Patricia Martín-Rodilla

University of A Coruña | UDC · Computer Science

In 2017, we launched eRisk as a CLEF Lab to encourage research on early risk detection on the Internet. Since then, thanks to the participants’ work, we have developed detection models and datasets for depression, anorexia, pathological gambling and self-harm. In 2023, it will be the seventh edition of the lab, where we will present a new type of t...

Research PhD. Work opportunities in Europe in NLP and related fields I'm sharing here open positions from our European project. Excellent work opportunities around Europe. https://hybridsproject.eu/phd-projects/

We present in this article the Plugin for phonetic-phonological analysis in Spanish (PAFe), which consists of a series of scripts (a code written with a programming language (Python) that, implement three different intonation comparison algorithms of an ELE (Spanish as a foreign language) student and a native speaker of Spanish), allowing, in turn,...

eRisk constitutes now a reference forum in the study and detection of risk on the Internet. The five previous editions have shown how the Internet may be used to address personal risks. We have contributed to creating tools and datasets, identifying and improving risk detection and estimation techniques, and applying and defining evaluation metrics...

This paper gives an outline of eRisk 2022, the CLEF conference’s sixth edition of this lab. Since the first edition, the main goal of our lab is to explore issues of evaluation methodology, effectiveness metrics and other processes related to early risk detection. Early alerting models may be used in a variety of situations, including those involvi...

Most of the new knowledge about our past that is generated in cultural heritage disciplines is produced in non-structured forms, such as project reports, monographs, or research papers. This proliferation of cultural heritage knowledge in textual discourse form requires support for information structuration and extraction of the semantic relations...

In 2017, we launched eRisk as a CLEF Lab to encourage research on early risk detection on the Internet. The eRisk 2021 was the fifth edition of the Lab. Since then, we have created a large number of collections for early detection addressing different problems (e.g., depression, anorexia or self-harm). This paper outlines the work that we have done...

Social networks constitute a valuable source for documenting heritage constitution processes or obtaining a real-time snapshot of a cultural heritage research topic. Many heritage researchers use social networks as a social thermometer to study these processes, creating, for this purpose, collections that constitute born-digital archives potentiall...

Automatic profiling models infer demographic characteristics of social network users from their generated content or interactions. Due to its use in business (targeted advertising, market studies...), automatic user profiling from social networks has become a popular task. Users’ demographic data is also crucial information for more socially concer...

Estudios acerca del impacto de los mecanismos de autoevaluación en la docencia en Ingeniería Informática señalan en los últimos años los beneficios de la autoevaluación como medio formativo en sí mismo, para alcanzar una evaluación continua real y para la mejora de la efectividad de los mecanismos de retroalimentación profesor-alumnado. Esto, unido...

Political bots, through astroturfing and other strategies, have become important players in recent elections in several countries. This study aims to provide researchers and the citizenry with the necessary knowledge to design strategies to identify bots and counteract what international organizations have deemed bots’ harmful effects on democracy...

This paper gives an outline of eRisk 2021, the CLEF conference’s fifth edition of this lab. The main goal of eRisk is to explore issues of evaluation methodology, effectiveness metrics and other processes related to early risk detection. Early alerting models may be used in a variety of situations, including those involving health and safety. This...

eRisk, a CLEF lab oriented to early risk prediction on the Internet, started in 2017 as a forum to foster experimentation on early risk detection. After four editions (2017, 2018, 2019 and 2020), the lab has created many reference collections in the field and organized multiple early risk detection challenges using those datasets. Each challenge fo...

There have been spectacular advances in many tasks of natural language processing (NLP) by making use of artificial intelligence (IA) techniques such as machine/deep learning (M/DL). However, these improvements do not affect all NLP tasks, specifically those that require deep linguistic knowledge, natural language understanding, semantic inference...

The intrinsic characteristics of humanities research require technological support and software assistance that also necessarily goes through the analysis of textual narratives. When these narratives become increasingly complex, pragmatics analysis (i.e., at discourse or argumentation levels) assisted by software is a great ally in the digital huma...

