the authors’ prior work in the third person.”), and avoid providing any other information that would allow reviewers to identify the authors, such as acknowledgments of individuals and funding sources. However, it is acceptable to explicitly refer in the paper to the companies or organizations that provided datasets, hosted experiments or deployed solutions if there is no implication that the authors are currently affiliated with the mentioned organization. We should note that reviewers are instructed not to search for tech reports, pre-prints, and other information about your research. Your responsibility is focused on making sure that the paper submission itself does not reveal your identity as author.
Ethical Review for Human-Subjects Research
ACM RecSys expects all authors to comply with ethical and regulatory guidelines associated with human subjects research, including research involving human participants and research using personally identifiable data. Papers reporting on such human subjects research must include a statement identifying any regulatory review the research is subject to (and identifying the form of approval provided), or explaining the lack of required review. Reviewers will be asked to consider whether the research was conducted in compliance with applicable ethical and regulatory guidelines.
Originality
Each paper should not be previously published or accepted to any peer-reviewed journal or conference, nor currently under review elsewhere (including as another paper submission for RecSys 2021). Papers published in workshop proceedings may only be submitted if the RecSys submission includes at least 30% new content; such papers must also reference the original workshop paper on the submission form (but not in the anonymized paper).
Plagiarism
Plagiarized papers will not be accepted for RecSys 2021. Our committees will be checking the plagiarism level of all submitted papers to ensure content originality using an automated tool.
If you reuse non-novel text from a prior publication (e.g., the description of an algorithm or dataset), please be sure to cite the prior publication as the source of that text. If you have questions about reuse of text or simultaneous submission, please contact the program chairs at least one week prior to the submission deadline. Please refer to the ACM Publishing License Agreement and Authorship Policy for further details.
Papers violating any of the above guidelines are subject to rejection without review and cases may be referred to the ACM Publications Ethics and Plagiarism committee for further action where warranted.
Patenting
Please take note that the official publication date is the date the proceedings are made available in the ACM Digital Library. This date may be up to two weeks prior to the first day of the conference. The official publication date affects the deadline for any patent filings related to published work.
SIGCHI Submitter Agreement
RecSys 2021 is a SIGCHI conference and making a submission to a SIGCHI conference is a serious matter. Submissions require time and effort by SIGCHI volunteers to organize and manage the reviewing process, and, if the submission is accepted, the publication and presentation process. Thus, anyone who submits to RecSys 2021 implicitly confirms the following statements:
I confirm that this submission is the work of myself and my co-authors.
I confirm that I or my co-authors hold copyright to the content, and have obtained appropriate permissions for any portions of the content that are copyrighted by others.
I confirm that any research reported in this submission involving human subjects has gone through the appropriate approval process at my institution.
I confirm that if this paper is accepted, I or one of my co-authors will present the paper at the conference, either in person or through a conference-designated remote presentation option. Papers that are not presented at the conference by an author may be removed from the proceedings at the discretion of the program chairs.
Important Dates
Abstract submission deadline: April 27th, 2021
Paper submission deadline: May 4th, 2021
Reviews released: June 22, 2021
Clarifications due: June 26, 2021
Author notification: July 6th, 2021
Camera-ready version deadline: July 27th, 2021
Deadlines refer to 23:59 (11:59pm) in the AoE (Anywhere on Earth) time zone.
Julian McAuley, University of California, San Diego, USA
E-mail:
Call for Reproducibility Papers
RecSys also strongly encourages the submission of algorithmic papers that repeat and analyze prior work. We distinguish between:
replicability papers, which repeat prior experiments using the original source code and datasets to show how, why, and when the methods work (or not); and
reproducibility papers, which repeat prior experiments preferably using the original source code in new contexts (e.g., different application domains and datasets, different evaluation methodologies and metrics) to further generalize and validate (or not) previous work.
Submissions regarding replicability or reproducibility papers are welcome in all areas related to recommender systems (see the main track Call for Papers for a list of topics).
In both replicability and reproducibility papers, we expect authors to provide all materials required for repeating the tests performed, including code, data, and clear instructions on how to run the experiments. Submissions from the same authors of the reproduced experiments will not be accepted. Failure to provide all materials will result in desk rejection.
Each accepted paper will be included in the conference proceedings and presented in a plenary session as part of the main conference program. Each accepted paper will also be allocated a presentation slot in a poster session to encourage discussion and follow-up between authors and attendees.
We encourage authors to create a companion website for each paper where details on how the code and data can be reproduced or re-used.
REVIEW CRITERIA
Both replicability and reproducibility papers will be evaluated along the following criteria:
Novelty
What is new about the reproduced experiments?
Was the original work not supported from the theoretical point of view?
Were the original experiments not clear about important points or lacking confirmation for some of the original claims?
Do the reproduced experiments bring more solid conclusions, with new datasets and metrics, with unbiased evaluation setups?
Are there new experiments that allow for a better understanding of the impact of previous results?
Impact
How important is the reproduction of the experiments to the community?
How obvious are the conclusions achieved?
Do the reproduced prior works, if validated, advance a central topic to recommender systems (a topic with a broad applicability or focused on a hot research area)?
Reliability
Is the evaluation methodology in line with the research challenges addressed by the reproduced experiment?
Are the selected baselines representative of the several algorithm types and techniques available?
Is the hyperparameter tuning strategy properly described?
Are algorithms and baselines properly tuned?
Availability
Are the code and datasets used to reproduce the experiments available to the reviewers at the time of review?
Is the shared material released in a permanent repository for easy access by researchers?
