[rede.APPIA] DaSSWeb – Data Science and Statistics Webinar – 25 March – Álvaro Figueira – Machine Learning to Identify HE Institutions’ Social Media Publication Strategies

DaSSWeb- Data Science and Statistics Webinar

 

Tuesday, 25 March, 14:30 (GMT)

 

Speaker

Álvaro Figueira

Faculdade de Ciências

Universidade do Porto, Portugal

Title:

A Machine Learning Approach to Identify Higher Education Institutions’ Social Media Publication Strategies

Abstract

In the competitive landscape of higher education, institutions use
international rankings to secure funding, attract talent, and enhance
their global reputation. At the same time, they leverage social media
to boost recognition and engagement. This study examines the
relationship between Higher Education Institutions’ (HEIs) rankings
and their social media posting strategies. Analyzing tweets from 18
HEIs in a consolidated ranking system, we identified four distinct
clusters based on posting strategies, aligning with three ranking
tiers: high, moderate, or low. Posts were categorized into five
topics—engagement, research, image, society, and education—and an LSTM
model successfully predicted social media activity, revealing clear
patterns. Our findings suggest a connection between social media
engagement and HEI prestige.


Zoom link

[rede.APPIA] [CfP] 1st Workshop on Evolutionary Generative Models at GECCO25

Dear Colleague(s),

Below you will find the extended deadline call for papers for EGM 2025 – The first workshop on Evolutionary Generative Models.

https://sites.google.com/view/egm-2025

Feel free to distribute, and thank you for your time.

Best regards,

The Workshop Chairs

João Correia

Jamal Toutouh

Una-May O’Reilly

Penousal Machado

Erik Hemberg


—–

CALL FOR PAPERS – EGM@GECCO’25

1st Workshop on Enhancing Generative Machine Learning with Evolutionary Computation

https://sites.google.com/view/egm-2025

Genetic and Evolutionary Computation Conference (GECCO'25)

Malaga, Spain, July 14 to 18, 2025

#Overview and Scope

Generative Models have emerged as key to the field in Artificial Intelligence (AI). In general, a generative model is an AI algorithm that learns the underlying data distribution to produce new distributions, thus generating new data. Evolutionary generative models refer to generative approaches that employ any type of evolutionary algorithm, whether applied on its own or in conjunction with other methods. In a broader sense we can divide evolutionary generative models into at least three main types:

(i) Evolutionary Computation (EC) as a Generative Model focuses on exploring how EC techniques that serve directly as generative models to produce data, designs, or solutions that fulfill specific criteria or constraints;

(ii) Generative Models Assisting EC consists in modern generative models, such as Generative Adversarial Networks or diffusion models, that enhance the performance and capabilities of EC methods (e.g., using generative models such as surrogate).  

(iii) EC Assisting Generative Models discusses the role of EC techniques in enhancing generative models themselves, particularly through optimization and exploration. This includes approaches where EC is used to evolve or optimize the parameters of generative networks, help address generative models issues, or introduce adaptive mechanisms that improve model flexibility and resilience. It also delves into topics related to EC population dynamics such as cooperative or adversarial approaches.

The workshop on Evolutionary Generative Models (EGM) aims to act as a medium for debate, exchange of knowledge and experience, and encourage collaboration for researchers focused on generative models in the EC community. Thus, this workshop provides a critical forum for disseminating the experience on the topic using EC as a generative model, generative models assisting EC and EC assisting generative models, presenting new and ongoing research in the field, and to attract new interest from our community.

# Topics:

. Evolutionary Generative Models

. Generative Models in Evolutionary Computation

. Evolutionary Machine Learning Generative Models

. Evolutionary Generative Artificial Intelligence

. EC-assisted Generative Machine Learning training, generation, hyperparameter optimisation or architecture search.

. Co-operative or Adversarial Generative Models

. Evolutionary latent and embedding space exploration (e.g. LVEs)

. Interaction with Evolutionary Generative Models

. Real-world applications of Evolutionary Generative Models solutions

. Software libraries and frameworks for Evolutionary Generative Models

All accepted papers of this workshop will be included in the Proceedings of the Genetic and Evolutionary Computation Conference (GECCO'25) Companion Volume.

