Candidate:
Gil Filipe da Rocha

Date, Time and Place
October 2, 14:00, Room Professor Joaquim Sarmento (G129), DEC, FEUP

President of the Jury
Rui Filipe Lima Maranhão de Abreu, PhD, Full Professor, Faculdade de Engenharia, Universidade do Porto

Members
Hugo Ricardo Gonçalo Oliveira, PhD, Associate Professor, Department of Computer Science, Faculdade de Ciências e Tecnologia, Universidade de Coimbra;
Bruno Emanuel da Graça Martins, PhD, Associate Professor, Department of Electrical and Computer Engineering, Instituto Superior Técnico, Universidade de Lisboa;
Eugénio da Costa Oliveira, PhD, Emeritus Professor, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto;
Sérgio Sobral Nunes, PhD, Associate Professor, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto;
Henrique Daniel de Avelar Lopes Cardoso, PhD, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto (Supervisor).

 Abstract
“The aim of argumentation mining is to automatically detect, identify and extract arguments from natural language text. The end goal is to provide a structured representation of the arguments (argument diagrams) that can be automated and analyzed in many different ways. Argumentation is a rhetorical act that has been studied for centuries and has been influenced by different research fields such as philosophy, linguistics, computer science, and artificial intelligence. In general, arguments are justifiable positions where pieces of evidence (premises) are offered in support of a claim (conclusion). Some characteristics of natural language text and, more specifically, of argumentation exposition make argumentation mining a complex task. Indeed, the ambiguity of natural language text, the assumption of commonsense reasoning and implicit knowledge, different writing styles, and the inherent complexity of argument diagrams are some of the challenges that argumentation mining systems have to overcome. Addressing these challenges, especially across different languages and text genres, demands robust argumentation mining systems. In this thesis, we conduct research toward the development of a robust computational system that can be employed to detect, identify, and extract argumentative content across different languages and text genres. Our vision is to deploy such a system to address argumentation mining in less-resourced languages (such as Portuguese) and in text genres that feature high-variability of argument exposition profiles (such as opinion articles). To this end, we combine techniques from computational linguistics and machine learning with knowledge from argument structure and rhetoric theories to automatically identify argumentative reasoning in natural language texts. To study argumentation mining in a less-resourced language and a challenging text genre, we conduct an annotation study to create a corpus annotated with arguments from opinion articles written in Portuguese. To address the challenging argumentation mining task, we propose a relation-based approach and context-aware models motivated by argumentation theory foundations and tailored to overcome some of the challenges of argument exposition. To tackle this task in a less-resourced language, we investigate how cross-language learning techniques can be employed to explore annotated resources from different languages and improve the performance of machine learning models in a target language. Finally, to improve the robustness of argumentation mining systems across different genres, we leverage recent advancements in language modeling capabilities and propose a cross-genre approach for argumentation mining.”

Candidate:
António Humberto e Sá Pinto

Date, Time and Place:
September 8, 14:30, Sala de Atos FEUP

President of the Jury:
António Fernando Vasconcelos Cunha Castro Coelho, PhD, Associate Professor with Habilitation, Faculdade de Engenharia da Universidade do Porto;

Members:
Magdalena Fuentes, PhD, Assistant Professor, Music and Audio Research Lab (MARL) and Integrated Design & Media (IDM), New York University (NYU);
Jason Hockman, PhD, Associate Professor, School of Computing and Digital Technology (DMT), Birmingham City University (UK);
Matthew Edward Price Davies, PhD, Senior Scientist,  SiriusXM/Pandora (USA) – (Supervisor);
Rui Pedro da Silva Nóbrega, PhD, Assistant Professor, Departamento de Informática, Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa;
Aníbal João de Sousa Ferreira, Associate Professor, Departamento de Engenharia Eletrotécnica e de Computadores, Faculdade de Engenharia da Universidade do Porto.

The thesis was co-supervised by Prof Rui Luís Nogueira Penha, Coordinating Professor at ESMAE, and Prof Gilberto Bernardes de Almeida, Assistant Professor at FEUP.