Are the reproduced experiments well documented, with all the details required for other researchers to reproduce the experiments, as well?
Are there discrepancies between what is described in the paper and what is available in the shared material?
Is the shared material complete with everything you need to exactly replicate the experiments?
SUBMISSION GUIDELINES
All submissions and reviews will be handled electronically. Papers must be submitted to PCS by 23:59, AoE (Anywhere on Earth) on May 4th, 2021. There will be no extensions to the submission deadline.
Formatting
ACM is changing the archive format of its publications to separate content from presentation in the new Digital Library, enhance accessibility, and improve the flexibility and resiliency of our publications. Following the new ACM publication workflow, all authors should submit manuscripts for review in a single-column format. Paper length is suggested to range between 7 pages (for reproductions of a single algorithm) to 14 pages (for reproductions of multiple algorithms). In any case, the maximum length is 14 pages (excluding references) in the new single-column format. Instructions for Word and LaTeX authors are given below:
Microsoft Word: Write your paper using the Submission Template (Review Submission Format). Follow the embedded instructions to apply the paragraph styles to your various text elements. The text is in single-column format at this stage and no additional formatting is required at this point.
LaTeX: Please use the latest version of the Primary Article Template – LaTeX to create your submission. You must use the “manuscript” option with the \documentclass[manuscript]{acmart} command to generate the output in a single-column format which is required for review. Please see the LaTeX documentation and ACM’s LaTeX best practices guide for further instructions. To ensure 100% compatibility with The ACM Publishing System (TAPS), please restrict the use of packages to the whitelist of approved LaTeX packages.
Authors are strongly encouraged to provide “alt text” (alternative text) for floats (images, tables, etc.) in their content so that readers with disabilities can be given descriptive information for these floats that are important to the work. The descriptive text will be displayed in place of a float if the float cannot be loaded. This benefits the author as well as it broadens the reader base for the author’s work. Moreover, the alt text provides in-depth float descriptions to search engine crawlers, which helps to properly index these floats.
Should you have any questions or issues going through the instructions above, please contact support at for both LaTeX and Microsoft Word inquiries.
Accepted papers will be later submitted to ACM’s new production platform where authors will be able to review PDF and HTML output formats before publication.
Anonymity
Papers in the reproducibility track will undergo single-blind review. It is expected that at the time of submission, code and datasets used to reproduce the experiments will be available under reasonably liberal terms and sufficiently well-documented such that reviewers may consult that documentation as they conduct their reviews.
Originality
Each paper should not be previously published or accepted to any peer-reviewed journal or conference/workshop, nor currently under review elsewhere (including as another paper submission for RecSys 2021). We do not prevent authors from submitting the same paper to institutional or other preprint repositories such as arXiv.org before the reviewing process is complete. Please refer to the ACM Publishing License Agreement and Authorship Policy for further details.
Plagiarism
Plagiarized papers will not be accepted for RecSys 2021. Our committees will be checking the plagiarism level of all submitted papers to ensure content originality using an automated tool. Hence, authors are advised in their own interest to use a similar tool (e.g., iThenticate, Turnitin, Viper, PlagScan, etc.) to check the plagiarism level of their manuscripts before submission. The originality report generated by the tool may also be submitted at the time of paper submission.
Papers violating any of the above guidelines are subject to rejection without review.
SIGCHI Submitter Agreement
RecSys 2021 is a SIGCHI conference and making a submission to a SIGCHI conference is a serious matter. Submissions require time and effort by SIGCHI volunteers to organize and manage the reviewing process, and, if the submission is accepted, the publication and presentation process. Thus, anyone who submits to RecSys 2021 implicitly confirms the following statements:
I confirm that this submission is the work of myself and my co-authors.
I confirm that I or my co-authors hold copyright to the content, and have obtained appropriate permissions for any portions of the content that are copyrighted by others.
I confirm that any research reported in this submission involving human subjects has gone through the appropriate approval process at my institution.
I confirm that if this paper is accepted, I or one of my co-authors will present the paper at the conference, either in person or through a conference-designated remote presentation option. Papers that are not presented at the conference by an author may be removed from the proceedings at the discretion of the program chairs.
Important Dates
Abstract submission deadline: April 27th, 2021
Paper submission deadline: May 4th, 2021
Author notification: July 6th, 2021
Camera-ready version deadline: July 27th, 2021
Deadlines refer to 23:59 (11:59pm) in the AoE (Anywhere on Earth) time zone.
We are pleased to invite you to contribute to the 15th ACM Conference on Recommender Systems (RecSys 2021), the premier venue for research on the foundations and applications of recommendation technologies. The upcoming RecSys conference will be held from September 27th to October 1st, 2021. The conference will be held in Amsterdam, Netherlands, with an inclusive format that accommodates remote attendance. The conference will continue RecSys’ practice of connecting the research and practitioner communities to exchange ideas, frame problems, and share solutions.
We invite proposals for tutorials to be given in conjunction with the conference. The goal of the tutorials is to provide conference attendees, including early-career researchers and researchers crossing-over from related disciplines, with an opportunity to learn about recommender system concepts and techniques. Tutorials also serve as a venue to share presenters’ expertise with the global community of recommender system researchers and practitioners. Tutorials focus on specific topics including, but not limited to:
Introductions to specific recommender systems techniques (e.g., deep learning, feature engineering, tensorflow).
Evaluation of recommender systems (e.g., system-centric and user-centric evaluation, experimentation).
Designing user experiences and interactions (e.g., virtual assistants, chatbots, etc.).
Using different types of data (semantic web, graphs) and media (text, images, video, speech) for building recommendations.