# Important dates

Submission opening: February 10, 2025

Submission deadline: March 26, 2025

Acceptance notification: April 28, 2025

Camera-ready and registration: May 5, 2025

Workshop date: TBC depending on GECCO program schedule (July 14 or 18, 2025)

# Instructions for Authors

We invite submissions of two types of paper:

·     Regular papers (limit 8 pages)

·     Short papers (limit 4 pages)

Papers should present original work that meets the high-quality standards of GECCO. Each paper will be rigorously evaluated in a review process. Accepted papers appear in the ACM digital library as part of the Companion Proceedings of GECCO. Each paper accepted needs to have at least one author registered by the author registration deadline. Papers must be submitted via the online submission system https://ssl.linklings.net/conferences/gecco/. Please refer to https://gecco-2025.sigevo.org/Paper-Submission-Instructions for more detailed instructions.

As a published ACM author, you and your co-authors are subject to all ACM Publications Policies (https://www.acm.org/publications/policies/toc), including ACM's new Publications Policy on Research Involving Human Participants and Subjects (https://www.acm.org/publications/policies/research-involving-human-participants-and-subjects).

# Workshop Chairs

·         João Correia, University of Coimbra (PT), jncor@dei.uc.pt

.         Jamal Toutouh, Univ. of Málaga (ES) – MIT (USA), jamal@lcc.uma.es

·         Una-May O’Reilly, MIT (USA), unamay@csail.mit.edu

·         Penousal Machado, University of Coimbra (PT), machado@dei.uc.pt

·         Erik Hemberg, MIT (USA), hembergerik@csail.mit.edu

More information at https://sites.google.com/view/egm-2025

[rede.APPIA] Deadline 4 April 2025 – ROAR-NET Training School on Computational Modelling of Combinatorial Optimisation Problems

Dear all, 

The First ROAR-NET Training School on Computational Modelling of Combinatorial Optimisation Problems, will take place at the Luxembourg Institute of Science and Technology (LIST) in Belvaux, Luxembourg, from 16 to 20 June 2025.

Trainee application deadline: 4 April 2025

More details: https://roar-net.eu/events/first-training-school/

About the Training School

The First ROAR-NET Training School will consist of a combination of lectures, problem-solving group projects, poster presentations by the Trainees, and team-building activities. Topics include:

  • Problem structuring
  • Problem modelling for constructive search and for local search
  • The ROAR-NET API specification
  • Practical aspects of model development and implementation

Each project involves the development, implementation (coding), and evaluation of a model for a given optimisation problem and will be carried out by a team composed of 4-5 Trainees and a mentor (a Trainer).

Who Can Apply?

PhD students, postdocs, researchers, and innovators with good programming and/or optimisation skills are invited to apply to attend the school as Trainees. Financial support is available for eligible applicants from COST Member and Near Neighbour Countries.

Trainee application deadline: 4 April 2025

For full details, see the Call for Trainee Applicationshttps://roar-net.eu/calls/ts-call-1/

About ROAR-NET

COST Action CA22137 – Randomised Optimisation Algorithms Research Network (ROAR-NET) is an interdisciplinary research network supported by COST. Involving researchers and innovators from academia, industry, and other interested parties, the network aims to make Randomised Optimisation Algorithms (ROAs) widely competitive in practice by identifying and reducing obstacles to their adoption at the scientific, technical, economic, and human levels. Focusing on practitioners, whose needs are seen as the driving force for new theoretical, methodological, and technical advances, ROAR-NET pursues the sustainable development of widely available software tools, training materials and programmes, and ultimately a more extensive acceptance and deployment of these methods.

The network brings together a large number of ROA theoreticians and algorithm developers, applied researchers, software developers, and practitioners from more than 40 countries. This geographical diversity helps to ensure that the frameworks, libraries, and software tools developed through the network are applicable to a wide range of real-world problems while supporting the latest theoretical developments.

Learn more about ROAR-NET: https://www.roar-net.eu/

About COST

COST (European Cooperation in Science and Technology) is a funding agency for research and innovation networks. COST Actions help connect research initiatives across Europe and enable scientists to grow their ideas by sharing them with their peers. This boosts their research, career, and innovation.

Learn more about COST: https://www.cost.eu/

We encourage all interested candidates to apply and look forward to welcoming you to Luxembourg in June 2025.