Abstract:

“Music Information Retrieval (MIR) is an interdisciplinary field focused on the extraction, analysis, and processing of information from various musical representations.
Grounded on the automatic analysis of musical facets such as rhythm, melody, harmony, and timbre, MIR enables applications in areas like music recommendation, automated music transcription, and intelligent music composition tools. Rhythm, an integral element of music, provides a foundation for decoding music’s complex relational structures and layered depth. Computational rhythm analysis is thus central to MIR research. It encompasses a wide range of tasks, such as the pivotal beat tracking, which unlocks the use of musical time across many MIR systems. However, conventional beat-tracking methods have struggled when dealing with complex musical features, such as expressive timing or intricate rhythmic patterns. While specialized approaches demonstrate some degree of adaptation, they do not generalise to diverse scenarios. Deep learning methods, while promising in addressing these issues, depend heavily on the availability of substantial annotated data. In scenarios requiring adaptation to user subjectivity, or where acquiring annotated data is challenging, the efficacy of beat-tracking methods lowers, thus leaving a gap in the applicability of computational rhythm analysis methods. This thesis investigates how user-provided information can enhance computational rhythm analysis in challenging musical conditions. It initiates the exploration of human-in-the-loop strategies with the aim of fostering adaptability of current MIR techniques. By focusing on beat tracking, due to its fundamental role in rhythm analysis, our goal is to develop streamlined solutions for cases where even the most advanced methods fall short. This is achieved by utilising both high-level and low-level user inputs —- namely, the user’s judgement regarding the expressiveness of the musical piece and annotations of a brief excerpt —- to adapt the state of the art to abstract particularly demanding signals. In an exploratory study, we validate the shared perception of rhythmic complexity among users as a proxy for musical expressiveness, and consequently as a key performance enhancer for beat tracking. Building upon this, we examine how highlevel user information can reparameterise a leading-edge beat-tracker, augmenting its performance to highly expressive music. We then propose a transfer learning method that finetunes the current state of the art, hereafter referred to as the baseline, to a concise user-annotated region. This method exhibits versatility across varied musical styles and offers potential solutions to the inherent limitations of previous approaches. Incorporating both user-guided contextualisation and transfer learning into a human-in-the-loop workflow, we undertake a comprehensive evaluation of our adaptive techniques. This includes examining the key customisation options available to users and their effect on performance enhancement. Our approach outperforms the current state of the art, particularly in the challenging musical content of the SMC dataset, with an improvement over the baseline F-measure of almost 10 percentage points (corresponding to over 16%). However, these quantitative improvements require further interpretation due to the inherent differences between our file-specific, human-in-the-loop technique and traditional dataset-wide methods, which operate without prior exposure to specific file characteristics. With the aim of advancing towards a user-centric evaluation framework for beat tracking, we introduce two novel metrics: the E-Measure and Annotation Efficiency. These metrics account for the user perspective regarding the annotation and finetuning process. The E-Measure is a variant of the F-measure focused on the annotation correction workflow and includes a shifting operation over a larger tolerance window. The Ae is defined as the relative (to the baseline) decrease in correction operations enabled by the fine-tuning process, normalised by the number of user annotations. Specifically, we probe the theoretical upper bound of beat tracking accuracy improvement over the SMC dataset. Our results show that the correct beat estimates provided by our approach surpass those of the state of the art by more than 20%. When considering the full length of the files, we can further frame this improvement in terms of gain per unit of user effort, quantifying the annotation efficiency of our approach. This is reflected in the substantial reduction of required corrections, with nearly 2/3 fewer corrections per user annotation compared to the baseline. In the final phase, we evaluate our human-in-the-loop strategy’s adaptability across a range of musical genres and instances presenting significant challenges. Our exploration extends to various rhythm tasks, including beat tracking, onset detection, and (indirectly) metre analysis. We apply this user-driven strategy to three unique genres with complex rhythm structures, such as polyrhythms, polymetres, and polytempi. Our approach exhibits swift adaptability, enabling efficient utilisation of the state-of-the-art method while bypassing the need for extensive retraining. This results in a balanced integration of data-driven and user-centric methods into a practical and streamlined solution.”

Keywords: Music Information Retrieval; User-centric; Transfer Learning; Beat Tracking.

Requested by:
Joana Rodrigues da Silva

Date, time and place
July 19, 14h30, room L119 DEMEC (FEUP)

President of the Jury:
António Fernando Vasconcelos Cunha Castro Coelho, PhD, Associate Professor with Habilitation, Departamento de Engenharia Informática, Faculdade de Engenharia da Universidade do Porto.

Members:
Teresa Isabel Lopes Romão, PhD, Associate Professor, Departamento de Informática, Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa;
Luís António Santos, PhD, Assistant Professor, Departamento de Ciências de Comunicação, Instituto de Ciências Sociais da Universidade do Minho;
Miguel Ângelo Rodrigues Midões, PhD, Invited Adjunct Professor, Departamento de Comunicação e Arte, Escola Superior de Educação do Instituto Politécnico de Viseu;
Helena Laura Dias de Lima, PhD, Associate Professor, Departamento de Ciências da Comunicação e da Informação, Faculdade de Letras da Universidade do Porto (Supervisor);
Alexandre Miguel Barbosa Valle de Carvalho, PhD, Assistant Professor, Departamento de Engenharia Informática, Faculdade de Engenharia da Universidade do Porto.