Ethical and legal aspects of recommender systems (e.g., privacy, fairness, accountability, transparency, and control of bias).
Recommender systems facing real-world challenges (e.g., large-scale recommender systems or stream-based recommendation).
Building and deploying recommender systems in specific domains (e.g., music, tourism, education, TV/video, jobs, enterprise, health, fashion).
Recommender systems supporting decision making.
Recommendation for groups, tasks, or situations, including intent-aware recommender systems.
Eliciting and learning user preferences.
Recommender systems that take users’ emotional state, physical state, personality, trust, level of expertise, and/or cognitive readiness into account.
Sensors and recommender systems (including mobile recommender systems and wearables).
Intersections of recommender systems with other domains (e.g., information retrieval, machine learning, human computer interaction, or databases).
Recommender systems in new domains, such as e-government, smart cities and energy.
The length of your proposed tutorial should be commensurate with the presented materials and the projected interest of the RecSys community in the tutorial topic. We expect tutorial slots of either 90 or 180 minutes. We may work with accepted tutorial presenters to adjust the length of the tutorials for the available slots. Realize that you need to be flexible, since we may not be able to accommodate your favorite choice of date and time for the tutorial.
We actively encourage both researchers and industry practitioners to submit tutorial proposals that target different levels of expertise and different interests. We also encourage the submission of hands-on tutorials, for instance through the use of notebooks that combine theoretical concepts with practical exercises.
As a tutorial presenter, you are expected to write a short tutorial summary for the conference proceedings (detailed instructions will be provided), present your tutorial at the conference in person (possibly also streamed and, if you wish, recorded for the ACM RecSys 2021 YouTube channel), and provide a link to your tutorial materials after the tutorial so that it can be posted on the ACM RecSys 2021 website and serve as a resource to the community.
If you submit a tutorial, please realize that you are expected to attend the physical conference and present your tutorial in person. We are closely monitoring the COVID-19 situation. If, at the time of the conference, it is clear that travel is not possible for individual presenters, then we will make arrangements for you to be able to present remotely. However, we hope that the situation will improve and remote tutorial presentation will not be necessary.
Submission Guidelines
All submissions and reviews will be handled electronically. Tutorial proposals must be submitted to PCS by 23:59, AoE (Anywhere on Earth) on 18 25 May 2021 (extended).
The tutorial proposal should be organized as follows:
Tutorial title.
Tutorial length.
Motivation for proposing this tutorial (why it is important for RecSys).
Name, email address, and affiliation of tutorial instructors (each listed instructor must present in person at the conference).
Detailed bulleted outline of the tutorial (this point should take the most space).
Targeted audience (introductory, intermediate, advanced) and prerequisite knowledge or skills.
Teaching experiences and history of prior tutorials by the presenters.
List of relevant publications by the presenters.
The submission should be a .pdf file of about 2 pages in length (single column, no particular formatting required).
Note that it is possible that we issue a second call for late-breaking tutorial proposals, but please do not count on it. We would appreciate it if you would submit your proposal to this call.
Evaluation Criteria
Tutorial proposals will be reviewed according to: ability of the tutorial to contribute to strengthening the foundations of recommender system research, or to broaden the field to look at important new challenges and techniques, experience and skill of the presenters, and the value of any materials released with the tutorial for the community.
Important Dates
Tutorial proposals due: 18 25 May 2021 (extended)
Tutorial proposals notifications: 8 10 June 2021 (postponed)
Camera ready tutorial session abstract: 14 July 2021
Tutorial Chairs
Tat-Seng Chua, National University of Singapore, Singapore
Alan Hanjalic, TU Delft, The Netherlands
E-mail:
Call for Workshop Proposals
We are pleased to invite you to contribute to the 15th ACM Conference on Recommender Systems (RecSys 2021), the premier venue for research on the foundations and applications of recommendation technologies. The upcoming RecSys conference will be held from September 27th to October 1st 2021. The conference will be held in Amsterdam, Netherlands, with an inclusive format that accommodates remote attendance. The conference will continue RecSys’ practice of connecting the research and practitioner communities to exchange ideas, frame problems, and share solutions. RecSys 2021 is pleased to invite proposals for workshops to be held in conjunction with the conference. The goal of the workshops is to provide additional venues for discussing novel ideas as well as recent results of research in progress.
In 2021 our goal is to have a balanced workshop program which comprises workshop formats of different types and a combination of newly emerging, currently evolving, and historically understudied topics. Different full-day and half-day workshop formats are possible, for example:
Workshops with novel interactive formats and a relatively small number of participants. Such workshop formats might for example target at the exploration of a certain topic during the workshop through a moderated discussion or breakout sessions, resulting in a draft paper or report to be completed and published after the workshop. Or they might focus on datasets and benchmarking for a particular problem or domain. Particular priority will be given to these formats which require the active involvement of the participants.
Workshops with the traditional workshop format on specialized topics. Such workshops typically have their own paper submission and review processes. Proposals for continuations of existing workshop series are welcome, however, please include a brief statement on the necessity for the new edition, including a description of the outcomes of previous years and the expected novelty of this edition.
We encourage you to contact us by email at up to three weeks before the deadline with workshop ideas; we will work with prospective workshop organizers to help them design successful proposals. In particular, for workshop proposals with novel interactive formats we are happy to assist you in further developing and implementing your ideas. We actively encourage both researchers and industry practitioners to submit workshop proposals.
Submission Guidelines
All submissions and reviews will be handled electronically. The maximum length is 7 pages (excluding references) in the new single-column format. Workshop proposals must be submitted to PCS by 23:59, AoE (Anywhere on Earth) on March 2nd, 2021.
