Skip to content

Call for Full and Short Papers

UMAP 2024 will adopt registration and presentation policies that must be followed by the authors of each accepted contribution. We invite prospective authors to carefully check them in the call before submitting. Any inquiries can be directed to umap2024-chair@um.org.

The 32nd International Conference on User Modeling, Adaptation, and Personalization (ACM UMAP 2024) is the premier international conference for researchers and practitioners working on systems that adapt to individual users or groups of users, and that collect, represent, and model user information. ACM UMAP 2024 is sponsored by ACM SIGCHI and SIGWEB. User Modeling Inc., as the core Steering Committee, oversees the conference organization. ACM UMAP operates under the ACM Conference Code of Conduct. The main conference proceedings, published by ACM, will be part of the ACM Digital Library.

The theme of ACM UMAP 2024 is “Collaboration and Cooperation for the Greater Good“. Specifically, we welcome submissions that highlight the impact that working together and synergy (such as between academia, industry, influential policy making bodies, committees and communities) can have on solving the world’s biggest problems; the focus is on investigations that capture how user modeling, personalization, and adaptation of (intelligent) systems, also with the use of large language models and generative AI, may influence user behavior, trustful processes and whether new models are required, for building sustainable and inclusive services and solutions that can address critical challenges of our world.

While we encourage submissions related to this theme, the scope of the conference is not limited to the theme only. As always, contributions from academia, industry, and other organizations discussing open challenges or novel research approaches are expected to be supported by rigorous evidence appropriate to claims (e.g., user study, system evaluation, computational analysis).

Important Dates

  • Paper Abstract Submission:

January 22, 2024 (mandatory)

  • Paper Submission:

January 29, 2024

  • Notification:

March 28, 2024

  • Camera-ready Submission (TAPS system):

May 9, 2024

  • Conference:

July 1 – 4, 2024

Note: the submissions deadlines are at 11:59 pm AoE (Anywhere on Earth) time.

Conference Tracks

Below you will find a detailed description of the focus of each conference track, as well as possible topics of interest associated with each track.

Personalized Recommender Systems

Cataldo Musto

University of Bari “Aldo Moro”, Italy

Université Libre de Bruxelles, Belgium

University of Innsbruck, Austria

Personalized, computer-generated recommendations have become a pervasive feature of today’s online world. From the traditional book and movie recommendations to suggestions of what we should eat and wear or where we should travel, recommender systems are seamlessly embedded in our daily lives. The underlying recommender systems are designed to help users and providers in a number of ways. From a user’s viewpoint, these systems assist humans by identifying relevant items or options (e.g., products, services, news articles, connections) within large collections. From a provider’s perspective, recommender systems have shown to be powerful tools to help users sift through massive information and steer consumer behavior. Regardless of who are the main stakeholders, the design of recommender systems requires careful consideration of various aspects, including the choice of the user modeling approach, the recommendation algorithm itself, and the user interface.

This track aims to provide a forum for researchers and practitioners to discuss open challenges, latest solutions, and novel research approaches in the field of recommender systems. To mature research works addressing any of the aforementioned technical aspects pertaining to recommendations, we also particularly welcome research contributions that address questions related to user perception and the business value of recommender systems.

 

Topics include (but are not limited to):

  • User modeling and preference elicitation
  • Recommendation algorithms including aspects of sustainability, scalability, and performance
  • Context-aware recommender systems (including temporal, social, and geographical)
  • Psychological aspects of recommendation (e.g., psychologically-informed user- and item-modeling and recommendation perception)
  • Business value of recommendation systems and multi-stakeholder environments
  • Responsible recommendation, including algorithmic bias and fairness, filter bubbles, ethics, and privacy
  • Evaluation of personalized recommender systems
  • Explanations, transparency, and trust for recommender systems
  • Conversational and sequence-aware Recommender Systems
  • Recommender Systems exploiting Large Language Models
  • Case studies of real-world implementations
  • Recommendation in non-traditional domains (e.g., education, health, e-governance, tourism, fashion, energy)
  • Recommender systems for people with diverse abilities (e.g., autism, dementia, hearing impairment, etc.)
  • Group modeling in recommender systems (aggregation techniques and beyond, e.g., modeling of group dynamics)
  • Reciprocal recommender systems (e.g., people-to-people)