Abstract:

“After the COVID-19 epidemic and the consequent humanitarian crises that devastated the planet, there is a need to claim the role of investigative journalism as a watchdog and permeation system of social justice and democracy through public exposure. We are witnessing a sharp decrease in investment in this journalism specialty, either because of its impertinence in dealing with public management issues or because of the time spent on this type of investigation, which fundamentally takes longer than current journalism to produce results. In this sense, we perceive the influence of automation and artificial intelligence in information production processes to highlight all human tasks with the possibility of being carried out in less time by technological systems. Considering this possibility, there was an interest in studying, in-depth, how robotics and the application of artificial intelligence through platforms that support the usual procedure of journalism can help and even improve the global state of investigative journalism practice, nowadays. The Connect-the-Dots platform and the DODO assistant emerge as a hypothetical digital solution for some of the problems that investigative journalism currently faces. It could be a way to practically implement investigative journalism in its scope of innovation by integrating tools and open-source practices in a Design-Based-Research approach to knowledge archaeology.”

Keywords: Artificial Intelligence, Automation, Investigative Journalism, Design-Based-Research, Digital Media.

Candidate:
Yulia Karimova

Date, time and place
June 2, 14:00, Sala de Atos FEUP

President of the Jury
António Fernando Vasconcelos Cunha Castro Coelho, PhD, Associate Professor with habilitation, Faculdade de Engenharia da Universidade do Porto.

Members
Maria Manuel Lopes de Figueiredo Costa Marques Borges, PhD, Associate Professor, Departamento Filosofia, Comunicação e Informação, Faculdade de Letras da Universidade de Coimbra;
José Luis Brinquete Borbinha, PhD, Full Professor, Instituto Superior Técnico da Universidade de Lisboa;
Irene Pimenta Rodrigues, PhD, Associate Professor, Departamento de Informática, Escola de Ciências e Tecnologia da Universidade de Évora;
Maria Cristina de Carvalho Alves Ribeiro, PhD, Associate Professor, Departamento de Engenharia Informática, Faculdade de Engenharia da Universidade do Porto (Supervisor);
Carla Alexandra Teixeira Lopes, PhD, Assistant Professor, Departamento de Engenharia Informática, Faculdade de Engenharia da Universidade do Porto.

Abstract
The growing amount of research data and the recognition of their value in the scientific community has led to the development of policies, infrastructures, tools and services. Researchers are encouraged to open their data and make them FAIR (Findable, Accessible, Interoperable and Reusable) to ensure the verifiability of results and transparency of research, while increasing their value. In this context, Research Data Management (RDM) becomes a vital component of high-quality research and a regular activity for researchers. The Data Management Plan (DMP), provision of quality metadata, repository selection, and data publication are some of the activities that researchers need to undertake when following the Open Science policies. However, these activities are time-consuming and not obvious to researchers, requiring specific knowledge, effort and experience. To support researchers, institutions are looking for solutions and developing workflows, tools, systems and services that aim to meet RDM requirements of both researchers and funding agencies. Implementing any information system, tool or service at a research institution requires their development, testing and evaluation, as well as adaptation to existing regulations. In this work, we present the development of a DMP support system that meets RDM requirements and researcher needs. We also propose its implementation in the institutional infrastructure and workflow. We explore various aspects related to the DMP support system development, namely RDM and DMP requirements and legislation at the international and national levels, institutional project management and RDM workflows, existing initiatives, recommendations and tools. We introduce a collaborative DMP-building method based on collaboration between researchers and a data steward. We describe its application to case studies from different scientific domains, analyze the results and propose its systematic evaluation. We also propose a path that simplifies the DMP creation process, to make plans more standard, high-quality, and detailed, by implementing controlled vocabularies in the DMP support system. To this end, we apply the collaborative method on projects from the same scientific domain, identifying specific aspects for this domain and proposing terms that can be used with controlled vocabularies and possibly contributing to the design of Domain Data Protocols. The proposed DMP support system also considers the existing mechanisms of automation and interoperability, namely the machine-actionable DMP (maDMP) standard. We analyze the maDMP standard and existing tools created according to this standard and propose a DMP structure and a DMP workflow that can help to make the DMP machine-actionable. Finally, we suggest the implementation of the DMP support system in the institutional RDM workflow, and the interface to support researchers in DMP creation and RDM activities in general. Moreover, this work concludes that the DMP support system can be implemented in any institution, and used for projects in different scientific domains. The results constitute a guide for institutions that are still at the beginning of the development of the RDM infrastructure. The feedback from researchers shows that they need support in DMP creation and monitoring, not only at the planning stage of the project but also during its course and sometimes even after. They are very positive about the implementation of the proposed system, highlighting its importance and necessity. Along with researchers, institutions also benefit from the implementation of such a system by providing support to researchers in RDM issues, reducing the time to create plans, improving the quality of DMPs and making projects comply with the RDM and funders’ requirements, thereby contributing to the prestige of the institution.