Contents of the proposal
The workshop proposal should be organized as follows:
Workshop title.
A short description of the workshop including the rationale for the workshop and how and why it fits the audience of RecSys. This description should include also the topic and its relevance to the community as well as format, and details about what type of submission is requested from prospective attendees. Please also add an explanation on how the workshop complements, rather than duplicates, the topics of the main conference.
Name, email address, and affiliation for workshop organizers and a brief description of their experience in organizing such events. Note that organizers are expected to attend the workshop and be actively involved in its organization.
Requested duration (half day or full day), and expected number of participants.
Description of workshop activities. Outline how the workshop will be organized and how the time will be spent. In particular, please sketch how you will engage participants to foster more interactivity and engagement during the workshop.
For workshops involving paper submissions, an initial − and for the most part confirmed − Program Committee (or a clear justification why it is not needed).
For more interactive workshop formats, also outline the process of selecting or inviting the participants.
Description of plans for promoting the workshop and disseminating the results, for instance, by organizing a journal special issue with extended versions of the workshop’s best papers.
History of prior workshops on this topic (e.g., including the number of submissions and attendees), if any.
EVALUATION CRITERIA
Ability of the topic to contribute to the continued development of the field of recommender systems.
Level of complementarity of the topic to the main conference.
Clear plan for attracting submissions, making the workshop itself productive, and disseminating results.
Evidence that this plan will be successful.
Experience of the organizers.
Workshop summary
The organizers of accepted workshops will be invited to write a camera-ready summary of the workshop. Workshop summaries will be later submitted to ACM’s new production platform where authors will be able to review PDF and HTML output formats before publication.
Formatting
ACM’s archival publication format separates content from presentation in the Digital Library to enhance accessibility and improve the flexibility and resiliency of our publications. Following the ACM publication workflow, all authors should submit manuscripts for review in a single-column format. Instructions for Word and LaTeX authors are given below:
Microsoft Word: Write your paper using the Submission Template (Review Submission Format). Follow the embedded instructions to apply the paragraph styles to your various text elements. The text is in single-column format at this stage and no additional formatting is required at this point.
LaTeX: Please use the latest version of the Primary Article Template – LaTeX to create your submission. You must use the “manuscript” option with the \documentclass[manuscript]{acmart} command to generate the output in a single-column format which is required for review. Please see the LaTeX documentation and ACM’s LaTeX best practices guide for further instructions. To ensure 100% compatibility with The ACM Publishing System (TAPS), please restrict the use of packages to the whitelist of approved LaTeX packages.
A document with some frequently asked questions can be found here.
Authors are strongly encouraged to provide “alt text” (alternative text) for floats (images, tables, etc.) in their content so that readers with disabilities can be given descriptive information for these floats that are important to the work. The descriptive text will be displayed in place of a float if the float cannot be loaded. This benefits the author as well as it broadens the reader base for the author’s work. Moreover, the alt text provides in-depth float descriptions to search engine crawlers, which helps to properly index these floats. Additionally, authors should follow the ACM Accessibility Recommendations for Publishing in Color and SIG ACCESS guidelines on describing figures.
Should you have any questions or issues going through the instructions above, please contact support at for both LaTeX and Microsoft Word inquiries. The overview papers of accepted workshops will be later submitted to ACM’s new production platform where authors will be able to review PDF and HTML output formats before publication.
IMPORTANT DATES
Workshop proposal submission deadline: March 2nd, 2021
Workshop proposal notification: March 16th, 2021
Camera-ready workshop summary deadline: July 20th, 2021
We furthermore encourage the organizers to stick to the following suggested deadlines in the schedule for authors:
Call for Papers publication: April 2nd, 2021
Paper submission deadline: July 29th, 2021
Reviewer deadline: August 14th, 2021
Author notification: August 21st, 2021
Camera-ready version deadline: September 4th, 2021
These dates consider in particular the synchronization with the notification of acceptance in the main conference track, and the availability of early registration for the authors of accepted workshop papers.
Deadlines refer to 23:59 (11:59pm) in the AoE (Anywhere on Earth) time zone.
Marijn Koolen, Royal Netherlands Academy of Arts and Sciences
Denis Parra, Pontificia Universidad Católica de Chile
Call for Doctoral Symposium Submissions
We are pleased to invite you to contribute to the 15th ACM Conference on Recommender Systems (RecSys 2021), the premier venue for research on the foundations and applications of recommendation technologies. The upcoming RecSys conference will be held from September 27th to October 1st 2021. The conference will be held in Amsterdam, Netherlands, with an inclusive format that accommodates remote attendance. The conference will continue RecSys’ practice of connecting the research and practitioner communities to exchange ideas, frame problems, and share solutions.
The Doctoral Symposium provides an opportunity for doctoral students to explore and develop their research interests under the guidance of a panel of distinguished researchers from both academia and industry. We invite students who feel that they would benefit from this kind of feedback on their work to apply for this unique opportunity, which will allow them to share their work with their peers as well as with senior researchers in the field. The Doctoral Symposium is particularly suited for candidates who have made some research progress, but who are not so far along that they can no longer make changes in their research plans. Typically, this means that they have defined their topic and have completed some research, but still have at least a year of research remaining before completing a dissertation (in many universities this corresponds to the dissertation proposal stage). The feedback from attendees in previous years has been very positive and the Doctoral Symposium has been considered very useful in providing research guidance.
The symposium has the following objectives:
Provide a supportive setting for feedback on students’ current research and guidance on
future research directions.