Knowledge Graphs, Semantics, Social and Adaptive Web

KTS – GESIS Leibniz Institute for the Social Science, Germany

Graz University of Technology, Austria

University of Bari “Aldo Moro”, Italy

The use of graphs recently emerged as a natural and straightforward fashion to effectively model a broad range of phenomena and scenarios, ranging from the relationships in a social network to the elements encoded in a knowledge base, without forgetting their applications related to bioinformatics, web page searching, transportation, and navigation. 

Research in the area of graphs typically includes: (i) schema design to represent data which will be modeled in the form of a graph; (ii) adding semantics to properties to the schema types and edges to make data meaningful and transform it into information (iii) reasoning over a graph to produce new information hidden behind the data; (iv) exploiting the information encoded in the graph for specific applications and use cases. All these aspects have triggered several heterogeneous research lines, that in turn significantly impacted user modeling, adaptation, and personalization.

As an example, the recent rise of knowledge graphs such as DBpedia and Wikidata has fueled the research in the area of adaptive web and personalized applications (e.g., recommender systems) by providing new and meaningful data points to model and represent all the actors (items, users, etc.) involved in the personalization process.

Similarly, graph-based information available in the so-called social web has provided a lot of new ideas to better model the users based on the information they spread on social networks and social media, as well as on the people they have relationships with. Moreover, by modeling the information spread on social media as a graph, it is possible to analyze very complex phenomena (e.g., diffusion of harmful content) with new and effective methods.

 

The use of languages and formalisms originally developed for the Semantic Web (e.g., ontologies) can further push all these methods by allowing reasoning and inference over the graphs. Additionally, incorporating neurosymbolic approaches into recommender systems, which combine symbolic reasoning with neural network-based techniques, holds great promise for enhancing the effectiveness of personalization. Finally, the use of graphs is particularly relevant for personalization since recent techniques for learning graph-based representations, ranging from GNNs to graph embedding techniques, obtained competitive performances in a broad set of scenarios and tasks, including state-of-the-art recommendation algorithms.

 

Accordingly, this track provides a forum for researchers to discuss open research problems, mature solutions, the latest challenges, novel applications, and innovative research approaches investigating the use of knowledge graphs for the social, semantic, and adaptive web. We invite original submissions addressing all aspects of personalization, user model building, and personal experience in online social systems.

 

Topics include (but are not limited to):

  • Graph-based Representations for UMAP
    • Exploiting Graphs for Adaptive Web and Personalized Applications
    • New Algorithms for Graphs (GNNs, graph embedding, etc.) applied to UMAP
    • Evaluation of Graph-based Algorithms and Representations
  • Social Web and Social Graphs
    • User Modeling based on Social Web
    • Web content personalization and search
    • Mining Social Networks for User Modeling and Personalization
    • Modeling individuals, groups, and communities
    • Exploiting Social Web for Quantified Self
    • Social Recommender Systems and Social Personalization
    • Crowdsourcing and Collective Intelligence
    • Privacy and Security Issues in Personalization based on Social Web
    • Ethical issues involved in studying the Social Web
  • Knowledge Graphs (KGs)
    • Recommendation and Personalization Algorithms based on KGs
    • New KGs for User Modeling and Personalization
    • Semantic Web and Linked Data for User Modeling and Personalization
    • Neurosymbolic approaches for User Modeling and Personalization
  • Knowledge Graphs Applications from UMAP perspective
    • Search, query, integration and analysis through Knowledge Graphs
    • Information visualization and exploratory analysis methods through Knowledge Graphs
    • Neural symbolic reasoning for social and adaptive web
    • Use of Social and Knowledge Graphs for Explanation Purposes
    • Use of Social and Knowledge Graphs to Prevent Spread of Harmful Contentù
    • Use of Social and Knowledge Graphs to Prevent Eco-chambers and Filter Bubbles
    • Use of Social and Knowledge Graphs to Increase Fairness and Transparency