One of the current limitations of fuzzy linguistic descriptions of data is the lack of diversity of protoforms that can be used to linguistically summarize data. Despite an important effort in providing protoforms with improved semantics that are applicable to time series data or specific application domains, type-I and type-II fuzzy quantified sen...

Research in digital humanities involves the need for conscious and explicit handling of data uncertainty. Recently, some initiatives have highlighted the importance of considering this uncertainty from the conceptual model to the final phases of implementation of software tools. Although the conceptual proposals for handling data uncertainty in the...

Anthropological, archaeological, and forensic studies situate enforced disappearance as a strategy associated with the Brazilian military dictatorship (1964–1985), leaving hundreds of persons without identity or cause of death identified. Their forensic reports are the only existing clue for people identification and detection of possible crimes as...

Research in the digital humanities often involves vague information, either because our objects of study lack clearly defined boundaries, or because our knowledge about them is incomplete or hypothetical, which is especially true in disciplines about our past (such as history, archaeology, and classical studies). Most techniques used to represent d...

Requirements for the analysis, interpretation and reuse of information are becoming more and more ambitious as we generate larger and more complex datasets. This is leading to the development and widespread use of information about information, often called metainformation (or metadata) in most disciplines. The Digital Humanities are not an excepti...

As a result of the multifaceted dimension of the relationship between humans and computer technology, human–computer interaction (HCI) is a vast and complex field in which many disciplines and approaches have a place. This includes psychology, computer science, and user studies, among others. In recent years, this relationship has generated great i...

When working in digital humanities, we are often required to manage knowledge that is highly vague, either because it refers to things in the world lacking clear-cut boundaries, or because it is incomplete or approximate. The usual approaches to knowledge representation and information modelling, often taken from engineering or natural science disc...

Any knowledge generation process involves raw data comprehension, evaluation and inferential reasoning. These practices, common to different disciplines, are known as data analysis, and represent the most important set of activities in research contexts. Researchers use data analysis software methods and tools for generating new knowledge in their...

Archaeology constructs new knowledge through the interpretation of material evidence, which must be supported by arguments to be persuasive and accepted. Disagreements and conflicts usually arise on how different authors interpret the same facts or support their discourse. Therefore, new knowledge emerges in a dialogical manner rather than from mon...

Now that we have contextualized and motivated why it is important a co-research approach to assist via software knowledge generation processes, we are ready to focus on the archaeological domain and their particularities. As we have showed in previous chapters, archaeological data sets (and in general the conceptualization of the archaeological ent...

Over the course of the previous chapters, we have explored the co-research environment in software Engineering and archaeology.

A software system is not a conceptually one-dimensional artefact, whatever the purpose for which the software was conceived or the (in our case archaeological) data was collected.

The previous chapter presented a formal validation of the software models which make up the framework presented in this book, applied to the specific case study of A Romea. This validation demonstrates the capacity of the framework to provide the kind of software-assisted knowledge generation for archaeological datasets, which we aim to offer by wa...

The main objective of the research carried out here is determining and showing how it is possible for software.

The previous chapter described the conceptual support for the expression of all the archaeological subject aspects for a given case study using the framework proposed.

At this stage of our research, it’s time to put what we developed and learned into practice applying it to a real case study.

In the previous chapter, an in-depth exploration of the problem (how to use software to assist to the generation of knowledge in archaeology) was given, along with a description of existing studies in related areas.

Dealing with abstraction processes that takes part in the human mind is not an easy task. As other kind of research areas.

An adequate conceptualization of the domain involved is the first step in any software technique, process, tool or system that we would want to build.

In recent decades, the strategic importance of software data interaction and presentation techniques for the analysis of large volumes of data (Big Data), along with their use in decision making, has grown considerably with the appearance of emerging disciplines [148], professions [66] and techniques which assist human beings in the handling and in...

This book focuses on innovative strategies to manage and build software systems for generating new knowledge from large archaeological data sets The book also reports on two case studies carried out in real-world scenarios within the Cultural Heritage setting. The book presents an original conceptual framework for developing software solutions to a...