Best regards,

Ekhiñe Irurozki

LTCI, Télécom Paris, Institut Polytechnique de Paris

[rede.APPIA] EPIA 2025 – Call for Papers

*************************************
CALL FOR PAPERS
**************************************
EPIA 2025
24th EPIA Conference on Artificial Intelligence
October 1-3, 2025
Universidade do Algarve, Faro, Portugal
**************************************

The EPIA Conference on Artificial Intelligence (AI) is a well-established European conference in the field of AI. Its purpose is to promote research in all areas of AI, covering both theoretical and foundational issues and applications and the scientific exchange among researchers, engineers, and practitioners in related disciplines. The 24th edition, EPIA 2025, will take place in Faro from the 1st to the 3rd of October 2025. As in previous editions, this international conference is hosted with the patronage of the Portuguese Association for Artificial Intelligence (APPIA).

**************************************
IMPORTANT DATES
– Paper submission deadline: May 23, 2025 (AoE)
– Notification of paper acceptance: July 4, 2025
– Camera-ready papers: July 14, 2025 (AoE)
– Conference dates: October 1-3, 2025

**************************************
CALL FOR PAPERS
We invite all members of the international AI research and industry communities to submit their high-quality, previously unpublished papers to EPIA 2025.
EPIA2025 is organized around thematic tracks. These are intended to provide an environment that fosters an active exchange of ideas between attendees within specific sub-areas of AI.
In addition to the parallel sessions for the different tracks, there will be plenary sessions with invited lectures given by leading scientists, discussion sessions, and social events. More detailed and up-to-date information may be found at: https://epia2025.ualg.pt/

**************************************
SUBMISSION GUIDELINES
Papers should be prepared according to the Springer LNAI format, using either a LaTeX or a Word template, and should be a maximum of 12 pages, including references. However, authors should consider any track-specific details in their submission.
EPIA 2025 will not accept any paper that, at the time of submission, is under review for, has already been published in, or has already been accepted for publication in a journal or another venue with formally published proceedings. Authors of EPIA 2025 submissions are also not permitted to submit their paper to a journal or another venue with formally published proceedings during the EPIA 2025 review period. (As a guideline, authors should regard publications with a DOI, ISBN, or ISSN as formal publications. Questions about submission eligibility should be referred to the program chair before the deadline.) These restrictions do not apply to workshops and similar specialized presentations without formally published proceedings.
Submitted papers will be subject to a double-blind review process and will be peer-reviewed by at least three members of the respective thematic track program committee.
Authors are responsible for removing names and affiliations from the submitted papers and taking reasonable care to assure anonymity during the review process. Authors should also follow the standards set out in the Springer Nature code of conduct.
All accepted papers will be published by Lecture Notes in Artificial Intelligence, provided that at least one author is registered in EPIA2025 by the early registration deadline.
Each accepted paper is required to be presented by one of the authors in a track session.
Prospective authors should select the thematic track to which their paper is to be submitted.

EPIA2025 features the following thematic tracks covering a wide spectrum of AI topics:



**************************************
EPIA 2025 COMMITTEES

Event and Program Chairs
José Valente de Oliveira, Universidade do Algarve, NOVA LINCS
João Leite, Universidade Nova de Lisboa, NOVA LINCS, APPIA
João Rodrigues, Universidade do Algarve, NOVA LINCS
João Dias, Universidade do Algarve, CISCA
Pedro Cardoso, Universidade do Algarve, NOVA LINCS

Organisation Chairs
Simão Melo de Sousa, Universidade do Algarve, NOVA LINCS
Helder Daniel, Universidade do Algarve, NOVA LINCS
José Barateiro, Universidade do Algarve, NOVA LINCS
Marielba Zacarias, Universidade do Algarve, CISCA
Paula Martins Ventura, Universidade do Algarve, CISCA

João Leite

Head of Department

Department of Computer Science

E-mail: jleite@fct.unl.pt

Web: userweb.fct.unl.pt/~jleite

FACULDADE DE CIÊNCIAS E TECNOLOGIA | NOVA FCT
Universidade NOVA de Lisboa

Campus de Caparica | 2829-516 Caparica | Portugal

(+351) 21 294 8300 Ext. 10704

www.fct.unl.pt

[rede.APPIA] ECMLPKDD 2025 Discovery Challenge: Call for Proposals open until March 24th of 2025