Intelligent User Interfaces

University of Canterbury, New Zealand

Charles University, Czechia

California State Polytechnic University, USA

User modeling allows systems to provide personalized support to humans, unlocking a potential to accomplish a wider range of tasks and/or make their existing tasks more efficient and/or convenient. While such systems are envisioned to seamlessly complement human abilities, research shows that humans do not always make the best possible decisions when working together with computer systems. Intelligent user interfaces aim to make the interaction between computer systems and humans smarter, more usable, more efficient, and more effective.

Typically, papers in this track explore the design, implementation, and evaluation of personalized/intelligent user-facing systems, interfaces, and interaction mechanisms. By designing and deploying improved forms of support for interactive collaboration between human decision makers and personalized systems, intelligent user interfaces enable decision making processes that better leverage the strengths of both collaborators. Beyond user modeling and personalization, papers in this track are encouraged to leverage solutions from human-computer interaction, data mining, natural language processing, information visualization, and/or knowledge representation and reasoning.

Topics include (but are not limited to):

  • User models for adapting user interfaces
  • Adaptive systems with natural interaction (e.g., natural language, speech, gestures)
  • Multimodal interfaces for adaptive systems (e.g., combining multiple modalities, such as speech, gestures, eye gaze, face, physiological info)
  • Intelligent user interfaces based on sensor data (e.g., UIs for cars, fridges, and IoT)
  • Intelligent wearable and mobile interfaces
  • Affective and aesthetic interfaces
  • User interfaces for supporting human decision-making (e.g., decision strategies)
  • AI-driven interfaces (e.g., conversational, games)
  • Interfaces for personalized systems (e.g., recommendation systems, personalized search systems, human-centered AI systems)
  • Explanations (e.g., explainable interfaces, explanations for personalized systems)
  • Personalized collaborative/multi-user interfaces (e.g. group recommenders, adaptive teamwork systems, user modeling for social networks)
  • Adaptive / intelligent information visualization
  • Biases in user interfaces (e.g., cognitive biases, biases due to the interface design)
  • Evaluation of intelligent user interfaces (e.g., user-centric studies of interactions with intelligent user interfaces)
  • Application-specific intelligent user interfaces (e.g., news, music)
  • Scalability of intelligent user interfaces to access huge datasets
  • Reproducibility (including benchmarks, datasets, and challenges)

Personalizing Learning Experiences through User Modeling

University of Portsmouth, UK

Monash University, Australia

University at Albany-SUNY, USA

Technology has become an integral aspect of the everyday practices of learning. Navigating the streams of information, acquiring new skills and competences, and developing knowledge ‘on the go’ in formal education, personal study, workplaces, personal development, and health, are increasingly valued and necessary. In fact, technological innovations bring new opportunities to support learners’ needs, to orchestrate and enable personalized learning solutions, feedback processes, learner-learner collaboration, social learning, and learner-algorithm interaction, with and without the involvement of the teacher. This opens up opportunities for innovation by modeling the cognitive, metacognitive, motivational, affective, social, and psychomotor aspects of learning that can improve the effectiveness of personalized learning experiences for learning progress and learner/teacher satisfaction.

The impact of the UMAP community on personalizing learner experiences ranges from more formal educational settings to workplace training, apprentice preparation, and continuous personal development. The experiences can happen in traditional domains such as mathematics, science, language, etc., but also extend to less traditional areas such as medicine, industry, sports, active aging, arts, and more. The datafication of these diverse learning experiences offers the UMAP community an opportunity to personalize learning in these, formerly less represented, areas by defining and developing novel user models.