The growing needs to analyse and interpret large amounts of complex information has generalised the use of information about information, often called metainformation (or metadata). Metadata approaches and standards have proliferated in fields as diverse as medicine, meteorology, geography, cultural heritage or education, among others. These approa...

Due to humanities generally produce knowledge in textual formats (e.g. narrative conclusions or reports), a properly management of the humanities corpus needs methods for conceptualizing and extracting information from textual sources. Discourse analysis techniques allow extracting information in terms of the connection between discourse structure...

Specialists in the humanities and social sciences often construct models of the realities they work with; these models are usually expressed in natural language, as thesauri, or by similarly informal means. Conceptual modelling, a more formalised approach, has been used in other fields for some time, and we hypothesised that its usage in the cultur...

The exponential increase in availability of scientific papers, institutional reports or research monographies in digital contexts (i.e. in digital repositories, archives or social scientific networks) has led to the advancement of manual, semi-automatic or automatic-based methods to analyze these texts in the digital environment. These techniques c...

Information systems are composed of different dimensions of information: methodological, structural, architectural, etc. These dimensions appear connected in textual specifications created at early stages of information systems conception. These multidimensional textual specifications are particularly relevant in cases of information systems concei...

Process mining has been successfully used in automatic knowledge discovery and in providing guidance or support. The known process mining approaches rely on processes being executed with the help of information systems thus enabling the automatic capture of process traces as event logs. However, there are many other fields such as Humanities, Socia...

Process mining has been successfully used in automatic knowledge discovery and in providing guidance or support. The known process mining approaches rely on processes being executed with the help of information systems thus enabling the automatic capture of process traces as event logs. However, there are many other fields such as Humanities, Socia...

The daily emergence of new terms to denote existing concepts or new realities in daily life is common in our days. Thus, the use of these new terms in daily life, media, social network or oral communications involves the necessity of managing the agreement process of conceptualizing and correct defining of these new terms, in order to include them...

Advanced interaction techniques are necessary to explore the potential of large data-volume systems. In this context, rich internet application patterns were defined, but usually reduced to the development of social web applications. However, other types of applications, such as data-analysis applications, require also advanced interaction solution...

Most of the information that is used as input for the development of information systems is originally produced in non-structured forms, such as verbal communications or free-style text documents. Requirements specifications or documents associated to translation and internationalization of contents are good examples of these kinds of free-style do...

In the last years publishing industry and editorial boards are experimenting big changes, with a sustained growth in sales and use of new e-reading structures and products. This exponential growth involves reading through mobiles devices and tablets, a new environment with new challenges. However, the readers often need some training and skills dev...

Knowledge generation processes are traditionally related to the DIKW (data-information-knowledge-wisdom) hierarchy, a layered model for the classification of human understanding. Software components can be situated in one or several of these layers, or assist in the interfaces between two of them. Most of the knowledge generation processes that occ...

Obtaining models of cultural heritage that guarantee information interoperability and, at the same time, maintain a high degree of fitness to the problem at hand is not a trivial quest. This paper proposes a two-step approach to attain this, where particular models for each problem at hand are derived from a common, standardised Cultural Heritage A...

In most cases, the studied software in the cultural heritage domain has been designed from the perspective of other disciplines, such as forestry engineering, geography or documentation. In the Institute of Heritage Sciences, the cultural heritage is studied as a research topic, with methodologies to study the cultural heritage activities and consi...

Most of elderly people suffer physical degeneration that makes them particularly vulnerable to falls. Falls cause injuries, time of hospitalization, re-habilitation which is particularly difficult for the elderly and disabled. This paper presents a new system with advanced capacities for learning and adaptation specifically designed to detect falls...

Falls in the elderly and disabled people represent a major health problem in terms of primary care costs facing the public and private systems. This paper presents a multi-agent system capable of detecting falls through sensors in a mobile device and act accordingly at runtime. The new system incorporates a fall detection algorithm based on machin...