Offer each student feedback and fresh perspectives on their work from faculty and students
outside their own institution.
Promote the development of a supportive community of researchers and a spirit of
collaborative research.
Contribute to the conference goals through interaction with other researchers and
conference events.
Student participants will have their extended abstracts published in the conference proceedings.
They will also present a poster of their work at the conference.
SYMPOSIUM FORMAT AND PARTICIPATION EXPECTATIONS
Participants are expected to attend the entire symposium, and are also expected to attend the RecSys 2021 conference. The RecSys conference will be held from September 27th to October 1st 2021, and the symposium will be held on September 26th, 2021. If circumstances prevent physical attendance, remote participation will be possible.
The format of the symposium will be primarily student presentations and Q&A opportunities with senior researchers in the field, supplemented by one or two panel sessions to provide advice.
Student presentations will be structured to provide maximum feedback. In particular:
Presentations will be limited to 15 minutes, followed by 20-25 minutes for feedback and discussion.
Two of the symposium faculty will be assigned to provide “primary” feedback for each presenter; following this primary feedback there will be a period of open feedback from all participants.
Students will be expected to take notes for another participant so that each of you can focus on interacting during the discussion surrounding your presentation.
During the main conference, students will also present their dissertation work and plans in the form of a poster presentation.
Being accepted into the symposium is an honor, and involves a commitment to giving and receiving thoughtful commentary with an eye towards shaping the field and upcoming participants in the research area.
SUBMISSION GUIDELINES
Applications are invited from graduate students pursuing a PhD project who would benefit from detailed workshop discussions of their doctoral research by a panel of established researchers. All submissions and reviews will be handled electronically.
Application
Applications should include the following:
An extended abstract (see below).
A curriculum vitae or resumé.
A one-paragraph statement of expected benefits of participation, including questions regarding your dissertation that you would like to ask your symposium mentors.
A brief letter of recommendation from your doctoral advisor, focused on how your participation in the doctoral symposium will benefit your dissertation research.
Submit these four items in a single PDF file to PCS by 23:59, AoE (Anywhere on Earth) on May 18th 25th, 2021 (extended).
Extended Abstract
The maximum length for extended abstracts is 7 pages (excluding references) in the new single-column format. See below for formatting instructions and selection criteria. Note that the student is the sole author of the abstract. Advisor(s) can be thanked in the acknowledgments.
Please write your extended abstract to the same quality standards as a regular RecSys submission.
Formatting
ACM’s archival publication format separates content from presentation in the Digital Library to enhance accessibility and improve the flexibility and resiliency of our publications. Following the ACM publication workflow, all authors should submit manuscripts for review in a single-column format. Instructions for Word and LaTeX authors are given below:
Microsoft Word: Write your paper using the Submission Template (Review Submission Format). Follow the embedded instructions to apply the paragraph styles to your various text elements. The text is in single-column format at this stage and no additional formatting is required at this point.
LaTeX: Please use the latest version of the Primary Article Template – LaTeX to create your submission. You must use the “manuscript” option with the \documentclass[manuscript]{acmart} command to generate the output in a single-column format which is required for review. Please see the LaTeX documentation and ACM’s LaTeX best practices guide for further instructions. To ensure 100% compatibility with The ACM Publishing System (TAPS), please restrict the use of packages to the whitelist of approved LaTeX packages.
A document with some frequently asked questions can be found here.
Authors are strongly encouraged to provide “alt text” (alternative text) for floats (images, tables, etc.) in their content so that readers with disabilities can be given descriptive information for these floats that are important to the work. The descriptive text will be displayed in place of a float if the float cannot be loaded. This benefits the author as well as it broadens the reader base for the author’s work. Moreover, the alt text provides in-depth float descriptions to search engine crawlers, which helps to properly index these floats. Additionally, authors should follow the ACM Accessibility Recommendations for Publishing in Color and SIG ACCESS guidelines on describing figures.
Should you have any questions or issues going through the instructions above, please contact support at for both LaTeX and Microsoft Word inquiries.
Accepted papers will be later submitted to ACM’s new production platform where authors will be able to review PDF and HTML output formats before publication.
Originality
Each paper should not be previously published or accepted to any peer-reviewed journal or conference/workshop, nor currently under review elsewhere (including as another paper submission for RecSys 2021). If you reuse non-novel text from a prior publication (e.g., the description of an algorithm or dataset), please be sure to cite the prior publication as the source of that text. If you have questions about reuse of text or simultaneous submission, please contact the program chairs at least one week prior to the submission deadline. Please refer to the ACM Publishing License Agreement and Authorship Policy for further details.
Plagiarism
Plagiarized papers will not be accepted for RecSys 2021. Our committees will be checking the plagiarism level of all submitted papers to ensure content originality using an automated tool.
Papers violating any of the above guidelines are subject to rejection without review and cases may be referred to the ACM Publications Ethics and Plagiarism committee for further action where warranted.
Confidentiality
Confidentiality of submissions is maintained during the review process, where only the DS Chairs will have access to the submissions. All rejected submissions will be kept confidential in perpetuity. All submitted materials for accepted submissions will be kept confidential until two weeks prior to the start of the conference. Submissions should contain no information or materials that are proprietary at publication time.
SELECTION CRITERIA
Your extended abstract will be evaluated by the DS Chairs with regard to:
Originality of the work with respect to current concepts and techniques (provide relevant citations).
Importance of the work with respect to fundamental issues in recommender systems (clearly identify the problems you are trying to solve).
Rigor and validity of claims, argumentation, methodology, results, and interpretations.
Clarity and persuasiveness of expression.