 

As personalized learning is interdisciplinary, there are thematic threads related to personalized learning that connect researchers and practitioners from sister communities, which we hope can join the discussion in the UMAP community. For instance, the focus of Educational Data Mining (EDM) on data and feature engineering, as well as algorithmic development, can provide input to learner models. Moreover, long-standing Artificial Intelligence in Education (AIED) work on augmenting learning with artificial intelligence can deliver personalized interventions to learners. In the same vein, Learning Analytics (LAK) research that ties indicators of learning with feedback processes can further inform learner modeling and adaptation of the learning experience.

 

This track invites researchers, developers, and practitioners from various disciplines to present their innovative solutions for modeling the learning experience, share outcomes, and discuss their challenges for effectively providing personalized support to learners in any kind of domain (school, workplace, industry, sports, health, etc.). The track encourages submissions focused on systems (within or without learning environments), including but not limited to intelligent tutoring systems, personal learning environments, sensing devices and ambient intelligent features, MOOCs, serious games, escape rooms, agent-based learning environments, virtual pedagogical agents and chatbots, and personalized immersive spaces, among others, that adapt to individual learners or to groups of learners, and that collect, represent and model learning information, interaction, and feedback processes to offer rewarding personalized learning experiences.

 

As the main theme of ACM UMAP 2024 is “Collaboration and Cooperation for the Greater Good”, we would particularly encourage submissions focusing on modeling collaborative and group learning experiences and the impact of learner collaborations on their cognitive, metacognitive, and behavioral states, among other aspects.

 

Topics framing this track include (but are not limited to):

  • Domain, learner, teacher and context modeling
  • Modeling cognitive, metacognitive, motivational, affective, social, and psychomotor aspects of learning
  • Diagnosis of learner needs and calibration of support and feedback
  • Adaptive and personalized support for learning
  • Open Learner Models (OLMs)
  • Open science issues in user modeling
  • User modeling and adaptation
  • Ethical issues in detecting and modeling learner information from technological devices
  • Algorithmic fairness in user modeling for learning
  • Learner-Artificial Intelligence interaction and collaboration
  • Modeling and enabling feedback processes
  • Educational data mining and learning analytics (including deep learning and the management of large, open, and public datasets) to develop user models
  • Modeling collaborative and group learning experiences (including adaptive technologies to support orchestrated classroom learning)
  • Personalized teacher awareness and support tools
  • User control for personalized learning and learner interfaces
  • Wearable technologies and augmented reality to personalize the learning experience
  • Semantic web and ontologies to represent learning
  • Interoperability, portability, and scalability issues
  • Case studies in real-world educational settings, including workplace training applications, sports training, promoting healthy habits and any kind of learning in the wild
  • Recommendations for better learning experience
  • Large language models and generative AI in personalized learning

Fairness, Transparency, Accountability, and Privacy

Polytechnic University of Bari, Italy

Kempelen Institute of Intelligent Technologies, Slovakia

University of Klagenfurt, Austria

Researchers and developers have a social responsibility to care about the impact of their technologies on individual people (users, providers, and other stakeholders) and on society. This involves building, maintaining, evaluating, and studying adaptive systems that are fair, ethical, beneficial to society, and in line with universal human rights. The importance of these topics is highlighted by their presence in ethical guidelines such as the ACM Code of Ethics, policy guidelines such as UNESCO’s Recommendation on the Ethics of Artificial Intelligence, as well as their influence on law and regulation such as the EU’s GDPR and the proposed AI Act.

Following these developments, the track on “Fairness, Transparency, Accountability, and Privacy” seeks contributions dealing with ethical and social matters of adaptive and recommendation systems, such as fairness and privacy, as well as works addressing compliance with policies and regulations, such as requirements for transparency, accountability, and protection of sensitive data. The research trends in Generative AI, e.g. in Large Language Models (LLM), frequently overlook aspects related to Fairness and Trust. The track seeks studies that delve into the transparency, trustworthiness, fairness, and privacy of these systems, and those aimed at developing methods for LLMs to selectively forget certain information to respect the user/stakeholders needs.