Candidate:
Zafeiris Kokkinogenis

Date, time and place
23^rd September, 14:30, Sala de Atos FEUP

President of the Jury:

Carlos Manuel Milheiro de Oliveira Pinto Soares, PhD, Associate Professor, Departamento de Engenharia Informática, Faculdade de Engenharia da Universidade do Porto

Members:

Alberto Fernandez Gil, PhD,  Associate Professor, Departamento de Ciencias de la Computación, Arquitectura de Computadores, Lenguajes y Sistemas Informáticos y Estadística e Investigación Operativa, Universidad Rey Juan Carlos;

Sandra Maria Monteiro de Melo, PhD, Main Researcher of the Business Unit INTELI – Policy & Intelligence for Sustainability, CEiiA – Centre of Engineering and Product Development;

Pedro José Ramos Moreira de Campos, PhD, Assistant Professor, Agrupamento Científico de Matemática e Sistemas de Informação, Faculdade de Economia da Universidade do Porto;

Rosaldo José Fernandes Rossetti, PhD, Associate Professor, Departamento de Engenharia Informática, Faculdade de Engenharia da Universidade do Porto (Supervisor);

Ana Paula Cunha da Rocha, PhD, Associate Professor, Departamento de Engenharia Informática, Faculdade de Engenharia da Universidade do Porto.

Abstract

Generally speaking, a large-scale socio-technical system is formed up of individual entities that are distributed along with the system’s space and act asynchronously in their decision making processes. Each of the individuals bears its own goals and tends to behave rather “selfishly” and “greedily” to maximise self-welfare utilities. However, this characteristic will generally affect negatively the global efficiency and the designed (expected) emergent behavior of the system. Indeed, private road transport imposes negative externalities on society, such as road capacity restrictions, accidents, congestion, etc. An efficient mobility model must take into account the real costs of transport, and its regulatory framework will need to produce the conditions for people to make sustainable transport choices. Economic theories offer two types of instruments for addressing the problem of transport externalities: command-and-control and incentive-based policies.

Command-and-control policies are government regulations which force users to change their behavior. In that sense, recent approaches to optimise the traffic network throughput and reduce traffic congestion basically rely on “road pricing”. However, this approach ends up penalising the user and creating social inequalities as it imposes a tax to be paid. Only those who are insensitive to the price will benefit. Also, a population may not be responsive to the defined penalties, and thus, the regulation may not be efficient.

On the other hand, an approach that has gained the community’s attention is based on the implementation and design of incentive schemes in public policy. Incentives are seen as those external measures that try to motivate a behavior change towards the objective of the system. It appears to be a “fairer” vision, as it does not discriminate the user but rather tries to bring the society into equilibrium.

The domain area on which this PhD thesis is focused concerns open and competitive multiagent systems, such as the Intelligent Transportation Systems (ITS) and the electricity markets. This thesis intends to address the issue of whether or not incentive-centred designs can favour the emergence of social-aware behavior in agents that have selfish tendencies for a (global) optimal evolution of a socio-technical system. Traditional transport planning tools using the four-step model combined with standard economic appraisal methods are not able to provide such analysis. Instead, a multi-agent system (MAS) social simulations can be used as it is argued in the literature of complex systems.

Keywords: Multi-Agent Systems, Incentive Mechanisms, Resource Markets, Policy Evaluation, Traffic Simulation.

Candidate:
Francisca Santos Silva Rocha Gonçalves

Date, time and place
22nd September, 10h00, Sala de Atos FEUP

President of the Jury
António Fernando Vasconcelos Cunha Castro Coelho, PhD, Associate Professor with Habilitation at Faculdade de Engenharia da Universidade do Porto

Members
Angus Carlyle, PhD, Professor at University of Arts London, UK;
Isabel Maria Antunes Pires, PhD, Invited Assistant Professor at Universidade Nova de Lisboa;
Raquel Maria Lemos e Castro, PhD, Researcher at Universidade Lusófona de Humanidades e Tecnologias;
Rui Luís Nogueira Penha, PhD, Assistant Professor at Instituto Politécnico do Porto (Supervisor);
Gilberto Bernardes de Almeida, PhD, Assistant Professor at Faculdade de Engenharia da Universidade do Porto.