ECMLPKDD 2025 Discovery Challenge
We welcome proposals for the Discovery Challenge of ECML PKDD 2025. Each year ECML PKDD hosts several challenges in order to promote research and evaluate machine learning approaches in real-world applications. The Discovery Challenge is open to academic and industrial institutions as well as to non-profit organizations. Each selected challenge will have a dedicated session in the conference to present the solutions, and will be invited to submit one paper to the ECML/PKDD workshop proceedings that describes the challenge and the winning solution(s). Moreover, each competition should select and review the two top solutions papers to be submitted to the ECML/PKDD workshop proceedings.
Conference website: ecmlpkdd.org/2025/
Discovery Challenge webpage: ecmlpkdd.org/2025/submissions-discovery-track/
———————— Key Dates & Deadlines ———————— Submission Deadline*: March 24, 2025 Author Notification*: March 31, 2025
———————— Competition Time Frame ———————— Start*: After April 21, 2025 End*: No later than June 30, 2025 Publish results*: No later than 8 July 2025 Submit Papers for Proceedings*: 31 July 2025
*All deadlines expire on 23:59 AoE (UTC – 12))
———————— Proposal Submission ———————— The proposals should cover the end to end organization of a challenge. The proposal should be 2 to max 4 pages and should contain the following information:
– Problem description: Why is the problem challenging and interesting? What is the real-world application and impact (research/societal, etc.)? Potential research impact? – Details on the exact tasks and the data (size, availability of meta data) – Privacy and ethical concerns and considerations related to the problem, tasks and data. – Evaluation: Describe very precisely how you will perform the evaluation, and any other policies. For example, what type of metrics you will use and how you will ensure a fair and rigid evaluation, are there just quantitative tasks or also qualitative evaluations and if so by whom, and how does this lead to the final ranking (pass/fail criteria, scores etc). – Communication plan: How do you plan to communicate, market and promote the challenge? How do you drive the volume submissions? Are you connected to particular communities? How do you ensure the challenge is made accessible for a a wide variety of participants, so that everyone could attend? How do you plan to communicate the results? – Technical details: The platform you will use to host the challenge, discussion areas, leaderboard, for example codabench.org or others. Baselines and code for data accessing that you will provide to participants. Will these be shared through github? – Reporting requirements for the participants’ submissions, like for example, a report, code etc. and are these must have requirements or optional, pass/fail or graded etc. ECML PKDD can offer facilities to upload papers (CMT). – Timeline for the challenge. Note that you should respect the overall time frame mentioned above. – Awards: The type of tangible or intangible awards/prizes you will consider for the winning solutions. – Details of the organizers of the challenge (Short CVs, Contact Details).
For reference, see the 2024 competitions at ecmlpkdd.org/2024/program-discovery-challenge/
Submission site: cmt3.research.microsoft.com/ECMLPKDD2025
Please submit your proposal as: Create new submission and select the track: Discovery Challenge.
———————— Paper format ———————— Discovery Challenge papers (describing the top systems) must be written in English, have a maximum of 8 pages, and should be formatted according to the Springer LNCS guidelines. Author instructions, style files and a copyright form can be obtained from the Discovery Challenge webpage (ecmlpkdd.org/2025/submissions-discovery-track/). In case of questions, do not hesitate to contact the Discovery Challenge chairs (mail list below).
———————— Contact ———————— Please send your submission through CMT. For further questions and information please contact the Discovery Challenge chairs, Carlos Ferreira (Polytechnic Institute of Porto & INESC TEC), Peter van der Putten (Leiden University & Pegasystems) and Rui Camacho (University of Porto & INESC TEC) through the following mailing list: ecml-pkdd-2025-discovery-challenge-chairs@googlegroups.com
Carlos Ferreira
ISEP | Instituto Superior de Engenharia do Porto Rua Dr. António Bernardino de Almeida, 431 4249-015 Porto – PORTUGAL tel. +351 228 340 500 | fax +351 228 321 159 mail@isep.ipp.pt | www.isep.ipp.pt
— Esta mensagem foi enviada para a rede APPIA, que engloba os associados da APPIA. Se desejar deixar de receber este tipo de mensagens, p.f. envie um email para appia [at] appia [ponto] pt