Topics of interest include (but are not limited to):

 

Fairness and Diversity: making sure applications are fair and broadly representative

  • Bias and discrimination in user modeling and recommendation
  • User, providers, and other stakeholders’ perceptions and expectations of fairness
  • Algorithmic methods for measuring and increasing fairness
  • UMAP applications for under-served groups
  • Enhancing/embracing diversity and cultural differences in user modeling and recommendation
  • Ethical considerations for user modeling and recommendation including ‘filter bubble’ or ‘balkanization’ effects
  • Studies on Fairness and Diversity of User Modeling and Recommendation models exploiting Generative AI (e.g., Large Language Models, personalized image generation)

 

Transparency: exposing a system’s workings for accountability, trust, and decision support

  • User perceptions or expectations of transparency in user modeling and personalization
  • Algorithmic support for transparency
  • Explanations, visualizations, and other interface innovations for transparency
  • Exposing model operation and effects, decision-making, and data storage for scrutiny and accountability
  • Explainable and scrutable user modeling and recommendation
  • (User-centric) evaluations of transparency or explanation mechanisms
  • Measuring transparency
  • Analysis of transparency and proposal of transparent models of User Modeling and Recommendation approaches based on Generative AI (e.g., Large Language Models, personalized image generation)

 

Privacy: protecting users’ information

  • Analysis of privacy implications of user modeling
  • Data minimization for user modeling and personalization
  • Compliance with data protection law in user models and personalized systems
  • Algorithmic, architectural, and interactive solutions to privacy, including personalized solutions
  • User perception, expectation, and behavior with regards to privacy in UMAP applications
  • Measuring, predicting, modeling, and personalization for privacy
  • Modeling of data protection and privacy requirements, including the economics of privacy and personal data
  • Contextual integrity for user modeling
  • Mechanisms to give users control

 

Accountability: holding relevant stakeholders to account for violations of applicable social norms, ethical guidelines, and regulations

  • Reporting tools or algorithmic advances to ensure legal compliance of user modeling and personalization systems
  • Actionable recourse for users to understand and correct system errors
  • Auditing for violations of fairness, safety, public benefit, or other concerns
  • Accountability measures for other social dynamics such as bias

 

Together, these properties are sustained through models and methods realized through combinations of algorithms and nontechnical approaches that tackle tradeoffs between the above properties and other elements of user experience (such as ease of use, efficiency, and confidence). These topics are construed broadly, and work on any aspect of social responsibility, regulatory compliance, and ethics of user modeling techniques and personalized systems including recommender systems is invited to this track.

Personalization for Persuasive and Behavior Change Systems

University of Turin, Italy

University of Amsterdam, Netherlands

University of Saskatchewan, Canada

To address various societal problems, changing human behavior is crucial. Persuasive and Behaviour change systems are intentionally designed to support people to achieve behavior change objectives. Research in this area has advanced over the years attracting interest from both practitioners and researchers due to the increasing realization of the important role interactive technologies can play in assisting and motivating people to achieve their various goals and objectives.

Persuasive and behavior change systems have applications in various domains including health and wellness, safety and security, environmental sustainability, education, and politics. For their personalization, persuasive and behavior change systems adapt and tailor the presented content or the decision context to increase their relevance, motivational appeal, or to enhance the user experience. The overall aim is to empower or assist people to achieve their goals, by exploiting user models and adapting systems. However, the persuasive use of personalizations on today’s large platforms or digital technologies is causing increasing concerns about behavior engineering that may harm users’ digital wellbeing, privacy  or autonomy. Personalized persuasive technology can be used to change user behaviour for unethical and exploitative purposes, for example, to achieve higher monetization in game design. Despite the recent advances, research in this area, where technology and theory should meet, is generally still in its infancy. 

We invite original submissions addressing the broad areas of personalization and tailoring, including but not limited to personalization models, user models, and personal experience designing personalized persuasive and behavior change systems, computational personalization, design, and evaluation methods, and personalized and adaptive behavior change technologies.