Abstract

The aim of this thesis is to connect people with underwater environments while creating awareness for the problem of anthropogenic noise pollution through artistic creation. This dissertation addresses the lack of information on underwater noise discourse, especially on the vibrational aspect of underwater sound. By asking how to convey the experience of underwater soundscapes and their human disruption, it proposes two major directions that inform and complement each other. First, several underwater soundscape recordings were realised. They provide an understanding of the ambience of places and allow attunement with the natural world. Second, six practice-based research artworks based on the soundscape recordings and methods from acoustic ecology and ecoacoustics, focusing on anthropogenic sounds aimed at improving inclusion with nature while creating awareness of the noise pollution problem. The revised strategies and concepts included place attachment, emotional affinity, nature-connectedness and ecology of æffect. These artworks provide the setting for challenging audiences to bond with underwater environments by listening to their soundscapes while revealing a particular aspect of underwater sound. Moreover, they explore creative strategies for developing sonic experiences with the introduction, experience and performance of underwater sounds in artistic creation. Additionally, the artworks introduce and approach a natural phenomenon related to underwater sound (Luciferina – bioluminescence; SINØ III – cymatics; #switchoffandlisten – noise awareness campaign; DIS_turbation – bioturbation; Munda – cavitation; 2182kHz – auditory masking). The insights from the artistic experiences proved critical to continue producing innovative contributions and to create knowledge while influencing the communities. The significance of this study is that it informs the theoretical understanding of noise pollution impacts on aquatic fauna and underwater acoustics by introducing a focus on the vibrational aspect of underwater sound: particle motion. In addition, it informs the empirical understanding of the practice-based research on developing the proposed artworks. The novelty lies in addressing biological phenomena as a creative resource to intervene in underwater noise dialogue, reveal hidden qualities of vibroscape ecology (such as particle motion) and translate them in a more grasping way through the artistic artworks. As underwater soundscapes are increasingly a topic of concern globally, they become crucial to fostering an emotional affinity between people and natural environments, promoting inclusion with nature.

Keywords: ecological sound art, acoustic ecology, underwater soundscapes, anthropogenic noise, vibroscape ecology, nature-connectedness, ecology of æffect.

Candidate:
Terhi Tuulikki Marttila

Date, Time and place:
June 27, 10:00, Sala de Atos of FEUP

 President:

António Fernando Vasconcelos Cunha Castro Coelho, PhD, Associate Professor with Habilitation, Faculdade de Engenharia da Universidade do Porto.

Members:

Anne Karhio, PhD, Associate Professor, Faculty of education of Inland Norway, University of Applied Sciences;

Manuel José de Freitas Portela, PhD, Full Professor, Faculdade de Letras da Universidade de Coimbra;

Vitor Manuel Pereira Duarte dos Santos, PhD, Assistant Professor, NOVA IMS da Universidade Nova de Lisboa;

José Miguel Santos Araújo Carvalhais Fonseca, Professor Auxiliar da Faculdade de Belas Artes da Universidade do Porto;

Diamantino Rui da Silva Freitas, PhD, Associate Professor, Faculdade de Engenharia da Universidade do Porto (Supervisor).

Abstract:

In this artistic research we start from the idea that digital works can be utilized for imagining and playing with yet impossible realities, for asking questions, and for portraying aspects of life such that we can explore these from a distance. This dissertation consists of three browser-based artworks programmed by myself in HTML, Javascript and CSS. These art experiences unfold on the screen, asking the person to interact with them in order to complete their meanings. The works incorporate, among other things, voice interaction through synthetic speech and speech input, the uses of which form an essential component of the works meanings. Each work is concerned with very different types of questions around migration, but overall, and as a triptych, the works explore what the movement brought about by migration implies from a human standpoint. The themes encompassed extend from exploring perspectives on language, where movement results in linguistic accent which provokes a notion of the Other through external difference (in We cannot take them all), or exploring the movement induced by the tension between our body and our personal needs and desires, but that is governed by (shifting) borders (in Speak out) and finally, at exploring migratory movement through the ambivalent relationship between the here and the there, the simultaneous processes of (re-)rooting and of living with homesickness (in Transplanted). While this research may not depart from clear research questions, it nevertheless arrives at observations about the artistic strategies that emerge when migration is explored through notions of voice/interaction. The works themselves open up a space of contemplation about the respective themes, inviting participation through voice.

Keywords: migration, voice interaction, electronic literature, digital art, artistic research