[rede.APPIA] ECML PKDD 2025: Applied Data Science Track Call for Papers

Call for Papers
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases – ECML PKDD 2025 Porto, Portugal, September 15-19, 2025
Conference website: ecmlpkdd.org/2025/
Call for Papers – Applied Data Science Track
The Applied Data Science Track solicits submissions that present compelling applications of Data Science and related areas (e.g., Business Analytics, Decision Support Systems, Machine Learning, Intelligent Data Analysis, Knowledge Discovery, Data Mining). The submissions should address challenging and important real-world tasks (e.g., Industry 4.0, Smart Cities, Health, Finance), thereby bridging the gap between Data Science practice and theory. The submitted papers should clearly explain the specific real-world challenges addressed (e.g., real-world domain goals, restrictions and other issues; analyzed data properties, including size and quality), the Data Science methodology used (including its evaluation procedure), and the conclusions and implications (e.g., domain impacts) that are drawn for the respective use cases. The ADS track aims to accept papers that provide practitioners with valuable insights into how to apply Data Science in real-world scenarios, showcasing their practical relevance. Alternatively, submissions may highlight novel use cases that contribute to expanding the understanding of the applicability of the Data Science methodologies in practical settings. Lastly, the track welcomes papers contributing to the overall knowledge base on the real-world application of Data Science principles. In terms of Data Science deployment level, it is expected a minimum Technology Readiness Level (TRL) of four: technology validated in laboratory environment. For example, this can include computer experiments that realistically simulate the real-world conditions (e.g., goals, restrictions) of the targeted use cases.
Authors are encouraged to comment on the practical implications and significance of their solutions, which can include deployment works or plans, and measured or estimated domain impacts in real-world scenarios or environments. Regarding methodological novelty, this track welcomes but does not require the introduction of novel Data Science techniques. Instead, the emphasis is placed on the relevance and impact of the applied solutions to real-world challenges, even if proposed systems combine previously known building blocks. Finally, to facilitate transparency and reproducibility, whenever possible, authors should disclose their computer code and/or data in a public form. In cases where there are business or industry proprietary code and/or data restrictions, acceptable solutions are the public disclosure of some portions of the code/data or their anonymized versions. Another possibility is the complementary usage of public domain Data Science libraries and datasets.
Paper Submission
Authors are invited to submit their papers using the CMT conference tool: cmt3.research.
A list of domains and data science subject areas follow below:
Application Domain: Agriculture, Food and Earth Sciences, Arts and Humanities, Industry (4.0, 5.0, Manufacturing, …), Finance, Economy, Management or Marketing, Health, Biology, Bioinformatics or Chemistry, Social Sciences (Social Good, Psychology, History, …), Education, Engineering and Technology, Smart Cities, Transportation and Utilities (e.g., Energy), Sports, Web and Social Networks.
Data Science Approach/Method: Data Engineering (e.g., data preprocessing, integration), Descriptive (e.g., data visualization, unsupervised learning), Predictive (e.g., classification, regression, time series), Prescriptive (e.g., optimization, simulation, metaheuristics), Model Exploitation (e.g., explainability, fairness, monitoring), Machine Learning (including Deep Learning), Natural Language Processing and General Intelligence (e.g., LLM), Reinforcement Learning.
Key Dates and Deadlines
CMT Opening: 2025-02-07
Abstract Submission: 2025-03-07
Paper Submission: 2025-03-14
Author Notification: 2025-05-26
CRC Submission: 2025-06-13