 

Topics include (but are not limited to):

  • Frameworks and models for developing personalized persuasive technology
  • Methods and Metrics for evaluating the effectiveness of personalized persuasive technology
  • Long-term evaluation and evidence of long-term effects of personalized persuasive technology
  • Methods for large-scale computational personalization of persuasive systems
  • Systematically investigating and highlighting the difference between user-driven personalization and system-driven personalization
  • Challenges and limitations of implementing personalized persuasive technology and possible solutions
  • The relationships between individual characteristics and effectiveness of various persuasive technology features
  • Case studies and examples, success and failure stories of personalized persuasive technology
  • How to balance the costs and benefits of personalizing persuasive technology
  • How to develop ethical and privacy-sensitive personalized persuasive technology
  • What do we personalize (for example, do we personalize towards context, content, persuasive strategies, approaches, end-goals)?
  • Personalized and Tailored Persuasive Technologies
  • Adaptive vs. Customizable Persuasive Technologies
  • Who do we personalize for (e.g., personality, gender, age, culture, persuadability, player types, emotional states)?
  • What types of personal data (e.g., from environmental sensors, wearables, etc. ) should we use to design personalized persuasive systems?
  • How should we communicate persuasive messages? What types of communication channels and interfaces should we use?
  • How can we support user motivation to comply with the recommendations provided.
  • Combining different persuasive strategies, including persuasive recommenders
  • Exploitative persuasion / behaviour change design patterns (e.g. taxonomies, methods for discovery, categories)
  • Personalized anti-persuasion methods and applications (how to help users defend themselves from exploitative or addictive persuasive technology?)

Virtual Assistants, Conversational Interactions, and Personalized Human-Robot Interaction

University of Bari “Aldo Moro”, Italy

Polytechnic University of Bari, Italy

University of Naples Federico II, Italy

Virtual assistants and conversational agents are being employed to support information search and exploration, as well as to mediate interaction with users. Human-robot interaction is also increasingly attracting attention as a new model to support user activity and empowerment, with particular attention to people with physical impairments, who can benefit from assistance during the execution of tasks. People may also be able to benefit from companionship provided by virtual assistants and robots. In both contexts, personalization is a key element to support the adaptation of an agent to personal interests, idiosyncrasies, and needs.

A personalized and adaptive interaction strongly relies on learning a computational model of human behavior, and on its integration into the decision-making algorithms of an agent. This includes also the possibility of endowing the agent with meta-cognition capabilities, such as the capability of reasoning about the partner’s intentions, desires, and beliefs, as well as their internal states, personality, and emotions. The ability of an agent to adapt its behaviour according to social expectations, specific cultural norms, and individual preferences will determine the success and large-scale use of its applications.

 

This track aims to investigate new models and techniques for the adaptation of these agents to individual users.

 

Topics include (but are not limited to):

  • User-tailored agent-based interaction paradigms
    • Opportunities for agent personalization (e.g., personality, assertiveness, appearance, level of support)
    • Applications of virtual assistants and personalized agents, such as
      • Support individual or collaborative work (e.g., in an employment or domestic context)
      • Giving advice or making recommendations
      • Finding information or answering questions
      • Solving problems or getting tasks done
      • Learning or play
      • Companionship
      • Dialogue and interaction with robots
      • Supporting people with disabilities
  • User modeling in human-agent interaction
    • User cognitive state assessment and monitoring
    • Activity, intention, and emotion recognition
  • Personalization and user modeling in conversational interactions, such as for
    • Speech and text-based conversational interfaces
    • Dialogue management
    • Multimodal interaction
    • Conversational recommender systems
  • Context and personalized agents
    • Multi-user context (e.g., domestic context, schools, health centers)
    • Interfaces for “smart” environments (e.g., smart speakers, smart home assistants)
    • Mobile interactions (e.g., in smartphones or cars)
    • Culture-sensitive agents
  • Adaptation
    • Adaptation in physical/virtual interaction
    • Adaptation in multimodal interaction
    • Learning for robotic adaptation
    • Affective and emotion-adapted human-agent interaction
  • User-centric evaluation methods for personalized human-agent interactions
  • Transparency and Legibility of Adapted Interaction

Research Methods and Reproducibility

Universidad Autónoma de Madrid, Spain

Shanghai University of Finance and Economics, China

University of Gothenburg, Sweden

Research on user modeling and adaptive systems has greatly evolved during the last decades, but important challenges remain regarding the systematic comparison of different systems, the development of universally accepted and applied methodologies, and the use of standardized metrics to evaluate the acceptability and usefulness of systems to the user.