To provide maximum feedback to each student, participation in the doctoral symposium is limited. Selection is based on two broad criteria:
Value of the symposium to the student:
The degree to which the applicant is positioned to benefit from participation, including the student’s position in the doctoral process (the greatest benefit is for students with a developed research idea but much of the work yet undone).
The degree to which the student may otherwise lack access to a diverse set of feedback and input on their research plans (e.g., availability of local experts and advisors).
Value of the student’s participation to other students:
The quality of the extended abstract (as identified above), both as a model of excellent research and as an indication of the student’s potential in the field.
Diversity of participation, including diversity by institution, country, research topic and approach, and demographics. In general, we might limit participation to one or two students per institution, depending on the number of applicants.
Evidence that the student will be an effective and active participant, providing feedback to others and helping to build a research network (such as, e.g., prior experience in meetings, workshops, etc., or any feedback the advisor may provide on this).
APPLICATION CHECKLIST
Well in advance of the deadline:
Write an extended abstract according to the formatting instructions above. The maximum length for extended abstracts is 7 pages (excluding references) in the new single-column format. Note that the student is the sole author of the abstract. Advisor(s) can be thanked in the acknowledgments.
Write a curriculum vitae.
Write a one-paragraph statement of expected benefits of participation.
Obtain a letter of recommendation from your advisor.
By the deadline (May 25th, 2021, 23:59 AoE):
Submit items 1-4 above in a single PDF file to PCS.
SUPPORT
Accepted students will receive free registration to RecSys 2021. Students receiving support will be requested to be part of the student volunteer cohort. Opportunities for travel support will be announced when available.
IMPORTANT DATES
Doctoral symposium submission deadline: May 18th 25th, 2021 (extended)
Doctoral symposium submission notification: June 22th, 2021
Deadline for the camera-ready version of the extended abstract: July 20th, 2021
Deadlines refer to 23:59 (11:59pm) in the AoE (Anywhere on Earth) time zone.
DOCTORAL SYMPOSIUM CHAIRS
Christine Bauer, Utrecht University, The Netherlands
Pablo Castells, Universidad Autónoma de Madrid, Spain
E-mail:
Call for Demos
Demos show implementations of novel, interesting, and important recommender systems’ concepts or applications. Allowing potential users to see and use a demo of a research work makes them excited about it – it makes the work real and tangible. Demos also allow researchers from academia and developers from small start-ups to large industries to present new recommender ideas and get valuable feedback from the recommender systems community.
We welcome new demonstrations of recommendation technologies coming from diverse communities ranging from psychology to mathematics. In particular, we care as much about the human and economic impact of these systems as we care about their underlying algorithms.
The conference will continue RecSys’ practice of connecting the research and practitioner communities to exchange ideas, frame problems, and share solutions. RecSys has an excellent history of being well-attended by industry representatives — past conferences have had attendees and presenters from Netflix, Amazon, Booking, Google, Facebook, LinkedIn, Criteo, Pandora, Spotify, etc. The blend of industry and academic attention provides an excellent environment to demonstrate and discuss latest inventions or ideas.
We invite demonstrations relevant to all aspects of recommender systems, including, but not limited to:
Interaction techniques (preference elicitation interfaces, recommendation presentation, explanations, and more)
Tools for development and analysis of recommender systems (design tools, evaluation systems, analytics tools)
Innovative applications of recommender systems
Recommender user experiments
Recommender platforms
Accepted demonstrations will be published in the conference proceedings as an extended abstract. Authors will also be required to present a poster of their work at the conference.
In addition, this year’s conference will introduce a novel “Best Demo Award”, recognized to a demonstration providing outstanding contributions to the community.
As this year’s call for papers states, research papers that include a demo component might have a slot in the Demos track. Authors of research papers can use the submission form of the main track to express their interest to present the demo component of their work; in case of acceptance, they will be contacted by the Demos chairs, with no need to start a new demo submission. Authors of rejected papers that expressed their interest to present their demo component are invited to start a new submission process as a demo, following this call for demos.
REVIEWING PROCESS
Reviewers will evaluate demos based on their significance, originality, and contribution to the field. In view of the RecSys conference goal of advancing the field, reviewers are also asked to consider the replicability of reported research. Sharing of data sets and code is encouraged (as indicated in the “Contents” section) and will be part of the review process. Given the mixed conference format, the audio and video quality of the accompanying screencast will be evaluated.
Demos that are out of scope, incomplete, or lack sufficient evidence to support the basic claims, may be rejected without full review.
SUBMISSION GUIDELINES
All submissions and reviews will be handled electronically. Demonstrations must be submitted to PCS by 23:59, AoE (Anywhere on Earth) on July 13th, 2021.
Contents
The description of the demo must include the following:
An overview of the algorithm or system that is the core of the demo, including citations to any publications that support the work.
A discussion of the purpose and the novelty of the demo.
A description of the required setup. If the system will feature an installable component (e.g., mobile app) or website for users to use throughout or after the conference, please mention this.
A link to a narrated screen capture of your system in action, ideally a video. The maximum duration of screen capture is 10 minutes. (This section will be removed for the camera-ready version of accepted contributions but might be included in the virtual platform used to host the online part of the conference.)
We also highly encourage any external material related to the demo (e.g., shared code on GitHub). Please, provide a link to the shared code in the extended abstract accompanying the demo.