Paper Format
Papers must be written in English and formatted in LaTeX, following the outline of our author kit. The kit includes a readme document, a LaTeX file template containing author instructions, and style files. The maximum length of papers is 16 pages (including references) in this format. The program chairs reserve the right to reject any over-length papers without review. Papers that ‘cheat’ the page limit by, including but not limited to, using smaller than specified margins or font sizes will also be treated as over-length. Note that, for example, negative vspaces are also not allowed by the formatting guidelines; further details can be found in the author kit. Up to 10 MB of additional materials (e.g., proofs, audio, images, video, data, or source code) can be uploaded with your submission. If there is an appendix, ensure it is submitted separately from your paper, which must adhere to the 16-page limit.The reviewers and the program committee reserve the right to judge the paper solely on the basis of the 16 pages of the paper; looking at any additional material is at the discretion of the reviewers and is not required.
Authorship
The author list as submitted with the paper is considered final. No changes to this list may be made after paper submission, either during the review period, or in case of acceptance, at the final camera-ready stage.
Double-blind Review
Similarly to previous years, we will apply a double-blind review-process (author identities are not known by reviewers or area chairs; reviewers do see each other’s names). All papers need to be ‘best-effort’ anonymized. Papers must not include identifying information of the authors (names, affiliations, etc.), self-references, or links (e.g., GitHub, YouTube) that reveal the authors’ identities (e.g., references to own work should be given neutrally like other references, not mentioning ‘our previous work’ or similar). We strongly encourage making code and data available anonymously (e.g., in an anonymous Github repository, or Dropbox folder). The authors might have a (non-anonymous) pre-print published online, but it should not be cited in the submitted paper to preserve anonymity. Reviewers will be asked not to search for them. We recognize there are limits to what is feasible with respect to anonymization. For example, if you use data from your own organization and it is relevant to the paper to name this organization, you may do so.
Conference Attendance
For each accepted paper, at least one author must register for the main conference and present the paper in person.
Proceedings
The conference proceedings will be published by Springer in the Lecture Notes in Computer Science Series (LNCS).
Reproducible Papers
Authors are strongly encouraged to adhere to the best practices of Reproducible Research, by making available data and software tools that would enable others to reproduce the results reported in their papers. We advise the use of standard repository hosting services such as Dataverse, mldata.org, OpenML, figshare, or Zenodo for data sets, and mloss.org, Bitbucket, GitHub, or figshare (where it is possible to assign a DOI) for source code. If data or code gets updated after the paper is published, it is important to enable researchers to access the versions that were used to produce the results reported in the paper. Authors who do not have a preferred repository are advised to consult Springer Nature’s list of recommended repositories and research data policy.
Ethics Considerations
Ethics is one of the most important topics to emerge in Machine Learning, Knowledge Discovery and Data Mining. We ask you to think about the ethical implications of your submission – such as those related to the collection and processing of personal data or the inference of personal information, the potential use of your work for policing or the military. You will be asked in the submission form about the ethical implications of your work which will be taken into consideration by the reviewers.
Authors Commit to Reviewing
Authors of submitted papers agree to provide the email address of at least one author who holds a PhD to be a potential PC member for ECML PKDD 2025 and may be asked to review papers for the conference if we have many more submissions than expected. This does not apply to authors who are (a) already contributing to ECML PKDD (e.g., accepted a PC/AC invite, are part of the organizing committee) or (b) not qualified to be ECML PKDD PC members (e.g., limited background in ML or DM).
Dual Submission Policy
Papers submitted should report original work. Papers that are identical or substantially similar to papers that have been published or submitted elsewhere may not be submitted to ECML PKDD, and the organizers will reject such papers without review. Authors are also NOT allowed to submit or have submitted their papers elsewhere during the review period. Submitting unpublished technical reports available online (such as on arXiv), or papers presented in workshops without formal proceedings, is allowed, but such reports or presentations should not be cited to preserve anonymity.
Conflict of Interest
During the submission process, you must enter the email domains of all institutions with which you have an institutional conflict of interest. You have an institutional conflict of interest if you are currently employed or have been employed by that institution in the past three years, or you have extensively collaborated with the institution within the past three years. Authors should also identify other conflicts of interest, such as co-authorship in the last five years, colleagues in the same institution within the last three years, and advisor/student relations (anytime in the past).
Contact
For further information, please contact Mail:
ecml-pkdd-2025-ads-track-chairs@googlegroups.com
Carlos Ferreira
ISEP | Instituto Superior de Engenharia do Porto Rua Dr. António Bernardino de Almeida, 431 4249-015 Porto – PORTUGAL tel. +351 228 340 500 | fax +351 228 321 159 mail@isep.ipp.pt | www.isep.ipp.pt — Esta mensagem foi enviada para a rede APPIA, que engloba os associados da APPIA. Se desejar deixar de receber este tipo de mensagens, p.f. envie um email para appia [at] appia [ponto] pt