This track invites submissions on how research methods should be applied to personalized systems, in particular, when running benchmarks and measurement scales, with particular attention to the reproducibility of results and techniques. Furthermore, the track looks for submissions reporting new insights from reproducing and/or replicating existing works.

Topics include (but are not limited to):

  • Replications of past work on user modeling, personalization and recommendation, as well as reproducibility studies
  • Resource papers, e.g., new datasets, new software frameworks
  • Replications of user studies with alternative participant groups
  • Standardization of evaluation methodologies for personalized systems
  • Measurement scales for user-centric evaluation
  • Data-centered questions, e.g., quality, biases, noise, representativeness
  • Theory and practice papers, industry challenges in terms of evaluation and reproducibility
  • Reflective works on and guidelines for the reproducibility of UMAP research
  • Reflections on evaluation methods, e.g.,
    • which methods do we have,
    • when to use what,
    • limitations of simulations and user studies,
    • pros and cons,
    • gaps, little-explored techniques

Submission

All submissions must be written in English. Papers should be submitted electronically, in a PDF format, through the EasyChair submission system, https://easychair.org/conferences/?conf=umap24, by selecting the “UMAP24 Full and Short Papers” track.

Length and Formatting

Format. We encourage two types of submissions (reviewers will comment on whether the size is appropriate for each contribution), in the ACM new single-column format.

  • Long papers (14 pages at most plus additional pages for references; figures, tables, proofs, appendixes, acknowledgments, and any other content count toward the page limit) should report on substantial contributions of lasting value. They should reflect more complex innovations or studies and should have a more thorough discussion of related work. Each accepted long paper will be included in the main conference proceedings and presented in a plenary session as part of the main conference program.
  • Short papers (7 pages at most plus additional pages for references; figures, tables, proofs, appendixes, acknowledgments, and any other content count toward the page limit) typically discuss exciting new work that is not yet mature enough for a long paper – they are not “work-in-progress” reports but rather complete reports on a smaller or simpler-to-describe but complete research work on advances that can be described, set into context, and evaluated concisely. In particular, novel but significant proposals will be considered for acceptance to this category despite not having gone through sufficient experimental validation or lacking strong theoretical foundation. Each accepted short paper will be included in the main conference proceedings and presented either as an oral presentation or at a poster session as part of the main conference program.

We recommend that supplementary material is linked to an external source using an anonymized link.

Anonymity. Submissions must be anonymous, given that ACM UMAP uses a double-blind review process. Authors must omit their names and affiliations from submissions, and avoid obvious identifying statements. For instance, citations to the authors’ own prior work should be made in the third person. Failure to anonymize your submission could result in desk rejection.

Templates. Following the ACM Publication Workflow, all authors should submit manuscripts for review in the new ACM single-column format. Instructions for authors are given below:

Should you have any questions or issues going through the instructions above, please contact support at acmtexsupport@aptaracorp.com for LaTeX and Microsoft Word inquiries.

Accessibility. 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 and 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.

Submission Policy. All submissions and reviews will be handled electronically. ACM UMAP has a no dual submission policy, which is why submitted manuscripts should not be currently under review at another publication venue. Particularly, please consider the following ACM’s publication policies:

  1. “By submitting your article to an ACM Publication, you are hereby acknowledging that you and your co-authors are subject to all ACM Publications Policies, including ACM’s new Publications Policy on Research Involving Human Participants and Subjects. Alleged violations of this policy or any ACM Publications Policy will be investigated by ACM and may result in a full retraction of your paper, in addition to other potential penalties, as per ACM Publications Policy.”
  2. “Please ensure that you and your co-authors obtain an ORCID ID, so you can complete the publishing process for your accepted paper. ACM has been involved in ORCID from the start and we have recently made a commitment to collect ORCID IDs from all of our published authors. The collection process has started and will roll out as a requirement throughout 2022. We are committed to improve author discoverability, ensure proper attribution and contribute to ongoing community efforts around name normalization; your ORCID ID will help in these efforts.”