Formatting
ACM is changing the archive format of its publications to separate content from presentation in the new Digital Library, enhance accessibility, and improve the flexibility and resiliency of our publications. Following the ACM publication workflow, all authors should submit manuscripts for review in a single-column format. The maximum length for extended abstracts is 4 pages (excluding references) in the new single-column format. Instructions for Word and LaTeX authors are given below:
Microsoft Word: Write your paper using the Submission Template (Review Submission Format). Follow the embedded instructions to apply the paragraph styles to your various text elements. The text is in single-column format at this stage and no additional formatting is required at this point.
LaTeX: Please use the latest version of the Primary Article Template – LaTeX to create your submission. You must use the “manuscript” option with the \documentclass[manuscript]{acmart} command to generate the output in a single-column format which is required for review. Please see the LaTeX documentation and ACM’s LaTeX best practices guide for further instructions. To ensure 100% compatibility with The ACM Publishing System (TAPS), please restrict the use of packages to the whitelist of approved LaTeX packages.
A document with some frequently asked questions can be found here.
Authors are strongly encouraged to provide “alt text” (alternative text) for floats (images, tables, etc.) in their content so that readers with disabilities can be given descriptive information for these floats that are important to the work. The descriptive text will be displayed in place of a float if the float cannot be loaded. This benefits the author as well as it broadens the reader base for the author’s work. Moreover, the alt text provides in-depth float descriptions to search engine crawlers, which helps to properly index these floats. Additionally, authors should follow the ACM Accessibility Recommendations for Publishing in Color and SIG ACCESS guidelines on describing figures.
Should you have any questions or issues going through the instructions above, please contact support at for both LaTeX and Microsoft Word inquiries.
Accepted demonstrations will be later submitted to ACM’s new production platform where authors will be able to review PDF and HTML output formats before publication. Additionally, we might request audiovisual material, such as a recording of the demo walkthrough two weeks before the conference start date, in order to allow for preparation of the conference’s online part.
Anonymity
All submissions will be single-blind peer reviewed. This means that submissions should include information identifying the authors and their organization.
Ethical Review for Human-Subjects Research
ACM RecSys expects all authors to comply with ethical and regulatory guidelines associated with human subjects research, including research involving human participants and research using personally identifiable data. Demos reporting on such human subjects research must include a statement identifying any regulatory review the research is subject to (and identifying the form of approval provided), or explaining the lack of required review. Reviewers will be asked to consider whether the research was conducted in compliance with applicable ethical and regulatory guidelines.
Originality
Demos must not be under review in any other conference at the time of submission and must contain novel contributions. Plagiarized demos will not be accepted for RecSys 2021. If you have questions about reuse of a previously presented demo or simultaneous submission, please contact the demo chairs at least one week prior to the submission deadline. Please refer to the ACM Publishing License Agreement and Authorship Policy for further details.
Patenting
Please take note that the official publication date is the date the proceedings are made available in the ACM Digital Library. This date may be up to two weeks prior to the first day of the conference. The official publication date affects the deadline for any patent filings related to published work.
SIGCHI Submitter Agreement
RecSys 2021 is a SIGCHI conference and making a submission to a SIGCHI conference is a serious matter. Submissions require time and effort by SIGCHI volunteers to organize and manage the reviewing process, and, if the submission is accepted, the publication and presentation process. Thus, anyone who submits to RecSys 2021 implicitly confirms the following statements:
I confirm that this submission is the work of myself and my co-authors.
I confirm that I or my co-authors hold copyright to the content, and have obtained appropriate permissions for any portions of the content that are copyrighted by others.
I confirm that any research reported in this submission involving human subjects has gone through the appropriate approval process at my institution.
I confirm that if this paper is accepted, I or one of my co-authors will present the paper at the conference, either in person or through a conference-designated remote presentation option. Papers that are not presented at the conference by an author may be removed from the proceedings at the discretion of the program chairs.
We are pleased to invite you to contribute to the 15th ACM Conference on Recommender Systems (RecSys 2021), the premier venue for research on the foundations and applications of recommendation technologies. The upcoming RecSys conference will be held from September 27 to October 1, 2021. The conference will be held in Amsterdam, Netherlands, with an inclusive format that accommodates remote attendance. The conference will continue RecSys’ practice of connecting the research and practitioner communities to exchange ideas, frame problems, and share solutions.
The Late-Breaking Results (LBR) track of RecSys offers an opportunity for presenting new, interesting, preliminary results and speculative or innovative work in progress. The track seeks novel contributions that should be published immediately, because they will influence the work of others. The topics listed in the main track call for papers serve as a reference, but we also encourage submissions with clear relevance to recommender systems that extend this list.
Accepted contributions for this track will be presented as posters, where the informal setting encourages presenters and participants to engage in lively discussions about the presented work. All submissions should convey a scientific result or work in progress that is not yet ready to be published as a research paper at a refereed conference, but the preliminary results are already interesting.
Accepted submissions will be published as extended abstracts in the ACM RecSys 2021 conference proceedings.
Submission Guidelines
Submissions should report on substantial contributions of lasting value. The maximum length is 7 pages (excluding references) in the new single-column format.
All submissions and reviews will be handled electronically. Submissions must be submitted to PCS by 23:59, AoE (Anywhere on Earth) on July 13, 2021.
In addition to these guidelines, the guidelines in the main-track call for papers apply for Formatting, Anonymity, Ethical Review for Human-Subjects Research, Originality, Plagiarism and Patenting. Please make sure that you have read and understood those.
SIGCHI Submitter Agreement
RecSys 2021 is a SIGCHI conference and making a submission to a SIGCHI conference is a serious matter. Submissions require time and effort by SIGCHI volunteers to organize and manage the reviewing process, and, if the submission is accepted, the publication and presentation process. Thus, anyone who submits to RecSys 2021 implicitly confirms the following statements:
I confirm that this submission is the work of myself and my co-authors.