Content Expectations

Originality and Significance. Papers should report on original and substantial contributions of lasting value. Described work should concern the theory and/or practice of UMAP. Moreover, papers showcasing the innovative use of UMAP and exploring the benefits and challenges of applying UMAP technology in real-life applications and contexts are welcome.

Commisurated evaluation. Evaluations of proposed solutions/applications must be commensurate with the claims made in the paper. Depending on the intended contribution, this may include simulation studies, offline evaluations, A/B tests, or controlled user experiments.

Reproducibility. Research procedures and technical methods should be presented in sufficient detail to ensure scrutiny and reproducibility. We recognize that user data may be proprietary or confidential, but we encourage the sharing of (anonymized, cleaned) data sets, data collection procedures, and code.

Discussion and Implications. Results should be clearly communicated and implications of the contributions/findings for UMAP and beyond should be explicitly discussed.

Ethical & Human Subjects Considerations

ACM UMAP expects papers to include a discussion of the ethical considerations, as well as the impact of the presented work and/or its intended application, where appropriate. ACM UMAP further expects all authors to comply with ethical standards 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.

Review Process & Camera-ready Submission

Review. ACM UMAP uses a double-blind review process. Authors must omit their names and affiliations from their submissions; they should also avoid obvious identifying statements. For instance, citations to the authors’ prior work should be in the third person. Submissions not abiding by anonymity requirements will be desk rejected.

Reviewers will evaluate papers based on their significance, originality, rigor, and contribution to the field. Papers that are out of scope, incomplete, or lack sufficient evidence to support the basic claims, may be rejected without full review. Furthermore, reviewers will be asked to comment on whether the length is appropriate for the contribution. In addition, ACM UMAP 2024 will introduce a new “Raise Your Voice” stage during evaluation, offering a small window to authors to optionally discuss the initial decision of their submission, enhancing the transparency and quality of the reviewing process.

The ACM Code of Ethics gives the ACM UMAP program committee the right to (desk-)reject papers that perpetuate harmful stereotypes, employ unethical research practices, or uncritically present outcomes/implications that disadvantage minority communities. Further, reviewers will be explicitly asked to consider whether the research was conducted in compliance with professional ethical standards and applicable regulatory guidelines. Failure to do so could lead to a (desk-)rejection.

Camera-ready Information. Accepted papers will be subject to further revision to meet the requirements of the camera-ready format required by ACM. We strongly recommend the usage of LaTeX/Overleaf for the camera-ready papers to minimize the extent of reformatting. Users of the Word template must use either the version for Microsoft Word for Windows, Macintosh Office 2011, or Macintosh Office 2016 (other formats such as Open Office, etc., are not admitted) for the camera-ready submission to avoid incompatibility issues.

Instructions for preparing the camera-ready versions of accepted papers will be provided after acceptance. This might include instructions to prepare a video of the accepted contribution. Camera-ready versions of accepted papers will be later submitted using ACM’s new production platform where authors will be able to review PDF and HTML output formats before publication.

Registration and Presentation Policy

Each accepted paper must be accompanied by a distinct full author registration, completed by the early registration date cut-off. Each accepted paper must be presented in person to be included in the conference proceedings, published by ACM and available via the ACM Digital Library. The official publication date is when the proceedings are made available in the ACM Digital Library. This date may be up to two weeks before the first day of UMAP 2024. The official publication date affects the deadline for any patent filings related to published work.

Program Chairs

  • Panagiotis Germanakos, SAP SE, Germany
  • Elvira Popescu, University of Craiova, Romania

Contact information: umap2024-program at um.org