I confirm that I or my co-authors hold copyright to the content, and have obtained appropriate permissions for any portions of the content that are copyrighted by others.
I confirm that any research reported in this submission involving human subjects has gone through the appropriate approval process at my institution.
I confirm that if this submission is accepted, I or one of my co-authors will present it at the conference, either in person or through a conference-designated remote presentation option. Papers that are not presented at the conference by an author may be removed from the proceedings at the discretion of the program chairs.
Important Dates
LBR abstract deadline: 10 July 2021
LBR submission deadline: 13 July 2021
LBR notifications: 30 July 2021
LBR paper camera ready: 10 August 2021
Deadlines refer to 23:59 (11:59pm) in the AoE (Anywhere on Earth) time zone.
Late-Breaking Results Chairs
Alexandros Karatzoglou, Google, UK
Katrien Verbert, KU Leuven, Belgium
E-mail:
Call for Industry Talk Proposals
The ACM Conference on Recommender Systems (RecSys 2021) is the premier venue for research and applications of recommendation technologies. The upcoming RecSys conference will be held from September 27th to October 1st 2021. The conference will be held in Amsterdam, Netherlands, with an inclusive format that accommodates remote attendance. The conference will continue RecSys’ practice of connecting communities of researchers and practitioners from academia and industry in order to exchange ideas, discuss problems, and share solutions.
Industry practitioners are invited to submit proposals to the RecSys industry track for a conference presentation. The industry track is focused on challenges and practical solutions to significant real-world issues faced by industry practitioners. We encourage submissions that describe substantial real-world challenges and novel deployed systems that power recommendations in commercial settings. This includes design and interaction aspects of recommender systems. We also recognize that diverse speaker backgrounds and topics facilitate richer discussions at the conference, therefore we especially encourage colleagues from backgrounds that are under-represented in the conference series to submit talk proposals.
All submissions will be reviewed by the Industry chairs. Factors taken into account during the selection process include relevance to real-world challenges, novelty, and contribution to the community. Shared data sets and code are encouraged, as are insights into quantitative and/or qualitative evaluation results. Real-world impact and ethical considerations of the systems described will also be taken into account. Note that proposals consisting of sales pitches for products will not be considered.
Examples of talk topics include, but are not limited to:
Lessons learned from real-world deployment of recommender systems including case studies, retrospectives, and user studies.
Societal impact, fairness and bias of recommender systems in the real world.
Holistic overviews or component deep dives of recommender system pipelines including ETL, candidate generation, research and production training, feature stores and inference.
Novel recommender system applications.
Novel techniques that solve significant issues in production deployment.
Online and offline metrics used to evaluate recommender systems and studies of their interaction in production settings.
Design and interaction aspects of recommender systems.
Other challenges faced by practitioners that are under-studied in the research community and their practical solutions.
Authors of the selected proposals will give an oral presentation in the Industry Track and be invited to present a poster at the conference poster sessions. Extended abstracts will also be published in the conference proceedings.
SUBMISSION GUIDELINES
All submissions and reviews will be handled electronically. Papers must be submitted to PCS by 23:59, AoE (Anywhere on Earth) on June 1st15th, 2021 (extended).
In order to allow for preparation of the conference’s online par, we might request audiovisual material, such as a recording of the talk, two weeks before the conference start date.
Formatting
ACM’s archival publication format separates content from presentation in the Digital Library to enhance accessibility and improve the flexibility and resiliency of our publications. Following the ACM publication workflow, all authors should submit manuscripts for review in a single-column format. The maximum length for extended abstracts is 4 pages (excluding references) in the new single-column format. Instructions for Word and LaTeX authors are given below:
Microsoft Word: Write your paper using the Submission Template (Review Submission Format). Follow the embedded instructions to apply the paragraph styles to your various text elements. The text is in single-column format at this stage and no additional formatting is required at this point.
LaTeX: Please use the latest version of the Primary Article Template – LaTeX to create your submission. You must use the “manuscript” option with the \documentclass[manuscript]{acmart} command to generate the output in a single-column format which is required for review. Please see the LaTeX documentation and ACM’s LaTeX best practices guide for further instructions. To ensure 100% compatibility with The ACM Publishing System (TAPS), please restrict the use of packages to the whitelist of approved LaTeX packages.
A document with some frequently asked questions can be found here.
Authors are strongly encouraged to provide “alt text” (alternative text) for floats (images, tables, etc.) in their content so that readers with disabilities can be given descriptive information for these floats that are important to the work. The descriptive text will be displayed in place of a float if the float cannot be loaded. This benefits the author as well as it broadens the reader base for the author’s work. Moreover, the alt text provides in-depth float descriptions to search engine crawlers, which helps to properly index these floats. Additionally, authors should follow the ACM Accessibility Recommendations for Publishing in Color and SIG ACCESS guidelines on describing figures.
Should you have any questions or issues going through the instructions above, please contact support at for both LaTeX and Microsoft Word inquiries.
Accepted proposals will be later submitted to ACM’s new production platform where authors will be able to review PDF and HTML output formats before publication.
Contents
Industry talk proposals must include the following:
Title and abstract of the proposal presentation
Short CV of the presenter(s) (up to 300 words)
Anonymity
All submissions will be single-blind peer reviewed. This means that submissions should include information identifying the authors and their organization.
IMPORTANT DATES
Proposal submission deadline: June 1st15th, 2021 (extended)
Author notification: June 29thJuly 6th, 2021 (extended)
